Most Download Articles

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

The Application, Problems and Development of China's Agricultural Smart Sensors Rui Yan, Zhen Wang, Yanhao Li, Zhemin Li, Xian Li Journal of Agricultural Big Data    2021, 3 (2): 3-15.   DOI: 10.19788/j.issn.2096-6369.210201 Abstract （1813）   HTML （98）    PDF（pc） （1468KB）（2974）       Knowledge map    Save Agricultural smart sensors are among the key technologies of intelligent agriculture. This paper describes the concept, characteristics, and implementation methods of smart sensors and introduces the composition, development, and application of agricultural smart sensors. The agricultural smart sensors were classified into three categories, based on the type of information they detect: life information, environmental information, and quality and safety sensors. The life information smart sensors detect plant and animal life information, and the environmental information smart sensors detect information about water, soil, livestock and poultry, and meteorological events. Currently, the application of agricultural smart sensors in China faces several problems. These include a low degree of integration (modular implementation), a heavy reliance on imports for the core components of agricultural smart sensors (sensor components and microcontroller), a low degree of intelligence, and limited application scope. The root causes of these problems mainly lie in the lack of core controllers dedicated to agriculture, the lack of self-developed high-end agricultural sensors, and the lack of dedicated wireless communication network protocols and high-precision smart sensor algorithms. The paper proposes some feasible countermeasures, such as manufacturing China’s “agricultural core” and high-performance MEMS sensors, constructing special agricultural wireless networks, and developing high-performance smart algorithms. If implemented, these countermeasures will help promote the intelligent manufacturing of agricultural smart sensors in China. With the rapid development of smart agriculture, China’s smart manufacturing of agricultural smart sensors is crucial. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Progress in the Development and Sharing of Big Data in Agricultural Science between China and Foreign Countries Zhao Ruixue, Zhao Hua, Zhu Liang Journal of Agricultural Big Data    2019, 1 (1): 24-36.   DOI: 10.19788/j.issn.2096-6369.190103 Abstract （1116）   HTML （96）    PDF（pc） （1011KB）（2399）       Knowledge map    Save Big data in agricultural science refers to the mass of scientific data that has accumulated and been integrated over a long period in scientific and technological activities associated with agriculture. These data not only directly reflect the overall basic level of agricultural science and technology in a country, but also affect the sustained and stable development and improvement of agricultural science and technology in the long term; they are valuable for resource preservation, development and use. As part of data-intensive scientific research, big data in agriculture are basic strategic resources that support the development of innovations in agricultural science and technology, and the development of modern agriculture, which are related to the country's strategic interests and security. To promote sharing and use of scientific big data in agriculture, literature reviews, websites survey and comparative analysis have been conducted. This review summarizes the development strategies and sharing policy of scientific big data , and analyzes the progress of the development and sharing of big data in agriculture. Focusing on the future development of big data in agriculture and providing a reference for the development and sharing of such data in China, this review provides suggestions for policy formulation and implementation, data development models and resource integration, data opening and publication, and other issues. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Research and Application of Big Data in Agriculture Jiang Hou, Yang Yaping, Sun Jiulin Journal of Agricultural Big Data    2019, 1 (1): 5-10.   DOI: 10.19788/j.issn.2096-6369.190101 Abstract （2084）   HTML （230）    PDF（pc） （2372KB）（2342）       Knowledge map    Save Against the background of China's strategy of promoting rural revitalization, big data has become a hot topic in agricultural research and application. Building on the basic characteristics of big data, this paper introduces the concept of agricultural big data and its typical characteristics. It summarizes current approaches for collecting agricultural big data, describes the application system and key technologies of an agricultural big data platform, and discusses the use of agricultural big data for agricultural decision-making, intelligent production, market match, agrometeorology and food safety. Finally, the paper examines the current difficulties in using agricultural big data. In sum, the paper contributes a foundation of understanding for the innovation and development of agricultural big data. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Progress in the Application of Big Data in Agriculture in China Zhou Guomin Journal of Agricultural Big Data    2019, 1 (1): 16-23.   DOI: 10.19788/j.issn.2096-6369.190102 Abstract （2093）   HTML （229）    PDF（pc） （915KB）（2261）       Knowledge map    Save Big data have become a new resource in modern agriculture and an important focus for technological innovation in agricultural science. Big data not only promote the production, operation, management and service provisions of modern agriculture, but also advance the integration of primary, secondary and tertiary industries. In developed regions such as Europe and the United States, special attention has been paid to the role of big data in modern agriculture; in China, research and application of big data in agriculture have also developed rapidly. Agricultural data generally have large spatial and temporal coverages, and are difficult to collect and complicated to process. Therefore, it is of great significance for the research and application of agricultural big data in China to systematically review the progress regarding the application of such data and further clarify the direction of future development. In this study, a literature review is combined with related scientific research; definitions of big data in agriculture proposed by different researchers are compared and analyzed; concepts and matters relating to big data in agriculture are explained; and progress in the application of big data in agriculture in management and policy, engineering and application, and technology and infrastructure in recent years is systematically summarized. Finally, based on the current situation regarding the development of big data in agriculture in China, this review suggests three aspects where special attention should be paid to promote its development: the issues of platform and data, demand and application, and trade and sharing. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

The Agricultural Pest and Disease Image Recognition Dataset in Nanjing, Jiangsu Province, in 2023 WANG BoYuan, GUAN ZhiHao, YANG Yang, HU Lin, WANG XiaoLi Journal of Agricultural Big Data    2023, 5 (2): 91-96.   DOI: 10.19788/j.issn.2096-6369.230214 Abstract （1570）   HTML （219）    PDF（pc） （4768KB）（2237）       Knowledge map    Save Agricultural pests and diseases pose a serious threat to crop yield and quality, making accurate and efficient detection and identification of pests and diseases crucial in agricultural production. In this paper, we propose a comprehensive agricultural pests and diseases dataset, which includes agricultural pest detection dataset, agricultural disease detection dataset, agricultural disease classification dataset, and rice phenotype segmentation dataset. By collecting and curating data from public sources and academic papers, we ensured the diversity and representativeness of the dataset. Rigorous quality control and validation measures were implemented during the data filtering, cleaning, and annotation processes to ensure the accuracy and reliability of the dataset. This dataset can be used for agricultural pest and disease recognition, as well as rice phenotype identification and other agricultural visual tasks. It provides valuable resources for agricultural pest and disease research and contributes to the sustainable development of agricultural production. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Big Data of Plant Phenomics and Its Research Progress Chunjiang Zhao Journal of Agricultural Big Data    2019, 1 (2): 5-14.   DOI: 10.19788/j.issn.2096-6369.190201 Abstract （2800）   HTML （233）    PDF（pc） （1041KB）（2202）       Knowledge map    Save Plant phenomics is capable of acquiring gigantic multi-dimensional, multi-environment, and multi-source heterogeneous plant phenotyping datasets through integrated automation platforms and information retrieval technologies, based on which the big-data driven plant phenomics research is established. This emerging research domain aims to systematically and thoroughly explore the internal relationship between "gene-phenotype-environment" at the omics level, so that phenomics methods can be utilized to unravel the formation mechanism of specific biological traits in a comprehensive manner. As a result, it is greatly catalyzing the research progress of functional genomics, crop molecular breeding, and efficient cultivation. In this paper, we summarized the background, definition, initiation, and features of the big-data driven plant phenomics, followed by a systemic overview of the progress of this field, including the acquisition and analysis of plant phenotyping data, data management and relevant database construction techniques for administering big data generated, the prediction of phenotypic traits, and its connection with the plant omics research. Furthermore, this paper focuses on discussing present problems and challenges encountered by both plant research and related applications, including (1) the standardization of collecting plant phenotypes, (2) research and development (R&D) of diverse phenotyping devices, supporting facilities, and low-cost phenotyping equipment, (3) the establishment of big data platforms that can openly share phenotyping data and phenotypic traits information, (4) theoretical approaches for fusion algorithms and data mining techniques, and (5) collaborative, sharing and interactive mechanisms for the plant phenomics community to adopt. Finally, the paper puts forward suggestions in four aspects that need to be strengthened: (1) systematic design and standards of plant phenomics research, (2) revealing the mechanism of plant phenotype and environtype to facilitate intelligent equipment R&D, (3) the establishment of big data for plant phenomics, and (4) the formation of collaborations through academic networks and specialized research groups and laboratories. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

The Development Direction of Fresh Agricultural Products Supply Chain in China after COVID-19 Dongnan Li, Guoyang Pan, Qian Zhou, Bin Li Journal of Agricultural Big Data    2020, 2 (3): 42-51.   DOI: 10.19788/j.issn.2096-6369.200305 Abstract （2413）   HTML （79）    PDF（pc） （687KB）（1915）       Knowledge map    Save Fresh agricultural products mainly include vegetables, fruits, meat, eggs, milk, and aquatic products. The degree of freshness of perishable primary products determines their own value. In 2020, the COVID-19 outbreak has had a huge impact on people's lives, further affecting the development process of China's fresh agricultural products industry and posing new challenges to the existing supply chain system of fresh agricultural products. Our investigation and analysis show that during the epidemic period, there were negative phenomena such as the contradiction between supply and demand of fresh agricultural products, the slow information transmission of the supply chain, and the narrow purchase channels of suppliers. At the same time, we also identify positive outcomes, such as the recovery of cold chain logistics and new developments in the fresh agricultural supply chain. To further understand the outbreak period, we conducted a survey on the running status of fresh agricultural products. This paper investigates the rise in purchases of fruits and vegetables by studying data from 500 consumers in seven regions including central and southern region. We also investigate the problem of the quality of fruits and vegetables and the future development of the fruit and vegetable industry, and we identify three ways of understanding the changes in the fruit and vegetable supply system since the purchasing outbreak. The study concludes that during the imbalance in the supply and demand of fruits and vegetables, when demand for fruits and vegetables is high, problems arise because of limitations of the fresh product supply system in China. Four factors are important to the future development of the fresh agricultural products supply chain system: the integration of the online supply chain model; the wisdom of the logistics supply chain; the strategic alliance model of agricultural products supply chain; and the demand of the agricultural products supply chain pattern. Together these four factors can ensure the stability and orderly development of the fresh agricultural products industry in the context of normalized epidemic prevention. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Accurate Precipitation Nowcasting with Meteorological Big Data: Machine Learning Method and Application Zhang Chenyang, Yang Xuebing, Zhang Wenshen Journal of Agricultural Big Data    2019, 1 (1): 78-87.   DOI: 10.19788/j.issn.2096-6369.190108 Abstract （1179）   HTML （34）    PDF（pc） （5172KB）（1886）       Knowledge map    Save Accurate precipitation nowcasting is essential for agricultural production, hydrological monitoring, flood mitigation, large organizations, and electrical systems. Because of the high uncertainty of weather systems, the performance of precipitation estimation by conventional meteorological methods based on physical models and statistical analysis is unsatisfactory. Determining how to improve the accuracy of precipitation estimation and forecasting in high resolution is challenging. This study proposes the method of terrain-based weighted random forests (TWRF) for radar-based quantitative precipitation estimation (QPE). This method can be regarded as a generalization of random forests via consideration of variations in the vertical profile of reflectivity (VPR) and orographic enhancement of precipitation for complex terrains. The performance was tested within the 45~100 km range of the Z9571 radar in Hangzhou, China during rainfall events in June and July, 2014. The experimental results showed that TWRF is better than conventional methods and random forests, and further indicate that utilization of the entire VPR and terrain-based modeling are effective for radar QPE. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Research and Design of Agricultural and Rural Digital Resources Architecture Dong Tang Wenfeng Du Weicheng Sun Guangrong Jia Xinwei Liang Journal of Agricultural Big Data    2019, 1 (3): 28-37.   DOI: 10.19788/j.issn.2096-6369.190303 Abstract （1121）   HTML （43）    PDF（pc） （586KB）（1703）       Knowledge map    Save The digital economy is a new form of economic and social development that arose after the agricultural economy and industrial economy, and it is one of the important engines leading global economic growth. The digital economy has become the most active area of China's economic development and an effective way to achieve sustainable economic development. Agriculture is the basic industry in China, and digital agriculture is an important part of China's digital economy. The development of digital agriculture is conducive to the realization of accurate decision-making and guidance in agricultural production, the promotion of agricultural competitiveness, and the sharing of digital economic development dividends among all farmers. The key factor of production in the digital economy is digital knowledge and information, namely digital resources. Digital resources in agricultural and rural areas include information such as databases, electronic documents, pictures, videos, web pages, and remote sensing images. At present, China's agricultural and rural informatization level is not high, and digital resources are relatively scarce. There are some practical problems in agricultural and rural digital resources, such as decentralization, inconsistent standards, and a lack of a digital resource management system covering the whole life cycle of data. It is necessary to carry out research and design work on the architecture of agricultural and rural digital resources, establish relevant standards and norms from a top-level perspective, improve and enhance the organizational form of digital resources, and build a blueprint for agricultural and rural digital resources. This paper analyses the classification of agricultural and rural digital resources by the Food and Agriculture Organization of the United Nations(FAO) United States Department of Agriculture(USDA) and designs the whole life cycle of digital resources covering agriculture and the countryside. This life cycle includes planning, design, collection, storage, processing, management, service, and use of data. Further, this paper establishes the architecture of digital resources in agriculture and the countryside. It focuses on the structure of an agricultural and rural thematic database, and presents the key construction tasks and development suggestions for improving the agricultural and rural digital resources system. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

International Comparative Study on Management Mode of National Science Data Center Mingrui Huang, Guoqing Li, Jing Li, Xiangtao Fan Journal of Agricultural Big Data    2019, 1 (4): 14-29.   DOI: 10.19788/j.issn.2096-6369.190402 Abstract （548）   HTML （10）    PDF（pc） （933KB）（1548）       Knowledge map    Save This paper presents models of the development, management, evolution of national science data center systems in the United States, the United Kingdom， and China. Our methods include network research and literature analysis to analyze the construction process, management mode and evaluation methods of these science data center sys‐ tems. In the United States, national data centers, domain-level data centers, and resource-node data centers exist and share data in an orderly manner, forming a data flow model from“the capillary to the aortic convergence.”In the United Kingdom, national level and field research data centers form a data flow model with“several parallel aortas”, in which data is directly obtained from the national and domain-level data centers. In China, similar to the US convergence model, national science data centers are established in key areas throughout the country to stan‐ dardize science data management and plan and build science data centers in the regions. The regional data cen‐ ters are encouraged to submit data to national data centers, thereby promoting the flow of scientific and technological resources from the relevant fields to the national platforms for convergence and integration. Our paper also considers the adjustment list released by the National Science Data Centers of China in June 2019, discussing the ecological correlation in scientific data management of National science data center and its science data management model relative to the new model that China's science data management may face. It is argued that the National Scientific Data Centers will play an important role in promoting the development of big science in China and provide support for the development of science and technology in the era of big data. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Design of an Agricultural Product Supply Chain Management System using Blockchain Technology Chenxue Yang, Zhiguo Sun Journal of Agricultural Big Data    2020, 2 (2): 74-83.   DOI: 10.19788/j.issn.2096-6369.200208 Abstract （1361）   HTML （60）    PDF（pc） （1013KB）（1540）       Knowledge map    Save Agriculture is the main industry in China. A safe, credible, stable, traceable, information-sharing, and large-throughput agricultural supply chain system is needed to achieve agricultural informatization. At present, information about China’s agricultural product supply chain has been stored in a centralized database and file system, with weak information management capabilities, leading to problems such as theft, tampering, deletion, and inconsistencies. In light of these problems, an efficient extraction method which combines an interstellar distributed file system and smart contract technology for heterogeneous information data in agricultural product supply chain is established. This method achieved fast extraction of large heterogeneous information transaction logs which including agricultural product production information, recording transportation information, consumer credit information, farmer-consumer transaction services. All kinds of information transaction logs and transaction records are stored in blockchain and IPFs network respectively. It proposed an access control method for agricultural product supply chain information data based on blockchain smart contracts, combined with an access method based on IPFS hash addressing, which can effectively ensure different agricultural production and operation participants access data within their authorities. A data management system of agricultural products supply chain based on blockchain technology is designed, which can ensure the transforming and upgrading of agriculture, thereby helping farmers increase their income and eliminate poverty. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Construction of an Agricultural Big Data Platform for XPCC Cotton Production Xin Lv, Bin Liang, Lifu Zhang, Fuyu Ma, Haijiang Wang, Yangchun Liu, Pan Gao, Zhangze, HouTongyu Journal of Agricultural Big Data    2020, 2 (1): 70-78.   DOI: 10.19788/j.issn.2096-6369.200109 Abstract （2116）   HTML （77）    PDF（pc） （1192KB）（1515）       Knowledge map    Save The Xinjiang Production and Construction Corps (XPCC) have created a modern cotton planting system with regional characteristics in China. This new system advances Chinese production techniques in the aspects of agricultural intensification, scale, development of agricultural machinery, and application of modern agricultural technology. During the years of systematic development and performance, massive data were accumulated by XPCC in the cotton planting field. As big data technology has become an important driving force for the development of intelligent agriculture in China, how to apply this technology to further improve the intelligent level of the cotton planting system and realize the healthy, efficient, and sustainable development of the whole cotton industry chain is a key problem in strengthening and enhancing XPCC’s ability to reclaim and defend the Chinese border in the information age. Thus, we constructed a big data platform that covers the entire industrial chain for cotton production in China based on a mature commercial big data storage and analysis system framework to promote the cooperation of industry, colleges, and institutes for cotton production big data in the XPCC. This platform was comprised of data, model, system, and application layers from the bottom up. In each layer, the cotton production chain was analyzed using five dimensions of agricultural resources, agricultural monitoring, production management, agricultural machinery scheduling, and market prediction. After completion, the developed platform intends to provide big data for comprehensive management and sharing, remote-sensing monitoring, agricultural machinery operation monitoring and maintenance, intelligent decision-making, quality traceability, and market early warning and prediction services for cotton production to potential users involved in cotton production and management. Finally, this paper analyzes the problems encountered in data sharing, model upgrades, and service modes in the process of platform research and development, and puts forward some suggestions to provide references for agricultural big data resource sharing and platform construction in China. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A Framework for Agricultural Big Data Standards Yanmin Yao, Yuqi Bai Journal of Agricultural Big Data    2019, 1 (4): 76-85.   DOI: 10.19788/j.issn.2096-6369.190408 Abstract （1312）   HTML （54）    PDF（pc） （622KB）（1487）       Knowledge map    Save As agricultural production, management, operations, and services enter the big data era, standardization is becoming increasingly important in ensuring the comparability between the collected results generated by diverse devices and instruments, compatibility between multi-source data, integrability between multiple types of data analysis systems, the quality of agricultural products at a global scale, and the coherence between different production and management processes. This article summarizes the domestic and foreign standards in the field of agricultural big data. There are currently few standards and norms that can directly guide the development of agricultural big data. Research studies for a big data standards framework are critically needed to guarantee and promote the continuous and in-depth development of agricultural big data applications. This paper draws on the methods proposed by the International Organization for Standardization and International Electrotechnical Commission to analyze the standard system for a framework from the perspectives of enterprice, information, computation, engineering, and technology. From informational and computational perspectives, the needs in developing agricultural big data standards were analyzed, and a framework for an agricultural big data standard system is proposed. This framework contains standards for fundamental guidelines, general practice, and applications. Among these needs, the fundamental guidelines for agricultural big data are the basis for the formulation and coordination of agricultural big data standards, including national big data-related laws, regulations, policies, and national standards related to big data. The general standards for agricultural big data include four categories of common agricultural standards: i.e., agricultural big data foundation, agricultural big data collection and processing, agricultural big data management, and agricultural big data-sharing services. The agricultural big data application standards are the agriculture standards and regulations formulated for specific parts of the whole process of agricultural big data, such as agricultural elements and ownership information, agricultural production processes, and agricultural operation and management. The design of the agricultural big data standard system is a complex and huge systematic project that requires the participation of multisector and multidisciplinary personnel, and it is one of the top priorities in agricultural big data development. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A Survey of Big Data Deep Learning Systems and a Typical Agricultural Application Lingxu Zhang,Rui Han,Wenming Li,Yinxue Shi,Chi Liu Journal of Agricultural Big Data    2019, 1 (2): 88-104.   DOI: 10.19788/j.issn.2096-6369.190208 Abstract （1250）   HTML （52）    PDF（pc） （2358KB）（1393）       Knowledge map    Save With the rapid development of information age, big data has become the key technology to promote people's production and daily life to undergo major changes, and plays a very important part in the development of various fields, including agriculture. In order to effectively analyze and utilize the big data and make it play its maximum value, the research and development of deep learning technology plays a decisive role. In this context, this paper gives a detailed introduction to the main technical characteristics and development of big data deep learning system, including deep learning model (such as CNN model and RNN model), optimization algorithm, big data learning framework, hardware configuration and so on. This paper also explains the technical characteristics and development process of five mainstream deep learning frameworks, including PyTorch, and compares the strengths and weaknesses of these frameworks. In addition, this paper also mentions the typical application of big data deep learning system in agriculture, "Grape Leaf Downy Mildew Forecasting System Based on Big Data", and takes its key step "Grape Leaf Classification and Recognition Process" as an example to introduce its working principle in detail, including data collection, sample feature extraction, clustering algorithms, classification algorithms and result analysis. This system uses big data and deep learning technology to help detect and prevent downy mildew of grape leaves. Finally, this paper introduces the main development trend of big data deep learning system, as well as the problems requiring attention in agricultural research and application. Today, big data deep learning system is playing an increasingly important role and has been widely used in the field of agricultural data analysis, including crop pest prediction. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Spectral and Imaging Datasets of Apple Leaf Disease and Insect Pests in China in 2015 Fei Gao, Xiaoli Wang, Tingting Liu, Zhuang Li, Rui Man Journal of Agricultural Big Data    2020, 2 (4): 120-124.   DOI: 10.19788/j.issn.2096-6369.200415 Abstract （1550）   HTML （93）    PDF（pc） （1305KB）（1023）       Knowledge map    Save China’s apple planting area and total output rank first in the world, but most of the current collection of spectral and imaging data from fruit trees focuses on apple leaf diseases and insect pests. In this study, the spectral reflectance and imaging data from apple leaves having three different diseases, spot leaf fall and powdery mildew, or the red spider insect pest, were collected from the National Apple Resource Nursery to provide data for the effective identification of apple leaves exposed to different diseases and insect pests. This will provide a foundation for the future use of aerospace remote sensing to monitor large-scale fruit tree diseases and associated insect pests. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Development and Visions of Blockchain Technology Hui Li, Yuming Yuan, Wenqi Zhao Journal of Agricultural Big Data    2020, 2 (2): 5-13.   DOI: 10.19788/j.issn.2096-6369.200201 Abstract （2210）   HTML （98）    PDF（pc） （1126KB）（1014）       Knowledge map    Save Blockchain (or distributed ledger) technology was introduced in 2008, when the famous Bitcoin cryptocurrency was initiated. Blockchain has been undergoing rapid growth in both academia and industry. Today, it is no exaggeration to say that blockchain has become a new, independent research topic—not a subtopic subsumed within cryptocurrencies. From a technical perspective, blockchain technology is based on various fundamental computing technologies, such as advanced cryptography, distributed data storage, peer-to-peer networking, and distributed consensus protocols. Generally, blockchain technology involves creating a shared, distributed ledger: that ledger can offer great flexibility and potential in resolving many important challenges in a complex computing context that involves multiple parties. Examples of such challenges include achieving mutual trust, privacy protection, and data consistency in large-scale business scenarios. Many business applications have already covered a broad range of industrial services, such as those related to finance, governance, medicine, and city construction. Blockchain technology is becoming increasingly adopted and applied; however, the current design of blockchain is practically far from sufficient—especially when dealing with critical domain challenges. Specifically, the key limitations of blockchain mainly derive from poor system scalability, weak resilience to external security attacks, and lack of computing interfaces for regulatory processes. Conversely, it is the very shortcomings of blockchain technology that motivate research efforts into many related technologies. Based on conventional blockchain design, new functional extensions and cryptography technical optimizations have been continuously proposed by researchers and practitioners: the aim is to make blockchain technology more practically applicable and meet various demands of different business users. In this overview paper, using the latest findings from both academic and industrial research, we systematically present the general architecture of blockchain technology with its five functional layers. The five-layered architecture comprises the following: a data layer; a network layer; a distributed consensus layer; a smart contract layer; and an application layer. We also provide a technical description of key theories and important techniques related to each functional layer. From the proposed general architecture of blockchain technology, we offer an in-depth explanation of its core technical extensions with respect to the following: blockchain integration with existing computer network techniques; the blockchain framework itself and important modules; and underlying critical cryptography techniques. Further, we discuss potential contributions that these promising technical extensions could provide with respect to reshaping and optimizing blockchain technology. Finally, following current developments with blockchain technology and its existing mainstream applications, the general views about future challenges and important directions for this technology is to facilitate future follow-up research. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A Review of Agricultural Supply Chain Management and Its Prospects for the Future Ganqiong Li, Xin Li, Longhua Zhao, Shiwei Xu Journal of Agricultural Big Data    2020, 2 (3): 3-12.   DOI: 10.19788/j.issn.2096-6369.200301 Abstract （1208）   HTML （60）    PDF（pc） （1052KB）（937）       Knowledge map    Save Agricultural supply chain is an indispensable part in the construction of modern agricultural market system in China. The establishment of a modern agricultural supply chain system is of great significance to promote the integrated development of primary, secondary and tertiary industries in rural areas, improve the modernization level of circulation, and enhance agricultural competitiveness and voice in the international market. Since entering WTO, China agriculture is highly open, and increasingly affected by the global agricultural supply chain in China. Strengthening agricultural supply chain management has become the focus of academic research, the difficulties of government concern and management control as well as the focus of agricultural producers and operators under the new situation of the global spread of COVID-19. Research of agricultural supply chain management started late in China, but it has developed rapidly in the past 10 years. Through literature research and related scientific research practice, this paper analyzes and compares the definitions of agricultural supply chain from different aspects, elaborates the concept and connotation of agricultural supply chain, and emphatically summarizes the research and application progress of agricultural supply chain management in theoretical innovation, mode innovation, risk management and technology innovation. Finally, combined with the new situation at home and abroad and the actual situation in China, the study puts forward the future research direction and hot areas that need to be further studied such as agricultural supply chain emergency management under emergencies, agricultural supply chain governance ability under the background of economic globalization, construction and management of green agricultural supply chain system, innovation of intelligent agricultural supply chain, and provide suggestions for promoting the development of agricultural supply chain management in China. Reference | Related Articles | Metrics | Comments（0）

Select

Big Data Applications and Construction for the Shandong Potato Industry Jia Ruan Huaijun Feng Wenjie Zhao Journal of Agricultural Big Data    2020, 2 (1): 29-35.   DOI: 10.19788/j.issn.2096-6369.200104 Abstract （638）   HTML （10）    PDF（pc） （727KB）（889）       Knowledge map    Save This paper analyzes the existing data for the Shandong potato industry to understand its production, circulation, storage, and processing characteristics, among other elements. According to the data analysis of production in the Shandong potato industry, potatoes are planted in spring and autumn, with Tengzhou and Jiaozhou as the main planting areas. According to the data analysis of circulation, the market price fluctuation shows the rule of “three years/one cycle,” with outstanding and refined management benefits. Potato exports from Shandong are the highest among potato exports in China. According to the data analysis of storage, the potato storage capacity can still meet local needs and cold storage constructions have been developed to include more modern and constant temperature storage facilities. According to the data analysis of processing, improvement is still needed in processing capacity. This paper outlines the construction of a big data platform for a single variety of Shandong potato. Modern precision agriculture in production will develop a measurement system that integrates all production elements and spaces will be constructed to guide intelligent production. In the circulation element, online e-commerce trading and safety traceability systems for potatoes will be constructed in addition to developing the quality of agricultural products. For the storage element, a potato refrigeration–packaging industry will be promoted, including the accelerated establishment of cold storage, warehouse storage, and logistics alliances. In the processing element, a staple potato food processing industry will be developed alongside the promotion of the cluster development of processing enterprises. We will effectively strengthen top-level designs, consolidate and integrate research into key technologies for big data, and promote data sharing, opening up, development, and utilization. By speeding up the adjustment of regional layouts, preventing excessive fluctuation of potato prices, and strengthening the information analysis and early warning for the whole industry chain, we can better lead the sustainable and high-quality development of the Shandong potato industry. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Preliminary Exploration of Big Data Security Supported by Blockchain in Agriculture Zhongfu Sun, Juncheng Ma, Feixiang Zheng, Keming Du Journal of Agricultural Big Data    2020, 2 (2): 25-37.   DOI: 10.19788/j.issn.2096-6369.200203 Abstract （712）   HTML （23）    PDF（pc） （1259KB）（869）       Knowledge map    Save Big data constitutes a core technology for smart agriculture. However, there are a number of issues related to security with big data that could limit progress with smart agriculture. Following the speedy development of blockchain technology and in light of its intrinsic security characteristics. Big data could provide a new driving force and means for big data to be safely applied. This paper addresses some challenges related to supporting the safe development of big data. Briefly described the current status of China's agriculture and the background of the development of smart agriculture. Regarding basic issues concerning smart agriculture, a systematic study is made of the mutual relationship between agricultural big data security and blockchain technology which involves a brief introduction to the significance of big data, existing risks of big data, current challenges, and measures to promote bigdata safety. Comprehensive analyzed the security characteristics of the blockchain, described the supporting status and roles of blockchain in big data security, and explained three core directions of blockchain data security, which are data confidentiality, integrality, and availability. In conclusion, proposed suggestions and future applications on how to use blockchain to help the security of big data development. Reference | Related Articles | Metrics | Comments（0）

Select

Research Progress of Multimodal Knowledge Graph in Agriculture Jiayun Chen, Xiangying Xu, Yonglong Zhang, Ye Zhou, Hongjiang Wang, Changwei Tan Journal of Agricultural Big Data    2022, 4 (3): 126-134.   DOI: 10.19788/j.issn.2096-6369.220320 Abstract （762）   HTML （32）    PDF（pc） （802KB）（847）       Knowledge map    Save Incorporating entities of multiple modalities and their semantic relationships on the basis of traditional knowledge graph, multimodal knowledge graph provides important information in the form of text, image and sound. It plays an important role in eliminating ambiguity and supplementing visual knowledge. In recent years, under the background of the rapid development of agricultural informatization and intelligence, knowledge graph technology has attracted extensive attention. In this article, the concepts of knowledge graph and multimodality are introduced in detail. Meanwhile, technical methods such as multimodal representation learning are elaborated from the perspective of graph construction. For the applications of multimodal knowledge graph in agriculture, we focus on the research of agricultural intelligent question answering system, plant diseases and pests’ identification, agricultural product recommendation and so on. At the same time, the challenges in construction and development of agricultural multimodal knowledge graphs are prospected and analyzed. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

The Status and Trends of Scientific Data Sharing Systems Yunting Li, Liangming Wen, Lili Zhang, Jianhui Li Journal of Agricultural Big Data    2019, 1 (4): 86-97.   DOI: 10.19788/j.issn.2096-6369.190409 Abstract （997）   HTML （33）    PDF（pc） （800KB）（785）       Knowledge map    Save Data-intensive research is emerging as a new paradigm for science discovery in the era of big data, and the use of open data has become common in the scientific community. Over time, different models of scientific data sharing have emerged, including scientific instruments models, data platforms models, data publishing models, crowdsourcing and data market models. Correspondingly, a variety of solutions have emerged for different fields and applications, such as data repositories, data federated services systems, data distribution systems, and on-demand computing and analysis cloud services systems. This paper examines development and future trends in scientific data sharing systems, using the Big Earth Data Cloud Services Platform as an example. It analyzes and compares the typical services and technical characteristics, using scenarios and representative systems of the above-mentioned four types of mainstream scientific data sharing systems. Our analysis suggests that future scientific data sharing systems will focus on the need to manage the full life-cycle of scientific data and will converge into a cloud service system providing functions such as data acquisition, storage, distribution and sharing, analysis, and intelligent services. By making data FAIR (Findable, Accessible, Interoperable and Reusable), machine understandable and AI-Ready, promote the formation of data sharing eco-systems. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Progress in the Application of Big Data in fishery in China Jinxiang Cheng, Yingze Sun, Jing Hu, Xue Yan, Haiying Ouyang Journal of Agricultural Big Data    2020, 2 (1): 11-20.   DOI: 10.19788/j.issn.2096-6369.200102 Abstract （1104）   HTML （44）    PDF（pc） （615KB）（766）       Knowledge map    Save Big data has become an essential resource for green fisheries, and is an important focus for innovation in fisheries science and technology. Big data promotes the production, operation, management, and service provisions of fisheries, and plays a pivotal role in advancing the integration of primary, secondary, and tertiary industries in fisheries. China is the largest aquaculture country in the world, and attaches great importance to research and application development of big data in modern fisheries. For historical and practical reasons, fisheries big data is characterized by diversified resource channels, complex structures, uneven quality, wide application scope, and low overall data quality. Therefore, for research on, and application of fisheries big data in China, it is important to review the progress regarding the application of such data systematically, and clarify the direction of future development. Based on literature research and related scientific research practices, this article compares and analyzes the definitions of fisheries big data by different scholars; elaborates on the concept of fisheries big data; introduces the multiple sources and main characteristics of fisheries big data; and reviews the management and policy progress of fisheries big data. The development and application of fisheries big data in recent years have focused mainly on scientific research, aquaculture management, resource investigation, and economic circulation. In combination with engineering practice, this article explores the scenario application of fisheries big data. Finally, based on the current situation, it identifies the problems and challenges, and provides suggestions for further promoting the development of fisheries big data in China. Reference | Related Articles | Metrics | Comments（0）

Select

Research and Application of Citrus Big Data Qiuzi Wen‑Han, Yongqiang Zheng, Yang Liu Journal of Agricultural Big Data    2021, 3 (1): 33-44.   DOI: 10.19788/j.issn.2096-6369.210104 Abstract （1019）   HTML （34）    PDF（pc） （1772KB）（749）       Knowledge map    Save Using the citrus industry chain model as the basic framework, this paper proposes an explicit definition of Citrus Big Data. For each of the four main parts of the citrus industry chain, i.e., production resources, planting operations, processing, storage and transportation, and marketing, the composition of data, acquisition methods and challenges in applications of its core data resources are analyzed, respectively. Applications of typical data technologies such as product standardization, image recognition, meteorology forecasting, data visualization, and digital traceability in the citrus industry are systematically reviewed. Cases studies on Coca Cola orange juice, Chongqing citrus and Gannan umbilical orange are presented, demonstrating that big data technology is playing a more and more important role in the citrus industry, aiding green farming, disease and insect pest control, production increase, and improvement of fruit commodity rates. In China, research on citrus has entered a stage of rapid development since 2007, and has made great progresses in talent training, fundamental research, and transformation and application of scientific research results, but research on the application of the new generation information technologies such as big data and artificial intelligence, is still limited. Major citrus production regions in southern China are actively exploring the feasibility route of digital transformation for citrus industry. As a core resource for industrial upgrading and digital transformation, Citrus Big Data has a wide range of applications and great potential for growth. Application of Citrus Big Data in China is still in its infancy, facing many challenges such as equality in science and technology, data sharing, development of key models and algorithms, etc. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Developing cost-effective and low-altitude UAV aerial phenotyping and automated phenotypic analysis to measure key yield-related traits for bread wheat Guohui Ding,Hao Xu,Mingxing Wen,Jiawei Chen,Xiue Wang,Ji Zhou Journal of Agricultural Big Data    2019, 1 (2): 19-31.   DOI: 10.19788/j.issn.2096-6369.190202 Abstract （1151）   HTML （128）    PDF（pc） （5195KB）（740）       Knowledge map    Save [Multi-scale plant phenotyping technologies are capable of collecting big vision-based and spectroscopic datasets, based on which reliable phenotypic analysis can be carried out through a range of computational algorithms based on computer vision and machine learning techniques. Quantitative traits measurement is key to crop genetics, breeding, cultivation and agricultural practices, because they can be used to dynamically evaluate yield, quality and stress resistance in a high-throughput and reproducible manner. As an important staple crop in China, it is essential to establish a systematic approach to monitor wheat growth and quantify yield-related traits during key growth stages. In this work, we firstly reviewed important yield-related traits for bread wheat and then developed a field phenotyping approach to collect a number of common traits using cost-effective and low-altitude unmanned aerial vehicles (UAVs). Based on the visible spectrum images acquired in a field experiment, we utilized professional software (i.e. Pix4Dmapper) to stitch UAV sub-images as well as to reconstruct 3D point cloud to represent the whole experimental field. After this phase, we developed an automated traits analysis pipeline to produce the vegetation map (e.g. Excess-Green index, ExG) and measure important yield-related traits. We have quantified plant height, vegetation index (e.g. ExG) and leaf area index at five key growth stages for 18 wheat genotypes. Our work validates that yield-related traits can be acquired through cost-effective UAVs, which can lower the threshold of conducting field phenotyping and reliable phenotypic analysis. Our work also exhibits a promising approach for research groups and organizations to follow standardize data collection, phenotyping data ontology, as well as the utilization of open-source analytic libraries to develop high-throughput phenotypic analysis techniques in crop phenotyping research. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Analysis and Application of High-throughput Plant Phenotypic Big Data Collected from Unmanned Aerial Vehicles Peisen Yuan, Mingjia Xue, Yingjun Xiong, Zhaoyu Zhai, Huanliang Xu Journal of Agricultural Big Data    2021, 3 (3): 62-75.   DOI: 10.19788/j.issn.2096-6369.210307 Abstract （1557）   HTML （68）    PDF（pc） （1209KB）（734）       Knowledge map    Save Plant phenotypes refer to the physical, physiological and biochemical characteristics and traits that are determined or influenced by genes and environmental factors. Accurate and rapid access to plant phenotypic information under different environmental conditions, and the analysis of the genetic and performance patterns of their genomes, can effectively promote research on the correlation between genomic and phenotypic information. The Unmanned Aerial Vehicle (UAV) high-throughput plant phenotyping platform is suitable for acquiring plant phenotypic data in field environments owing to the UAV’s mobility and flexibility, and it has the great advantages of a high data acquisition efficiency and low cost. With the help of advanced sensor technologies, such as hyperspectral imaging and LIDAR, the UAV provides a feasible way to efficiently acquire plant phenotypic data. Effective analyses and processing methods and techniques for plant phenotypic data acquired by UAVs must be employed. Thus, high-throughput plant phenotypic analyses based on UAV platforms provides an important tool for studying plant phenotypic information from the field. This paper summarizes and analyzes the latest research results of UAV-based high-throughput crop phenotyping using big data analysis technology and artificial intelligence, as well as its research principles, relevant algorithms, processes, key technologies and applications. The main focus is on big data processing and intelligent analysis techniques related to UAV-based high-throughput plant phenotype big data and to the analysis of typical phenotypes, such as plant height, leaf area index, and plant diseases. We analyzed the current research needs and provide both a summary and outlook on related applications. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Research on Construction of Fisheries Science Data Center Feng Lu,Lihua Wang,Shuo Xu Journal of Agricultural Big Data    2019, 1 (3): 57-70.   DOI: 10.19788/j.issn.2096-6369.190306 Abstract （740）   HTML （35）    PDF（pc） （1779KB）（732）       Knowledge map    Save Basic, original fisheries science data is generated in the process of fishery technological activities, and has important scientific significance and practical value for agricultural, marine and economic fields. The Fishery Science Data Center, which manages fishery science data and applications of that data, is a crucial strategic resource for technological innovation and industrial development. It also provides important technical support to development strategy and scientific decisions, and improves the modernization of fishery. This study analyzes the characteristics, sources, and possible applications of fishery science data in the context of needing for fishery science data application, with the goal of improving the comprehensive service and smart decision-making ability of the data center and effectively preserving, managing, sharing and mining fishery science data.In the context of needing for fishery science data application We analyze and describe the function and position of the data center in terms of the demands for scientific data in the fishery technological innovation process. The overall architecture of the data center supports data fusion, big data analysis and cloud computing services. Technical roadmaps identify a storage and fusion platform for multi-source heterogeneous fishery data, a big data analysis and application platform in fishery science, and a cloud service platform. The study also considers factors in the sustainable development of the data center, including data collection, systems construction, standards setting, shared services mode, skills and training, and energy saving. The end goal is to ensure the continuous operation of the data center, maximize the value of fishery science data, point the direction for further building fishery science data . Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Developing a Combined Map of the Spatial Distribution of Autumn Crops in Henan Province Using Multi-source Remote Sensing Laigang Guo Yan Wang Lijun He Jia Yang Xiuzhong Zhang Hongli Zheng Guoqing Wang Journal of Agricultural Big Data    2020, 2 (1): 53-59.   DOI: 10.19788/j.issn.2096-6369.200107 Abstract （1443）   HTML （44）    PDF（pc） （1037KB）（732）       Knowledge map    Save Mapping the spatial distribution of all crops, using remote sensing, is important for monitoring agricultural production in China. The classification results provide basic data for quantitative and scientific management. The spectral characteristics of different autumn crops are known from years of experience using remote sensing to monitor crop planting areas. A combined map of crop spatial distribution in Henan Province in 2019 was made using multi-source remote sensing and different classification methods, based on topographic and geomorphic characteristics and crop planting structures. The classification crops include corn, peanuts, rice and soybeans, and the multi-source images include Sentinel-2, Landsat 8-OLI, GF6 WFV with different spatial resolutions. The accuracy of the classification results was verified using ground samples and survey data. The planting structure of autumn crops is complicated, including single crops of corn and rice, as well as mixed crops of corn, peanuts and soybeans. In the study area, corn was planted over the largest area, followed by peanuts. The overall accuracy and Kappa coefficient of the combined map were 86.13% and 0.83, respectively, which met the basic requirements for monitoring crops at provincial scale. The paper addresses the optimization of remote sensing data sources, classification methods, ground surveys and precision verification approaches. In this study, the technical ability to monitor crops using remote sensing of planting structures was tested in a large-scale business application. It offers technical support for using remote sensing to produce a combined map at large scale. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Tomato Dataset for Agricultural Scene Visual-Parsing Tasks Lingli Zhou, Ni Ren, Wenxiang Zhang, Yawen Cheng, Cheng Chen, Zhongyi Yi Journal of Agricultural Big Data    2021, 3 (4): 70-76.   DOI: 10.19788/j.issn.2096-6369.210408 Abstract （1293）   HTML （81）    PDF（pc） （1003KB）（717）       Knowledge map    Save Agricultural robots are an important part of the development of agricultural modernization, and computer vision technology effectively promotes their application in the field of agriculture by perceiving and analyzing crops and the environment. However, because of the complexity and diversity of agricultural scenes, the detailed and annotated large-scale image datasets required by advanced computer vision methods are scarce in the field of agriculture. This lack of datasets is the main challenge in the development of computer vision technology in the field. To solve this problem, this paper presents a large-scale tomato image dataset that can be used for semantic image segmentation, instance segmentation, target detection, and other tasks. The dataset consists of synthetic and real images. The synthetic images include 3250 synthetic tomato images and the corresponding pixel-level semantic segmentation label images; the real images consist of 750 monocular images and 400 binocular images taken by RGB cameras, some of which have detailed manual labels for instance segmentation and target detection. This research aims to enrich many aspects of the dataset, including its capacity, the dimensionality of the annotation information, and the complexity of the scene, and to provide data support for solving future problems in the field of agriculture using computer vision technology. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Establishing a Peanut Big Data Platformin China: A Proposal and Applications Hui Feng Xiao Wang Laigang Li Guoqiang Qiao Lu Wei Dong Zheng Guoqing Zhang Journal of Agricultural Big Data    2020, 2 (1): 45-52.   DOI: 10.19788/j.issn.2096-6369.200106 Abstract （746）   HTML （29）    PDF（pc） （1022KB）（712）       Knowledge map    Save China's peanut industry includes activities such as production, processing, import and export for consumption of China’s peanuts around the world ranking first, which is in a pivotal position in the international community. However, China's peanut industry exhibits weak international competitiveness. Better industry data are seen as part of the solution. Having effective data about single agricultural products along each whole industry chain is viewed as an important solution for advancing agricultural supply-side structural reform, and could improve the efficiency of the single agricultural product industry chain. For example, the application of single agricultural product big data such as the “zdscxx-pg” -China Apple Big Data Platform plays an important role in the development of China's agricultural superiority industry . Although peanuts are an important agricultural product of China, there is no peanut big data platform of the whole industrial chain open to the public. This paper focuses on how to build a peanut big data platform, which could help the peanut industry improve efficiency and sustainability assisted by big data. In this paper, we first summarize the actual experience of setting up a data platform for a single product, and analyze the key issues. We identify the different types and sources of relevant data, and outline the platform scheme. Finally, we build the overall structure for a peanut big data platform, and propose practical applications of the platform data. Our research shows the value of a peanut big data platform that covers the whole industry chain, gathers and shares data resources of the peanut industry, grasps the situation of peanut industry, relies on the platform to provide accurate services to all links and entities in the peanut industry, integrates large-scale peanut industry companies into quality and safety traceability and its importance for the sustainable development of China’s peanut industry. It can assist the government in formulating a development strategy for the peanut industry. It can gather data along the whole industry chain and share real-time data with industry participants. A peanut big data platform can reveal peanut industry conditions that are helpful to improve peanut quality, such as optimizing peanut planting layout and promoting producer-seller connections. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Dynamic Dataset of Plant Community Characteristics of Leymus chinensis Meadow Steppe in HulunBuir，China (2009–2015) Ruirui Yan, Baorui Chen, Baohui Zhang, Guixia Yang, Xiaoping Xin Journal of Agricultural Big Data    2021, 3 (2): 75-78.   DOI: 10.19788/j.issn.2096-6369.210208 Abstract （570）   HTML （38）    PDF（pc） （801KB）（709）       Knowledge map    Save The zonal distribution of vegetation in Hulunbuir steppe is meadow steppe and typical steppe from east to west. And there are five different grassland types in Hulunbuir in order: Chrysanthemum tenuifolia, Stipa bayal, Leymus chinensis, Stipa grandis, and Stipa krylosti. These five grassland types constitute different grassland types and combinations in Hulun Buir, and are the main body of the grassland in Hulun Buir. Through the field study on the changes of plant community in a long-term fixed plot of Leymus chinensis meadow steppe in Outer Hulun Buir, this dataset contains plant community characteristics, including plant community coverage, plant community height, plant community abundance, and aboveground green stock of the plant community were collected and arranged from 2009 to 2015. We studied changes in the plant community in the long-term fixed sample plot of Leymus chinensis meadow grassland in Hulunbuir. Researchers can retrieve data on the characteristics of the plant community by survey year. The establishment and sharing of long-term monitoring data sets of plant communities in Leymus chinensis meadow steppe in Hulunbuir is important for continued research. The data can support ecological monitoring of warm meadow grassland and dynamic research into plant community characteristics of this steppe type in the context of global climate change and human disturbance. This study provides a theoretical basis for understanding the response law of the grassland ecosystem and the restoration and succession of the grassland ecosystem under long-term enclosure. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

The development of deep learning based Natural Language Processing (NLP) technology and applications in agriculture Cui Yunpeng, Wang Jian, Liu Juan Journal of Agricultural Big Data    2019, 1 (1): 38-44.   DOI: 10.19788/j.issn.2096-6369.190104 Abstract （2091）   HTML （122）    PDF（pc） （10801KB）（706）       Knowledge map    Save Deep learning is an emerging but rapidly advancing technology having a profound impact on modern natural language processing (NLP) technology. This paper discusses recent developments of NLP technology driven by deep neural networks (DNN), as well as new products and recent cases. In particular, the paper examines advances relevant to the agriculture domain, such as DNN-based word embedding vector construction, the computational ability to recognize and name domain-specific entities and agricultural literature terms. Additionally, it analyzes the implementation details of related technologies. Finally, the paper reviews the trends and outlook for NLP technology, highlighting the significance of NLP technology for intelligent applications in agriculture. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

The Exploration and Practices on Data Management in Forestry Science Ping Xiao Yundan Hou Ruixia Ji Journal of Agricultural Big Data    2019, 1 (3): 46-56.   DOI: 10.19788/j.issn.2096-6369.190305 Abstract （620）   HTML （14）    PDF（pc） （593KB）（704）       Knowledge map    Save For several years, the National Forestry Science Data Sharing Service Infrastructure (NFSDSSI) has established a forestry science data system, developed a software and hardware system to offer data on the Internet, and daily it operates data sharing services that are geared to the needs of science and technology innovation, economy and social development, and all of society. This paper describes the hierarchical and classified management of forestry science data according to the investigations and practices of NFSDSSI’s developments and service operations. The forestry science data framework consists of 12 first-level categories in accordance with forestry science subjects, and a forestry science data system has been established. The forestry science datasets are divided into three levels according to the relevant laws and regulations. Hence, open-level datasets can be shared conveniently, restricted-level data sets can be shared in a controlled manner, and proprietary-level data sets can be shared securely. This paper outlines the strengthening and implementation of the main responsibility of the NFSDSSI’s support organizations. In particular, rules and regulations have been explored, developed, and implemented; a series of technical standards have been formulated to normalize the collection, processing, storage, and data quality assurance of data sets; and software and hardware equipment, financing, and personnel for data management and operations have all been obtained. This paper also introduces the platform structure and service operations for sharing data on the Internet. The established data storage, management, and service operation systems; online and offline data sharing; thematic data sets and data products; technical support services for user data applications; and special subjects for important requirements are now all available to users. This paper summarizes and analyzes the effectiveness of data management, various structures, and service operations of the NFSDSSI, and proposes new ideas for the NFSDSSI’s work to further strengthen and standardize forestry scientific data management and ensure scientific data security. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

From Liangping Pomelos to Meizhou Pomelos: Using Blockchain Technology to Trace the Origins of Agricultural Products Linli Jiang, Lei Shi Journal of Agricultural Big Data    2020, 2 (2): 94-103.   DOI: 10.19788/j.issn.2096-6369.200210 Abstract （656）   HTML （20）    PDF（pc） （1367KB）（701）       Knowledge map    Save Traceability of agricultural products involves tracking such products in a positive, reverse, or non-directional manner. That traceability covers all processes: from planting and production, logistics and transport, warehousing and sales through to consumer terminals; it does so by means of special information collection equipment, intelligent information-control systems, and information sharing. In that way, consumers are able to obtain the information they need. Given the occurrence of increasing numbers of food safety incidents and improvement of people’s material living standards over recent years in China, citizens’ demands for the quality and safety of agricultural products have grown. The traditional traceability system of agricultural products has exposed ever-greater problems. However, meeting consumer needs has also become increasingly difficult. Thus, it is necessary to establish a set of transparent guidelines in this regard. There is an urgent need in China to establish a credible traceability system for agricultural products—a system that can better guarantee the quality and safety of such products. Blockchain technology is essentially a shared database: stored information is characterized by non-forgery, non-tampering, full traceability, openness, and transparency. By combining blockchain technology with the Internet of Things, artificial intelligence, time stamp encryption, and other technologies, it is possible to establish a traceability system for agricultural products to cover planting, picking, circulation, storage, sales, and production. By focusing on Liangping pomelos and taking Meizhou pomelosas an example, this study analyzes the application of the conventional traceability system for Liangping pomelos; it exposes the problems associated with applying that system. This paper also examines the application of blockchain technology for the traceability of grapefruit. The framework of such a system is presented. A discussion is made of the traceability mechanism with respect to obtaining planting information, cold chain transportation, supervision and quality inspection links, and consumption links. Finally, this paper summarizes the application of blockchain technology in the traceability of other agricultural products; it identifies current problems, thereby setting the stage for further innovation and development. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Application and Prospects for Big Data of Traditional Chinese Medicine Resources Mingxu Zhang, Yuan Chen, Tuya Xilin, Ru Zhang, Yaqiong Bi, Chunhong Zhang, Taotao Wu, Minhui Li Journal of Agricultural Big Data    2021, 3 (1): 14-24.   DOI: 10.19788/j.issn.2096-6369.210102 Abstract （1219）   HTML （25）    PDF（pc） （1523KB）（687）       Knowledge map    Save Big data refers to the collection of massive amounts of information, and it has four characteristics: large amounts of data; strong real-time performance; multiple types of data; and valuable data. Following the rapid development of computer science and information technology, big data has been widely applied in the field of health and medicine. China has undergone major improvement to its national big data resources. In conjunction with that process and the promotion of the Belt and Road Initiative, the need to upgrade and transform China’s traditional medicine resource industry has clearly emerged. Integrating China’s traditional medicine resource industry with big data analysis technology can effectively promote the development of industries related to such medicine as well as in-depth research. The comprehensive development of big data of traditional Chinese medicine resources has increasingly become an important driving force in developing related industries. With respect to traditional Chinese medicine resources, big data mainly involves the accumulation and processing of large volumes of information, such as the following: the number of types of traditional Chinese medicine resources; the spatial distribution of plant and animal species used in traditional Chinese medicine; the number of industrial resources; changes in the availability of resources; cultivating plant and animal species for traditional Chinese medicine versus harvesting them from the wild; the amount of resources that need to be purchased; demand level; supply level; the quality of materials used in traditional Chinese medicine; and knowledge related to the application of such medicine. Analyzing those data can exert a vital influence on overall planning related to the resource industry for traditional Chinese medicine. Accordingly, an opportune assessment of the application and development of big data technology for Chinese medicine resources can better guide the direction of future research. The present study begins with an application of big data technology to traditional Chinese medicine resources. This paper summarizes the current status regarding the development of resource databases for traditional Chinese medicine. This study made use of dynamic monitoring stations for traditional Chinese medicine resources; it also describes how research has progressed with respect to the application of big data technology for resources for traditional Chinese medicine. This study concludes with suggestions for problems that may occur in developing big data technology for Chinese medicine resources. This article covers scientific planning and offers guidance for the sustainable development of the resources industry for Chinese medicine; it sets a foundation for additional high-quality research into clinical treatment for traditional Chinese medicine as well as the pursuit of careers in such medicine. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

2022 Inner Mongolia UAV Potato Image Dataset HU Tianci, WANG Ruili, JIANG Chengxiang, BAI Tao, HU Lin, WANG Xiaoli, GUO Leifeng Journal of Agricultural Big Data    2023, 5 (1): 40-45.   DOI: 10.19788/j.issn.2096-6369.230112 Abstract （236）   HTML （20）    PDF（pc） （911KB）（654）       Knowledge map    Save Potatoes are the fourth largest food crop in the world, and large-scale planting of potatoes is an important basis for ensuring high yields of potatoes. With the development of digital agriculture, the large-scale planting of potatoes also tends to be automated and intelligent. UAVs are an important tool in crop plant protection and growth monitoring. UAV spectral data play an important role in crop identification and crop growth status analysis. important. In order to explore the role of spectral data and image data in potato growth, this study conducted three different spatial resolution images on two mature seed potato experimental fields in Hulunbeier, Inner Mongolia, on August 13, 16 and 18, 2022. Spectral data and image data are collected. UAV remote sensing was used to obtain multi- spectral images at different heights, and the data of potato leaves on the ground were collected. After manual in- spection and sorting, this dataset was constructed. The spectral data of this dataset is complete and the leaf data is clear, which can provide data support for research on potato crop identification, planting area estimation, and potato-related vegetation index changes on different dates during the maturity period. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Design and Implementation of a Big Data Platform for Cloud Server Farm Smart Services Nuojuan Ling, Yuan Rao Journal of Agricultural Big Data    2021, 3 (4): 10-19.   DOI: 10.19788/j.issn.2096-6369.210402 Abstract （588）   HTML （56）    PDF（pc） （1305KB）（642）       Knowledge map    Save With the wide use of modern information technology in the field of agriculture, a massive amount of agricultural data can now be collected and analyzed to promote the development of agricultural modernization. This paper considers the existing research of the whole industry chain of production and management of the special agricultural products of the Dabie Mountain region. Systematical analysis was conducted to determine the characteristics of the data of various industry value chains, such as the production, processing, and marketing of agricultural products in this region. Moreover, the data resources of agricultural production and management were effectively integrated. Subsequently, the design pattern of a big data platform architecture, which includes four layers, an infrastructure layer, a data resource layer, a data processing and analysis layer, and a data display layer, was adopted. The data resource database was built for the whole industry chain of Dabie Mountain agricultural products. This database was based on the Hadoop big data framework and a big data platform for the smart services of a cloud server farm. Specifically, the platform’s functions were developed for the business tasks required by the relevant agricultural employees in the industrial area. The data in the developed database were successively processed by data cleaning, data mining, and data modeling to explore the regular dynamic changes in agricultural product production and management. Smart service functions such as information sharing, smart early warnings, and auxiliary decision-making were realized. In particular, the information sharing function offers data resource sharing services for each subsystem of the big data platform; the smart early warning function provides early warning services for production environment, price, and other key indices of agricultural products during the production and operation of the overall agricultural product industry value chain; the auxiliary decision-making function notifies agricultural practitioners of changes in the production and operation of agricultural products within the industry’s region and provides services such as auxiliary business decision-making services. The research and development of the cloud-based smart service big-data management center and data visualization system will be a useful reference for promoting the development of information and intelligence of the whole industry chain of special agricultural products in the Dabie Mountain region. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Practice in the CoreTrustSeal Certification of World Data Center Juanle Wang,Yi Wang,Kun Bu,Mingming Wang,Yanjie Wang Journal of Agricultural Big Data    2019, 1 (3): 71-81.   DOI: 10.19788/j.issn.2096-6369.190307 Abstract （790）   HTML （19）    PDF（pc） （1632KB）（639）       Knowledge map    Save A scientific data center is a vehicle for scientific data management, and assessment and certification are very important for the scientific data management of scientific data centers. The Data Seal of Approval (DSA) established mechanisms to enable trusted digital repositories to provide core level certification for data repositories. Subsequently, the World Data System (WDS) of the International Science Council and DSA jointly launched the CoreTrustSeal partnership certification and international scientific data center certification worldwide. With the Measures for Managing Scientific Data released in March 2018 by the State Council of China, China's scientific data centers are facing the urgent need to improve their level of professionalism and international influence. Hence, this paper analyzes the three categories of articles and 16 requirements for CoreTrustSeal certification, introduced in the actual certification document of the World Data Center for Renewable Resources and Environment (WDC-RRE), which was established in 1988. It also details the experiences of certification and suggests that a scientific data center should strengthen its top-level design, pay attention to long-term data cataloging, improve the level of internationalization, strengthen the preparation of certification supporting materials, and advance the online accessibility of certification materials. After submitting its application in April 2018, the WDC-RRE became the first CoreTrustSeal-certified Trustworthy Data Repository in the geosciences field in Asia in February 2019. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Big Data Portal Development in Agrobiodiversity: Current Research and Future Outlooks Zheping Xu,Zengting Shao,XueJun Zhu,Fang Wang,Yuanyuan Wang,Man Xiao,Keping Ma Journal of Agricultural Big Data    2019, 1 (2): 76-87.   DOI: 10.19788/j.issn.2096-6369.190207 Abstract （955）   HTML （60）    PDF（pc） （846KB）（628）       Knowledge map    Save Agrobiodiversity refers to the variety and variability of animals, plants, and microorganisms used directly or indirectly for food and agriculture, including crops, livestock, forestry, and fisheries. The underpinning of the entire agricultural system and an important part of agricultural production informatization, agrobiodiversity is also the basis of national resource strategies and national security. Although data and knowledge related to agrobiodiversity have been obtained from various research projects, several problems still exist; these include scattered data, lack of top-level designs, inadequate data standards, insufficiently interoperable systems, slow response, and few high-quality think tanks and data portals. To improve research and development on a big data portal for agrobiodiversity in China, we describe advances in agrobiodiversity big data in China and abroad in terms of research data platforms (basic, crop, livestock, forestry, and fishery data platforms; traditional cultural knowledge and think tank platforms; and assessment indicators) and basic resource objects (taxonomy, thesaurus, metadata standard, ontology, and scientific research workflow). In addition, we suggest a system architecture comprising four levels, namely, basic, resource, organizational, and application levels. Finally, we provide a future outlook on the construction and resource sharing of agrobiodiversity data platforms in China. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Construction and Application Prospects of Big Data Platform for Plant Protection in Anhui Province Meng Dong Wei Qian Rong Yang Qianjin Zhang Liping Zhang Journal of Agricultural Big Data    2020, 2 (1): 36-44.   DOI: 10.19788/j.issn.2096-6369.200105 Abstract （702）   HTML （27）    PDF（pc） （910KB）（623）       Knowledge map    Save In recent years, China’s agricultural plant protection has become increasingly important, and the forecasting system of agricultural plant protection is not perfect. The basic reason is that the collection, mining, and decision-making ability of agricultural big data are insufficient. At present, there are many information platforms related to agricultural plant protection on the market, but they all face problems, such as insufficient classification of resources and inaccurate resource information. As a major agricultural province, the problem of plant protection in Anhui Province is particularly serious. To promote the development of a plant protection system in Anhui Province, this article uses the digital image library of agricultural plant protection as the bottom layer, and aims to realize the distributed storage and processing of data resources by constructing a platform for big data management, analysis, mining, and visual display. To meet the actual requirements of agricultural production, management decision making, and technological innovation, we conduct technical research and product research on a system framework, data cleaning, data mining, knowledge discovery, cognitive computing, and data modeling. We construct a big data platform integrating management, sharing, innovative applications, and services. We provide practitioners with accurate plant protection information, such as identification and auxiliary diagnosis of agricultural disasters, prediction of agricultural disasters, and plant protection knowledge. We overcome temporal and geographical restrictions using the Internet to help practitioners solve the difficult problems of plant protection in production in real time. This measure can reduce economic costs, reduce operation intensity, and improve the timeliness of prevention and control. Finally, we provide suggestions to address the shortcomings of current big data platforms for plant protection. In the future, it will be necessary to supplement the platform with further informational data that it lacks, such as data on remote sensing, meteorology, and soil; increase the number of diseases, pests, and weeds in the database; improve the data sharing level; optimize the data analysis technology; strengthen data application and promotion; and improve data security guarantees, become an important part of smart agriculture Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Prospect of Agricultural and Rural Application of Trusted Blockchain Wensheng Wang Journal of Agricultural Big Data    2020, 2 (2): 14-24.   DOI: 10.19788/j.issn.2096-6369.200202 Abstract （745）   HTML （32）    PDF（pc） （1176KB）（604）       Knowledge map    Save The potential of blockchain applications for promoting the high-quality development of agriculture and rural areas has received attention worldwide. China is currently in a mature stage of national poverty alleviation and a crucial period for rural revitalization. The weakly-centralized/ decentralized nature of Chinese agricultural and rural industrial and social structures suggest a natural coupling and application integration point with emerging blockchain technology. However, the majority of agricultural and rural blockchain research efforts focus mainly on rural finance and approach issues in a fragmented manner. In contrast, explores the application of blockchain technology in agriculture and rural areas from the holistic perspective of the national "comprehensive rural revitalization" strategy. After reviewing the technical characteristics of blockchain and related global application research, we systematically examine prospects in agricultural and rural development, and identify blockchain opportunities in eleven domains, such as smart agriculture based on trusted Internet of ThingsIoT , credible support networks for the new agricultural management systems, agricultural product quality and safety systems, credible rural collective asset management system, credible rural tourism industry, rural living environment improvement initiative, targeted poverty alleviation, credible migrant workers' rights and interests protection network and so forth. Our findings suggest that the combination of blockchain and 5G, artificial intelligence and other "new infrastructure" elements can accelerate the evolution of society to society 5.0. Reference | Related Articles | Metrics | Comments（0）