Most Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Application and Prospects for Big Data of Traditional Chinese Medicine Resources in Inner Mongolia
    Mingxu Zhang, Ru Zhang, Tuya Xilin, Yuan Chen, Yaqiong Bi, Chunhong Zhang, Taotao Wu, Minhui Li
    Journal of Agricultural Big Data   2021, 3 (2): 42-53.  DOI:10.19788/j.issn.2096-6369.210205
    Abstract529)   HTML23)    PDF (3449KB)(334)      

    “Big data” refers to a huge information collection that has four characteristics: large data volume; complex type; low value density; and high effectiveness. Big data technology is a non-structured data processing technology that can efficiently handle large volumes of data collected by different industries. “Big data of traditional Chinese medicine resources” relates to the large volumes of data with practical significance that are generated during the long development of China’s traditional medicine industry. Inner Mongolia is a region where ethnic minorities live in concentrated communities. With their long historical development, both traditional Mongolian and Chinese medicine have come to play an important role in disease prevention and treatment; considerable amounts of traditional Chinese and Mongolian medicine data have accumulated. One of the most important forces for the current development of resource-related industries with respect to traditional Chinese medicine is how to collect and organize these data is currently an important one in the development of resource-related industries with respect to traditional Chinese medicine; which is also a driving force in the modernization of such medicine. Following scientific and technological development, combining traditional Chinese and Mongolian medicine resources with cutting-edge big data technology offers an effective means for modernizing such medicine. In the present study, we summarizes the construction process of a database was created for traditional Chinese and Mongolian medicine resources and a big data platform for the traditional Chinese medicine industry in Inner Mongolia. This paper also summarizes the results related to the application of big data technology for traditional Chinese and Mongolian medicine resources in that region. At last, a proposal is made for dealing with problems that may be encountered in developing traditional medicine Chinese and Mongolian resources in Inner Mongolia. The research method adopted in the present study can be applied to the sustainable use of traditional Chinese medicine resources. That approach can also address the deficiencies with traditional Chinese medicine and ethnic medicine in different parts of China. This study offers solutions related to research into the application of big data technology for traditional Chinese medicine resources in Inner Mongolia as well as other parts of the country. In that way, this article presents a scientific foundation for applying big data technology for traditional Chinese medicine resources in the future.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract445)   HTML18)    PDF (1209KB)(256)      

    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
    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
    Abstract403)   HTML33)    PDF (1468KB)(237)      

    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
    Research on the Construction of the Agricultural Big Data Information Platform
    Qiang Li, Maofang Gao, Ying Fang
    Journal of Agricultural Big Data   2021, 3 (2): 24-30.  DOI:10.19788/j.issn.2096-6369.210203
    Abstract379)   HTML24)    PDF (946KB)(153)      

    [Concepts]The agricultural big data information platform is a comprehensive system that collects data from agricultural production experiences to realize the informatization, digitization and intelligence of an agricultural industry using modern technologies such as big data and the Internet of Things. [Current Research Status] Big data is pushing forward the construction of modern agriculture in China. A key theme of agricultural development is the use of high technology, guided by policy, to develop intelligent agriculture. [Summary]The construction method and proposed implementation for the agricultural big data information platform are reviewed. In this exercise, we address the characteristics of agricultural big data, describe the core functions of the agricultural big data platform, and explore standard specifications of digital agriculture. We also propose various sampling strategies, combined with a distributed information network and modular agricultural data collection platform. The goal is to implement precise variable management measures to yield low-input, high efficiency, and sustainable agricultural data production. [Outlook]In China, there is currently a strong focus on enhancing agricultural productivity through using digital approaches and big data information platforms. The development of agricultural information collection technologies and methods is important for promoting high-quality agricultural development in China, building digital agriculture, and becoming globally recognized in the agricultural sector.

    Table and Figures | Reference | Related Articles | Metrics
    Functional Design and Development of the Big Data Center of the Whole Tea Industry Chain
    Fuqiao Chen, Chen Ling
    Journal of Agricultural Big Data   2021, 3 (2): 54-66.  DOI:10.19788/j.issn.2096-6369.210206
    Abstract374)   HTML23)    PDF (2433KB)(180)      

    The National Whole Tea Industry Chain Big Data Project is one of the single-product big data platforms approved by China’s Ministry of Agriculture and Rural Affairs. The goal of its construction is to provide professional and authoritative data services for tea-related government departments, business entities, scientific research institutions, and the public. The platform is committed to supporting the tea industry’s scientific decision-making, improving the digitalization of the tea industry, and boosting the digital transformation of China’s tea industry. The data platform promotes industrial transformation and upgrading and provides a pilot experience for the construction of other digital agriculture projects. The center is designed and constructed around the tea industry in accordance with the principles of availability, usability, and ease of use. The platform conducts the collection, storage, and mining of tea industry data. Its functions are conducted in accordance with the ideas of integrated management and modular application. The platform has strengthened digital collection and application functions and developed a rich and diverse data collection function. At the same time, a relatively independent data mining and model system is developed on the basis of the specific application scenarios. Through preliminary construction and debugging, the center now has the ability to collect, analyze, and publish data. Consumption trend data, e-commerce data, and public opinion monitoring data are useful in decision-making, understanding the operating rules of the tea industry, formulating industrial policies, and guiding scientific decision-making. This article introduces the background, significance, positioning, and construction objectives of the National Whole Tea Industry Chain Big Data Pilot Project by drawing on the project construction plan and progress. It focuses on the technical route, main modules, and main functions of the project. It also analyzes the main features of the project and looks forward to the later construction plan.

    Table and Figures | Reference | Related Articles | Metrics
    Big Data Construction of Oil Crops (Rapeseed, Peanut) Whole Industrial Chain
    Rui Jiang, Fenghong Huang, Yu Wu, Mengjia Huo, Huawei Liu
    Journal of Agricultural Big Data   2021, 3 (2): 67-74.  DOI:10.19788/j.issn.2096-6369.210207
    Abstract310)   HTML10)    PDF (1043KB)(122)      

    A data platform serving an agricultural industry value chain can accelerate the transformation of agricultural techniques, promote agricultural upgrades, improve the quality and efficiency and sustainable development, and accelerate the process of agricultural modernization. In China, the construction of such a platform for important agricultural products is still in the early stages and the data foundations are weak, facing challenges such as limited rural information infrastructure, incomplete information about agricultural product processing, data resources fragmented across the industry, and limited data acquisition effectiveness and scope. Taking oil crops (rape, peanut) as an example, this paper analyzes current efforts to construct a data platform for an industry value chain. It applies the concepts and principles of big data platforms in the context of the oil crop industry, and proposes a framework and key functions required of the platform. In addition, this paper also develops a set of models relevant to an agriculture-focused data platform, which support data mining and application services. These include an integrated meteorological yield prediction model, a remote sensing yield prediction model, a price monitoring model, a policy topic evolution model, and a semantic comparative analysis model. This paper then explores the construction scheme of a data platform for the oil crops industry using big data, natural language processing and artificial intelligence technology. This platform supports aggregating, analyzing, and mining important data about the crop growing environment, input resources, production and processing, distribution, and consumption. By collating relevant data resources, the platform can enhance digital technology R&D and application capabilities, simplify data governance, and demonstrate applications for the industry value chain. The paper highlights replicable, accountable and well-established approaches for constructing a comprehensive data platform for an agricultural industry value chain, with the goal of promoting the digitalization of agricultural production, operations and management, and modernization of agricultural and rural areas.

    Table and Figures | Reference | Related Articles | Metrics
    Methods for Agricultural Resource Data Collection and Integration: A Study of the Xinjiang Production and Construction Corporations
    Hui Wang, Haijiang Wang, Pan Gao, Ze Zhang, Tongyu Hou, Lü Xin
    Journal of Agricultural Big Data   2021, 3 (2): 31-41.  DOI:10.19788/j.issn.2096-6369.210204
    Abstract281)   HTML7)    PDF (2642KB)(123)      

    Agricultural resource data include quantities, text, symbols, charts, graphs or other analog inputs that describe agricultural resources. Agricultural resource data yield agricultural resource information. The Xinjiang Production and Construction Corporations are vigorously promoting the study and construction of applications using agricultural big data. Traditional methods for collecting and integrating agricultural data reveal problems such as inconsistent collection standards, poor data quality, information fragmentation, and low fluidity. A set of economic, feasible and efficient methods for agricultural data collection and integration is urgently needed. This study reviewed the research progress on agricultural data resources in China, particularly research on methods for collecting and integrating agricultural resource data. On the basis of systematic observation and analysis of existing agricultural resource data from the Xinjiang Production and Construction Corps, important concerns and necessary functions were identified. Through this study, agricultural data collection and integration methods were divided into a technical indicator specification module, an agricultural resource collection module, a data quality inspection module, a heterogeneous data conversion module, a data classification coding module, a data management module, a decision support module, and an agricultural resource sharing module. An agricultural resources data collection and integration method model was established and the Xinjiang Corps’ agricultural resources integration and sharing platform was built. The quantity, quality, and effectiveness of agricultural resource data are related to the development foundation of agricultural big data. On the basis of progress in the study of data collection and integration methods, this paper describes preliminary collection and integration of dispersed and unique agricultural resource data. This research will continue to identify ways to improve and streamline data collection and integration practices. The goal is an economical and effective working procedure that effectively prepares data for mining, and reveals relationships among different agricultural resource data elements.

    Table and Figures | Reference | Related Articles | Metrics
    Software Research and Development of a Multi-parameter Detection System for Plant Ion Absorption Based on LabVIEW
    Xiaoding Feng, Xiaodong Wang, Bin Luo, Cheng Wang
    Journal of Agricultural Big Data   2021, 3 (2): 16-23.  DOI:10.19788/j.issn.2096-6369.210202
    Abstract246)   HTML2)    PDF (1866KB)(63)      

    Inorganic ions are an important part of the growth environment of crop plants with the function of regulating physiological activities. Obtaining the absorption information of plant and environmental nutrient ions during the growth process can reveal the nutrient absorption mechanism of plants and assist agricultural researchers or producers in monitoring plant growth status. Using the kinetics of plant ion absorption, we design an online, in-vivo, multi-channel plant ion absorption multi-parameter detection software system. Research in hydroponic environments uses the ion electric signal acquired by the liquid ion selective microelectrode and NI-9205 acquisition card. This signal is then converted into an ion concentration in the software, and then the ion access of absorption kinetics characteristic parameters is realized by automatically fitting the ion concentration depletion curve in real time online. The software system is developed and designed using the LabVIEW software platform combined with the Actor Framework multi-threaded concurrent design mode and object-oriented design ideas to complete modular design. The system includes a user interface, data acquisition, data processing and analysis, and database applications. It also analyzes and builds the asynchronous communication structure between the levels of the multitasking system. It builds an abstract data message interface using the design principles of high cohesion and low coupling to isolate the upper and lower modules to enhance the reliability and scalability of the software. In the data processing and analysis module, the voltage-concentration calibration conversion algorithm that obeys the Nernst equation is embedded, and the specific process of extracting the characteristic parameters of plant ion absorption kinetics is completed. After experimental testing, the system can accurately complete the collection of ion voltage signals; concentration, calibration, and conversion; and the acquisition of characteristic multi-parameters in real time. It can meet the needs of automatic online monitoring of plant ion absorption kinetic characteristic parameters in agricultural scientific research and production. It can also provide a basis for nutrition research and the formulation of cultivation management measures.

    Table and Figures | Reference | Related Articles | Metrics
    The Development of Blockchain and Its Application in Agriculture
    Huijuan Wang, Qian Xu, Ailian Zhou, Xiaohe Liang, Nengfu Xie, Xiaoyu Li, Saisai Wu
    Journal of Agricultural Big Data   2021, 3 (3): 76-86.  DOI:10.19788/j.issn.2096-6369.210308
    Abstract224)   HTML9)    PDF (839KB)(106)      

    [Related Concepts]Blockchain is a decentralized, open and shared distributed database that has the characteristics of decentralization, high openness, anonymity, machine autonomy, anti-tampering, and traceability. [Current Research Status]At present, blockchain has become a leading technology to advance the development of countries worldwide and has been applied in many fields, including finance, education, and medical care. Its applications are continuously emerging, and China has now included it as part of the national technology strategy. Most of the available research literature on blockchain technology focuses on its development and application in the financial sector. Few studies have attempted a systematic review of the development process and characteristics of blockchain technology, and "blockchain + agriculture" is still in its infancy. [Summary of This Paper]This paper systematically combs the main development process of blockchain, divides it into four stages (origin of the technology, blockchain 1.0, blockchain 2.0, and blockchain 3.0), summarizes the main characteristics and development status of each stage, and discusses in depth representative cases of blockchain application in the agricultural sector. By combing the development process and analyzing the application cases, this paper explores the application potential of blockchain technology, summarizes new opportunities for blockchain in agriculture, and puts forward ideas for using blockchain technology in agriculture in China. [Prospect]The application of blockchain technology can effectively reduce information asymmetry, improve information transparency, reduce data storage costs, and contribute to the development of modern agriculture. To make blockchain technology more applicable to agriculture, we need to understand the problems and challenges that may arise in the future, while still devising targeted measures to promote the development of blockchain for the agricultural sector.

    Table and Figures | Reference | Related Articles | Metrics
    Dynamic Dataset of Plant Community Characteristics of Leymus chinensis Meadow Steppe in HulunBuirChina (20092015)
    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
    Abstract221)   HTML10)    PDF (801KB)(62)      

    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
    Over Two Decades of Research with Greenlab Model
    Mengzhen Kang, Xiujuan Wang, Jing Hua
    Journal of Agricultural Big Data   2021, 3 (3): 3-12.  DOI:10.19788/j.issn.2096-6369.210301
    Abstract210)   HTML7)    PDF (879KB)(57)      

    The GreenLab model is an organ-level Functional-Structural Plant Model (FSPM), which simulates plant growth and development processes with the discrete dynamic system, including biomass production, partitioning, and structure formation. It is a generic FSPM that integrates multi-disciplinary knowledge from botany, mathematics, agronomy, computer science, and automation science. Sino-French cooperation around GreenLab since 1998 has led to the development of new methods, algorithms, and software. These include a dual-scale automaton, parameter inversion for plants with branching structure, stochastic FSPM with theoretical computation, plant fast modelling and visualization, a plant growth modelling and fitting tool in Scilab and Matlab, and a simulator for complex structure in c++. The GreenLab model has been applied on dozens of plants with their own features, including maize, wheat, cucumber, tomato, rapeseed, pine tree, and maple tree, covering plants ranging from herbaceous crops to complex trees. The model is characterized by the fact that its source-sink parameters affecting the biomass production and partitioning can be inversely estimated through the measured organ biomass and quantity. It is applicable for single stem or branching structures, deterministic or stochastic cases, with common organ-level target data for parameter identification and model calibration. This paper reviews the development history and recent advances of the GreenLab model and presents the basic concepts and key methods. These include dual-scale automaton, organ series, the generic plant fitting. It gives some details on the structural model (the computation on organ quantities and the stochastic simulation on organ production) and the functional model (demand of organ and plant, biomass production and allocation, and organ growth). With the availability of plant phenotype technologies, GreenLab can be used for building parallel agricultural system, supporting the deep understanding of the plant-environment interaction, and the intelligent decision support for management and control of production management.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract198)   HTML22)    PDF (1305KB)(100)      

    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
    Evaluation of Green Development of Rice-Based Cropping Systems Using Remote Sensing Data and the DNDC Model: Case Study of Qianjiang City
    Ayitula Maimaitizunong, Shuai Yanju, Haodong Wei, Zhen He, Qinxi Xiao, Qiong Hu, Baodong Xu, Liangzhi You, Cougui Cao, Lin Ling
    Journal of Agricultural Big Data   2021, 3 (3): 33-44.  DOI:10.19788/j.issn.2096-6369.210304
    Abstract187)   HTML8)    PDF (1323KB)(68)      

    The purpose of this study was to estimate the greenhouse gas emission and carbon sequestration of different rice-based cropping systems in Qianjiang City, China, and to evaluate potential for their green development.


    First, classified remote-sensing images were with the random forest method to map the distribution of rice cropping systems in Qianjiang City. Combined with meteorological, soil, and crop management datasets, a revised and validated DeNitrification–DeComposition (DNDC) model was used to conduct regional simulations. Estimates for methane (CH4) and nitrous oxide (N2O) emissions and changes in soil organic carbon (dSOC) in Qianjiang City were obtained. Second, scenario simulations were conducted in the DNDC model under the assumption that the current rice–crayfish system was evolved from different rice cropping systems, and changes in the related indicators were used to evaluate the green development potential of the systems.


    All indicators showed that the validated DNDC model had good performance to simulate the effect on CH4 and N2O. In 2019, the CH4 and N2O emissions and the annual dSOC of the main rice cropping systems per km2 in Qianjiang City were 0.40–64,043.34 kg, 0.002–227.08 kg, and 0.18–5,835.27 kg C, respectively. The annual CH4 and N2O emissions per unit area in the rice–crayfish system were the lowest, at 394.50 kg·hm-2 and 1.43 kg·hm-2, respectively. The dSOC per unit area was the highest in the rice–crayfish system, at 274.30 kg C·hm-2, and that in the rice–fallow system was the lowest, at 204.95 kg C·hm-2. The annual total CH4 emission increased by 2.31%–11.25%, the total N2O emission increased by 11.49%–67.09%, and the dSOC decreased by 9.95%–22.81% when the rice–crayfish system was converted to other rice cropping systems in Qianjiang City.


    In this study, the rice–wheat system showed the largest CH4 emission, and the rice–rape system showed the largest N2O emission, both of which had moderate carbon sequestration capacity. The greenhouse gas emission of the rice–fallow system is lower than that of the rice–dryland rotation system, but its carbon sequestration ability is poor. The rice–crayfish system has stronger emission reduction and carbon sequestration ability compared with the other rice-based systems, and has higher green development potential, though there is still potential for emission mitigation.

    Table and Figures | Reference | Related Articles | Metrics
    Construction and Application of a Comprehensive Management Service Platform for Fishing Vessels and Fishing Ports
    Muhan Xue, Shuo Xu, Feng Lu, Yong Zhu, Jianguang Wu, Yigang Wang
    Journal of Agricultural Big Data   2021, 3 (3): 45-54.  DOI:10.19788/j.issn.2096-6369.210305
    Abstract179)   HTML8)    PDF (1260KB)(42)      

    The tracking data of fishing vessels and fishing ports are basic data needed for the management and operational maintenance of businesses related to these entities. These data have wide scientific applications and can add value to the dynamic supervision of fishing vessels, the operation and management of fishing ports, crew management, safety in the fish production chain, catch traceability, and the construction of ‘intelligent’ fishing ports. The integration, sharing, and exchange of such data resources are of great worth for comprehensive fisheries reform and to enhance the capacity of the vessels and ports. A popularized and comprehensively applied shared information system for fishing vessels and the ports that support fishing vessels would provide more abundant data for scientific fisheries management and research. Presently, there is scattered construction and deployment of information systems for fishing vessels and fishing ports, a lack of business collaboration and data docking among the existing systems, no capacity for data sharing among fishing vessels, and failure to maximize the value of the data collected. Based on the integration and allocation of the information resources of fishing vessels and fishing ports and the demand for joint command of safety in fishery production, this study considered the methods currently used for data classification, sharing standards, interaction modes, and model construction. Thereafter, the structure of these data resources, shared metadata standards, and interaction patterns were examined. The study provides a standardized basis for describing the features of specific data sets and for realizing data resource sharing by fishing vessels and fishing ports, as well as the exchange mode of each link; formulates a safe and stable information transmission mode; and improves the levels of information technology applications for fishing vessels and fishing ports. Finally, the study proposes an information interaction model for fishing vessels and fishing ports. This research reveals the high potential value of the data resources of fishing vessels and fishing ports, and introduces technical specifications of data-sharing standards and information interaction modes. In addition, the application and promotion of this model is planned.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract177)   HTML16)    PDF (1003KB)(61)      

    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
    Sensitivity Analysis of Genetic Parameters of RiceGrow Model
    Yijun Meng, Xiaolei Qiu, Leilei Liu, Bing Liu, Yan Zhu, Weixing Cao, Liang Tang
    Journal of Agricultural Big Data   2021, 3 (3): 23-32.  DOI:10.19788/j.issn.2096-6369.210303
    Abstract154)   HTML7)    PDF (1112KB)(37)      

    Genetic parameter calibration is an important step before applying the crop growth model, which often calls for a lot of time and effort. Sensitivity analysis can help to identify sensitive parameters, improve calibration efficiency, and simplify the model. Using Simlab and Matlab software, this study analyzed the sensitivity of rice genetic parameters of RiceGrow model by EFAST method and obtained the parameter sensitivity of the model in different regions and under different climate scenarios (historical meteorological data from 1981 to 2015 and global future warming 2.0℃ climate scenarios). The TDCC (Top-Downward-Coefficient of Concordance) coefficient was used to calculate the sensitivity ranking consistency. The results showed that Optimum Temperature (OT) was the most sensitive parameter affecting flowering period and total dry matter, followed by Temperature Sensitivity (TS), Photoperiod Sensitivity (PS) and Intrinsic Earliness (IE). OT was the most sensitive parameter affecting maturity period and the whole growth period. TS, IE, PS and Basic Filling Factor (BFF) were also sensitive parameters. The sensitive parameters affecting yield are mainly maximum CO2 assimilation rate (AMX), Specific Leaf Area (SLA) and Harvest Index (HI), followed by IE, TS, BFF, OT and PS. The sensitivity parameters in all regions and under different climate scenarios are relatively consistent, but the sensitivity ordering varies greatly. The sensitivity indexes of most parameters under warming climate scenarios slightly increase, while a few slightly decrease. The variation of parameter sensitivity under different climate scenarios is small, while which among different regions is large. When calibrating the model for phenology and dry matter, OT is the most sensitivity. In areas with low temperature and high latitude, the parameters related to temperature, photoperiod and photosynthesis should be focused. When calibrating the parameters of the yield, we need to focus on AMX, HI, SLA. Relative growth rate of LAI is not sensitive, so it can be ignored in parameter calibration, and can also be eliminated from the model to simplify the model. The results would be used to localize crop model and provide a way to improve the efficiency of parameter calibration.

    Table and Figures | Reference | Related Articles | Metrics
    Parameter Adjustment and Optimization Methods for The WheatSM
    Xiafei Jin, Xianguan Chen, Zhihong Gong, Liping Feng
    Journal of Agricultural Big Data   2021, 3 (3): 13-22.  DOI:10.19788/j.issn.2096-6369.210302
    Abstract143)   HTML7)    PDF (782KB)(43)      

    The crop growth model is an effective tool to evaluate crop production, resource utilization, and climate change impact. The WheatSM (Wheat Growth and Development Simulation Model) has been applied to crop production optimization and management and has achieved good achievements. However, because of the large number of model parameters, it’s complicated to debug the model parameters. To determine the parameters of the WheatSM model quickly and accurately, it is necessary to simplify the parameter adjustment work of the model and promote its wide application in the field of agricultural meteorology. In this study, on the basis of automatic adjustment methods of crop model parameters at home and abroad, an automatic adjustment coupling system of WheatSM model parameters is constructed based on the PEST (Parameter Estimation) method. The phenology and yield parameters of the WheatSM model were optimized automatically. Shangzhuang, Beijing was selected as a representative site.This study compared the optimization results with the trial-and-error simulation results, andused the automatic optimization method and trial-and-error method to adjust wheat phenology parameters and yield parameters for wheat growth model WheatSM, based on the meteorological data, soil data of the test sites, and the test data of different sowing dates of winter wheat from 2014 to 2016. The results show that the PEST method has high precision and good simulation effect for automatic adjustment and optimization of model parameters. The error of simulated phenology was less than 7 days, and the error of simulated yield was less than 228.63 kg·hm-2. The PEST method has the advantages of being less time consuming and allowing for the simultaneous batch processing of data. Using this automatic parameter adjustment system can reduce the workload of parameter calibration, save model operation time, simplify work complexity, and obtain higher simulation accuracy. This study provides a convenient method for WheatSM parameters automatic optimization and a theoretical reference and guidance for improving the efficiency and accuracy of crop model parameters calibration.

    Table and Figures | Reference | Related Articles | Metrics
    Construction and Application of a Comprehensive Service Platform for Intelligent Field Crop Production
    Qing Zhao, Guoqiang Li, Feng Hu, Laigang Wang, Hecang Zang, Jie Zhang, Meng Wang, Hui Zhang, Guoqing Zheng
    Journal of Agricultural Big Data   2021, 3 (4): 29-39.  DOI:10.19788/j.issn.2096-6369.210404
    Abstract142)   HTML15)    PDF (1734KB)(44)      

    With the support of national policy, agriculture has been integrated with rapidly developing information technology. New technologies such as the Internet of Things, artificial intelligence, cloud computing, and big data have been widely used in the field of agricultural production. After nearly a decade of development, various agricultural informatization application platforms have been formed that focus on Internet-of-Things-based agricultural monitoring supplemented by intelligent analysis. The demonstration of these platforms has promoted the modernization and transformation of traditional agriculture; however, the functional requirements of these platforms still need to be further integrated and improved to facilitate intelligent monitoring and sophisticated management in the overall agricultural production process. To improve the overall level of informatization of field crop production, this paper presents a comprehensive service platform for intelligent crop production in the field using a wide range of information technologies such as the agricultural Internet of Things, intelligent control, decision-making models, and big data mining. It integrates eight major business processes, including Internet-of-Things-based environmental perception, nitrogen fertilizer decision-making, agricultural remote sensing services, the intelligent management of water and nitrogen, pest monitoring and early warning, product traceability, and agricultural technology promotion, and provides a big data platform. The demonstration of the platform shows that its information services are rich in content, which meets the needs of different users for agricultural production-related data services and improves the precise management of the field crop production process. The proposed platform substantially advances the baseline for a comprehensive application for modern information technology in the intelligent production of field crops.

    Table and Figures | Reference | Related Articles | Metrics
    Estimating the Leaf Area Index of Maize based on Unmanned Aerial Vehicle Multispectral Remote Sensing
    Jia He, Laigang Wang, Yan Guo, Yan Zhang, Xiuzhong Yang, Ting Liu, Hongli Zhang
    Journal of Agricultural Big Data   2021, 3 (4): 20-28.  DOI:10.19788/j.issn.2096-6369.210403
    Abstract140)   HTML7)    PDF (1279KB)(50)      

    Remote sensing technology can be used to estimate the leaf area index (LAI) value of crops rapidly and harmlessly. The purpose of this study is to research the accuracy, reliability, and adaptability of the LAI using unmanned aerial vehicle (UAV) multispectral remote sensing. During a summer maize-fertilizer cross test, the LAI and multispectral images captured by a six-rotor UAV with a MicaSense RedEdge-M camera (which has five high-resolution channels: blue, green, red, red edge, and near infrared) were collected at the jointing, tasseling, and maturity stages of the maize. The normalized differential vegetation index (NDVI), optimized soil adjusted vegetation index (OSAVI), enhanced vegetation index (EVI), and normalized differential red edge index (NDRE) were calculated at each stage. The correlation between these metrics and the LAI were analyzed and their values were established based on the multispectral images at different growth stages. Then, an LAI model for each growth stage was established. After the accuracy of these models was tested using independent data, a maize LAI estimation map was made by processing each pixel in the maize multispectral image using these models. The results indicate the following: 1) There is a high correlation between the LAI and the NDVI, OSAVI, EVI, and NDRE values at the jointing, tasseling, and maturity stages. 2) LAI estimation models were established based on OSAVI, NDRE, and NDRE for the jointing, tasseling, and maturity stages, respectively. They had decision coefficient values (R2) of 0.549, 0.753, and 0.733, respectively, and the R2 of the verification models were 0.907, 0.932, and 0.926, respectively. The predicted and measured values at different growth stages had relative error values of 8.57, 8.37, and 9.24 and root-mean-squared error values of 0.104, 0.087, and 0.091, respectively. 3) The spatial distribution of the LAI at field scale was mapped by the LAI estimation models at each growth stage, yielding R2 values of 0.883, 0.931, and 0.867 and relative error values of 9.17, 8.86, and 9.32, respectively. Therefore, the LAI map reflected the real-world spatial distribution pattern of the LAI in the maize fields well. The established agricultural UAV remote sensing monitoring system provides accuracy, reliability, and adaptability for precision agriculture applications as well as the corresponding retrieval models for studying the feasibility of estimating the LAI during different growth stages.

    Table and Figures | Reference | Related Articles | Metrics
    Research on Intellectual Property Protection of Scientific Data Sharing
    Yahui Fan, Liang Zhu, Hua Zhao, Jianhua Zheng
    Journal of Agricultural Big Data   2021, 3 (4): 3-9.  DOI:10.19788/j.issn.2096-6369.210401
    Abstract138)   HTML13)    PDF (476KB)(58)      

    Scientific data is the most basic and active technological resources in the information era. Scientific data sharing is an inevitable trend of development. The implementation of scientific data sharing can save social resources, avoid duplication of labor, and verify existing scientific research. It has important practical significance and urgent social needs. As the premise of scientific data sharing, intellectual property protection plays a very important role in promoting the orderly use of scientific data and providing continuous innovation for the development of science and technology. It is the fundamental problem to be solved urgently to realize scientific data sharing. This paper mainly uses literature research, comparative analysis and other methods to analyze the relevant literature on scientific data and intellectual property rights at home and abroad in recent years. On the basis of summarizing the current situation of intellectual property protection of scientific data sharing in China, the relationship between scientific data sharing and intellectual property rights is excavated, and the main problems of intellectual property protection faced by scientific data sharing are extracted. The determination of data property rights and ownership is the basis for the distribution of rights and interests of scientific data sharing applications. At present, the ownership of scientific data property rights in China is not clear, and there is a lack of recognized property rights solutions. Lack of unified policy guidance, weak awareness of intellectual property protection and lack of motivation for scientific data publishing. In view of these problems, this paper puts forward the intellectual property protection countermeasures for scientific data sharing: clarify the ownership of scientific data property rights and balancing the interests of all parties; establish government guidance mechanism, and make the government fully functional; promote scientific data publishing and standardize scientific data citation; ensure the intellectual property protection technology support for innovative scientific data sharing. In order to build a good data sharing environment, we should protect the legitimate rights and interests of data producers.

    Reference | Related Articles | Metrics
    Data Mining for Fishing Vessel Purchase Based on Gradient Boosting Decision Tree Algorithm
    Yide Li, Feng Lu, Yong Zhu, Shuo Xu, Lu Sun
    Journal of Agricultural Big Data   2021, 3 (3): 55-61.  DOI:10.19788/j.issn.2096-6369.210306
    Abstract138)   HTML2)    PDF (712KB)(21)      

    The purchase of a fishing vessel is a significant and complex process in the daily management of marine fishing fleets, and it yields the largest amount of data in all fishing vessel management operations. Through processing and analysis of the historical purchase data of fishing vessels, the potential decisive factors related to the purchase of fishing vessels can be found. This is significant to the protection of fishermen's economic interests and the development of fishing vessel management policies. We extracted and numerically processed the historical purchase data of fishing vessels from January 2018 to July 2020 using the physical and purchase data of fishing vessels in the Chinese Fishery Law Enforcement Command System (CFLECS) and taking Zhejiang Province as a typical case. The gradient boosting iterative decision tree (GBDT) algorithm was used to iterate the classifier regularly. We produced the results of feature classification and training set, and these were used to generate single decision tree and multiple decision tree models. We calculated the weight of the basic parameters of fishing vessels, such as length, material, and fishing type, to predict the potential possibility of fishing vessel transactions and to analyze the tendencies of fishermen when purchasing fishing vessels. The results indicate that age, length, trawler, and stow net are the principal determinants of fishing vessel transactions. The trawler and stow net vessel can only be obtained through the fishing vessel transaction. Thus, when the fishing vessel types are different, there is a great difference in the possibility of their being purchased. By comparing the loss functions of various features, we can find that the loss values of features with 20 years of age and ship length are more than 15% smaller than the loss values of other features, which means that the classification recognition rate calculated with selected features is higher. Consequently, quantitative analysis for fishermen's propensity to purchase fishing vessels can maximize fishermen's economic interests, and it can also play an auxiliary role in the formulation of fishing vessel management policy.

    Table and Figures | Reference | Related Articles | Metrics
    Design and Implementation of a Trusted Tea Quality Control System Based on Edge Intelligence
    Yali Shu, Yuan Rao, Lei Xu
    Journal of Agricultural Big Data   2021, 3 (4): 40-50.  DOI:10.19788/j.issn.2096-6369.210405
    Abstract109)   HTML11)    PDF (1830KB)(68)      

    The process of tea production and processing is characterized by multiple types of hazardous substances, low information utilization, and multi-source data heterogeneity. However, the traditional tea quality supervision and traceability system has several problems. For instance, tea quality control data are easily tampered with or forged; the credibility of data sources is difficult to guarantee; and the privacy of enterprises cannot be guaranteed. To enhance the management of tea quality control and improve the credibility of tea quality control information, a trusted tea quality control system architecture based on edge intelligence was designed based on blockchain and edge intelligence technologies. The system includes a data perception layer, an edge layer, a storage layer, and an application layer. It utilizes intelligent equipment and IoT technology to perform mechanized operations and automatically obtain tea quality control data. It then takes advantage of the network, computing, and storage resources of edge computing devices. A variety of artificial intelligence algorithms are deployed at the edge of the data source to detect the authenticity of the data. The Hyperledger Fabric open source framework is used as the blockchain platform to build a trusted storage service, and MySQL is used as the off-chain database. The key data are hierarchically encrypted and stored in the blockchain network and off-chain database, and the information is summarized on the chain for storage to ensure that the off-chain data cannot be tampered with and to realize the dual on-chain and off-chain trusted storage modes. Finally, a trusted tea quality control system based on edge intelligence was developed, and a combination of Internet and mobile terminals is used to provide enterprises, regulatory authorities, and consumers with services such as intelligent information acquisition, whole-process management, and trusted traceability. This proposed system can provide a real-time tea quality control information verification service for supervision departments, which helps them to carry out their work. In addition, it strikes a balance between the needs of enterprises to protect private data and the needs of consumers for open and trusted tea traceability data, which protects consumers' right to know and increases their trust in product quality.

    Table and Figures | Reference | Related Articles | Metrics
    Construction and Implementation of Fujian Provincial Science and Technology Commissioner Service Cloud Platform Based on Big Data
    Zhipeng Li, Jian Zhao, Miaomiao Wang, Hong Chen, Xiaodang Gao
    Journal of Agricultural Big Data   2021, 3 (4): 59-69.  DOI:10.19788/j.issn.2096-6369.210407
    Abstract105)   HTML9)    PDF (1475KB)(46)      

    The science and technology commissioner is an important starting point for agricultural technology innovation and agricultural technology services. The application of modern information technology to satisfy the production needs of farmers and improve the work efficiency of the science and technology commissioner, which has become an important means to improve the service level of the science and technology commissioner.


    On the basis of detailed analysis of the development status quo and needs of science and technology commissioners in Fujian Province, the overall framework of the service cloud platform for science and technology commissioners is constructed under the guidance of big data and cloud computing thinking. Detailed design and practical application have been carried out, which have also been applied in the selection, management and service of scientific and technological missions.


    In terms of data resources, an object-oriented "dual tree structure" entity-relationship model of agricultural knowledge has been innovatively constructed. 142 thematic databases have been built according to types, including nearly 200,000 pieces of technical information; In terms of management, the platform has functions such as online selection, knowledge service, demand release, achievement docking, interactive consultation, dynamic tracking, big data analysis, etc., and realizes the online application, assessment management, performance evaluation, dynamic service. When applying for science and technology commissioners, the application of informatization has greatly improved the efficiency of registration and review. At the same time, the accumulation of points for the services of each science and technology commissioner also provides a basis for the selection of science and technology commissioners in the next year. In terms of service, it has enriched the supply methods of agricultural and rural science and technology innovation, and helped more than 5,000 science and technology commissioners in the province to provide real-time online services for the production line, effectively expanding the service scope and service depth of science and technology commissioners. The lack of "combat in the army" in the process allows science and technology commissioners with different disciplines and professional backgrounds to realize "group services" on the platform, collaboratively solve various industrial technical problems, and realize "cloud" precise services, remote services, and dynamic services, so that farmers and enterprises can obtain timely and rapid remote support from scientific and technological commissioners and teams without leaving home. In terms of service channels, Wechat Official Accounts and small programs have worked well, effectively increasing the user's viscosity.


    The construction has innovated the supply and demand docking mechanism of agricultural technology, realized the "order-based" demand docking and "menu-based" service supply mode, and enabled the platform to have the functions of "technology intermediary" and "talent intermediary", preventing it from being divorced from grass-roots reality and improving service effectiveness. Also, it has provided technical support for comprehensive rural revitalization and agricultural supply-side reform. How to mine and analyze large-scale agricultural data is an important direction for the next cloud platform construction.

    Table and Figures | Reference | Related Articles | Metrics
    Journal of Agricultural Big Data   2021, 3 (3): 1-2.  DOI:10.19788/j.issn.2096-6369.2021.03.001
    Abstract89)   HTML14)    PDF (638KB)(42)      
    Reference | Related Articles | Metrics
    Research and Development of an Intelligent Management Platform for Native Chinese Pig Breeds in Anhui Province
    Bolun Guan, Guimin Liu, Wei Dong, Liping Zhang, Rong Qian
    Journal of Agricultural Big Data   2021, 3 (4): 51-58.  DOI:10.19788/j.issn.2096-6369.210406
    Abstract84)   HTML3)    PDF (1173KB)(41)      

    With the continuous popularization of information technology, animal husbandry informatization has rapidly developed. As a major pig breeding province, Anhui occupies a vital position in the animal husbandry industry in China. There are various breeds of local pigs in Anhui, and the meat of local Anhui pig breeds is delicious and has high nutritional value. However, the growth cycle of pig breeds in Anhui is long and mostly based on small-and medium-scale cultivation, which leads to higher artificial costs and lower feeding capabilities in native breeding pigs. Thus, the number of local pig breeds has decreased. Considering the problems of long growth cycle and high labor cost of the small-scale breeding of Anhui local pig breeds, this paper presents a pig breeding information management platform developed to realize the overall intelligent management of pig breeding information. The platform adopts a B/S architecture, which is divided into a view layer, logical business layer, and data layer. It has eight functional events, such as boarhsow events, piglet fattening, pig farm veterinarian visits, and statistical analysis. Moreover, it connects mobile terminals and the Internet. Furthermore, a reasonable database structure that closely matches production requirements has been designed. The platform is convenient for retail and small-scale users; substantially reduces the labor costs of pig breeding; and improves the intelligence, standardization, and informatization of pig breeding. The results of a trial show that the live pig breeding information management platform can provide efficient and comprehensive information management and reduce the production cost for individual and small-scale pig breeders. Simultaneously, it can dynamically monitor production data and facilitate scientific decision-making.

    Table and Figures | Reference | Related Articles | Metrics