气象大数据超短临精准降水机器学习与典型应用

doi:10.19788/j.issn.2096-6369.190108

农业大数据学报 ›› 2019, Vol. 1 ›› Issue (1): 78-87.doi: 10.19788/j.issn.2096-6369.190108

气象大数据超短临精准降水机器学习与典型应用

张晨阳^1,^2,³(),杨雪冰^1,³,张文生^1,^2,^3,^*()

^1. 中国科学院自动化研究所,北京 100190
^2. 中国科学院大学,北京 100049
^3. 气象大数据与机器学习联合实验室,北京 100190

收稿日期:2018-08-28 出版日期:2019-03-26 发布日期:2019-04-04
通讯作者: 张文生 E-mail:zhangchenyang2016@ia.ac.cn;zhang@ia.ac.cn
作者简介:张晨阳,男,博士。研究方向：机器学习,深度学习,农业气象数据挖掘|杨雪冰,男,博士、助理研究员。研究方向：机器学习,农业气象数据挖掘;Email： <email>yangxuebing2013@ia.ac.cn</email>
基金资助:
国家自然科学基金(61602482、61472423)

Accurate Precipitation Nowcasting with Meteorological Big Data: Machine Learning Method and Application

Zhang Chenyang^1,^2,³(),Yang Xuebing^1,³,Zhang Wensheng^1,^2,^3,^*()

^1. Institute of Automation, Chinese Academy of Sciences, Beijing 100190
^2. University of Chinese Academy of Sciences, Beijing 100049
^3. Joint Laboratory of Meteorological Big Data and Machine Learning, Beijing 100190

Received:2018-08-28 Online:2019-03-26 Published:2019-04-04
Contact: Zhang Wensheng E-mail:zhangchenyang2016@ia.ac.cn;zhang@ia.ac.cn

摘要/Abstract

摘要：

超短临精准的降水估计对农业生产、水文监测、洪涝减灾、大型活动、电力系统等方面具有重要意义。由于天气系统具有高度不确定性,传统基于物理模型和统计分析的气象方法在降水估计中难以满足高分辨率条件下的精度要求,如何提升超短临降水估计的精准性在研究和应用领域是极具挑战性的问题。本文提出了基于地形的加权随机森林(terrain-based weighted random forests, TWRF)方法用于雷达定量降水估计(quantitative precipitation estimation, QPE)。该方法可视为随机森林方法的推广,并在此基础上考虑了反射率垂直廓线(vertical profile of reflectivity, VPR)的特征重要性变化以及复杂地形区域降水的山岳抬升效应。对TWRF在中国杭州湾地区Z9571雷达45~100km覆盖范围内2014年6月份和7月份的降水过程上进行了实验验证,结果表明TWRF方法优于传统气象方法及随机森林方法,并表明利用整个VPR与基于地形的建模可以有效提升雷达QPE效果。

关键词: 气象大数据, 定量降水估计, 随机森林, 机器学习, 天气雷达

Abstract:

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.

Key words: meteorological big data, quantitative precipitation estimation, random forests, machine learning, weather radar

中图分类号:

张晨阳, 杨雪冰, 张文生. 气象大数据超短临精准降水机器学习与典型应用[J]. 农业大数据学报, 2019, 1(1): 78-87.

Zhang Chenyang, Yang Xuebing, Zhang Wenshen. Accurate Precipitation Nowcasting with Meteorological Big Data: Machine Learning Method and Application[J]. Journal of Agricultural Big Data, 2019, 1(1): 78-87.

图/表 7

图1

图2

图3

图4

表1

图5

图6

参考文献 31

[1]	S.M. Sumi, M.F. Zaman, H. Hirose . A rainfall forecasting method using machine learning models and its application to the Fukuoka city case[J]. International Journal of Applied Mathematics and Computer Science, 2012,22(4):841-854.
[2]	B. Sivakumar, F.M. Woldemeskel . A network-based analysis of spatial rainfall connections[J]. Environmental Modelling and Software, 2015,69(C):55-62. doi: 10.1016/j.envsoft.2015.02.020
[3]	S. Araghinejad, M. Azmi, M. Kholghi . Application of artificial neural network ensembles in probabilistic hydrological forecasting[J]. Journal of Hydrology, 2011,407:94-104. doi: 10.1016/j.jhydrol.2011.07.011
[4]	A.G. Evsukoff, M. Cataldi, B.S.L.P.D. Lima . A multi-model approach for long-term runoff modeling using rainfall forecasts[J]. Experts Systems with Applications, 2012,39(5):4938-4946. doi: 10.1016/j.eswa.2011.10.023
[5]	俞小鼎, 姚秀萍, 熊廷南 , 等. 多普勒天气雷达原理与业务应用[M]. 北京: 气象出版社, 2006.
	Yu X D, Yao X P, Xiong T N , et al. Principle and Application of Doppler Weather Radar[M]. Beijing: China Meteorological Press, 2006.
[6]	T.W. Harrold, E.J. English, C.A. Nicholass . The accuracy of radar-derived rainfall measurements in hilly terrain[J]. Quarterly Journal of the Royal Meteorological Society, 1974,100(425):331-350. doi: 10.1002/qj.49710042506
[7]	J.S. Marshall , W.M.K. Plamer. The distribution of raindrops with size[J]. Journal of Meteorology, 1948,5(4):165-166.
[8]	J.W. Wilson, E.A. Brandes . Radar measurement of rainfall - a summary[J]. Bulletin of the American Meteorological Society, 1979,60(9):1048-1058. doi: 10.1175/1520-0477(1979)060<1048:RMORS>2.0.CO;2
[9]	W. Hall , M.A. Rico-Ramirez, S. Kramer. Classification and correction of the bright band using an operational C-band polarimetric radar[J]. Journal of Hydrology, 2015,531:248-258. doi: 10.1016/j.jhydrol.2015.06.011
[10]	R. Wexler . Radar detection of a frontal storm 18 June 1946[J]. Journal of Meteorology , 1947 ,4(1): 38-44. doi: 10.1175/1520-0469(1947)0042.0.CO;2
[11]	J.S. Marshall, R.C. Langille, W.M.K. Palmer. Measurement of rainfall by radar[J]. Journal of Meteorology, 1947,4(6):186-192. doi: 10.1175/1520-0469(1947)0042.0.CO;2
[12]	Q. Cao, Y. Hong, Y. Qi , et al. Empirical conversion of the vertical profile of reflectivity from Ku-band to S-band frequency[J]. Journal of Geophysical Research Atmospheres, 2013,118(4):1814-1825. doi: 10.1002/jgrd.50138
[13]	Q. Cao, Y. Wen, Y. Hong , et al. Enhancing quantitative precipitation estimation over the continental United States using a ground-space multi-sensor integration approach[J]. IEEE Geoscience and Remote Sensing Letters, 2014,11(7):1305-1309. doi: 10.1109/LGRS.2013.2295768
[14]	J. Zhang, K. Howard, X. Xu, et al. A warm season radar QPE algorithm using adaptive Z-R relationships [C]. World Environmental and Water Resources Congress, 2008, 1-10.
[15]	H. Seyyedi, E.N. Anagnostou, P.E. Kirstetter , et al. Incorporating surface soil moisture information in error modeling of TRMM passive microwave rainfall[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014,52(10):6226-6240. doi: 10.1109/TGRS.2013.2295795
[16]	肖现, 廖菲, 肖辉 , 等. 北京对流性降水的雨滴尺寸分布瞬时特征与雷达降水的关系[J]. 热带气象学报, 2010,26(4):445-451.
	Xiao X, Liao F, Xiao H , et al. Systematic Variation of Drop Size in Convective if Beijing and Radar-Rainfall Relations[J]. Journal of Tropical Meteorology, 2010,26(4):445-451.
[17]	肖艳娇, 万玉发, 王珏 , 等. 改进的C波段天气雷达定量降水估计算法研究[J]. 暴雨灾害, 2011,30(4):321-327.
	Xiao Y J, Wan Y F, Wang J , et al. Study of an Improved Modified C-Band Radar Quantitative Precipitation Estimation Algorithm[J]. Torrential Rain and Disasters, 2011,30(4):321-327.
[18]	高晓荣, 梁建茵, 李春晖 , 等 . 多平台(雷达、卫星、雨量计)降水信息的融合技术初探[J]. 高原气象, 2013,32(2):549-555.
	Gao X R, Liang J Y, LI C H , et al. Preliminary Studies on Merged Techniques Based on Precipitation Information from Multiplatform(Radar,Satellite and Rain Gauge)[J]. Plateau Meteorology, 2013,32(2):549-555.
[19]	龚雪鹏, 徐晓, 聂祥 , 等. 毕节CINRAD/CD雷达定量估测降水Z-I关系的研究[J]. 科技风, 2017,1:77-78.
	Gong X P, Xu X, Nie X , et al. Research on the Quantitative Estimation of Precipitation Z-I relationship by CINRAD/CD Radar in Bijie[J]. Technology Wind, 2017,1:77-78.
[20]	R. Xiao, V. Chandrasekar . Development of a neural network based algorithm for rainfall estimation from radar observations[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997,35(1):160-171. doi: 10.1109/36.551944
[21]	W. Hong . Rainfall forecasting by technological machine learning models[J]. Applied Mathematics and Computation, 2008,200(1):41-57. doi: 10.1016/j.amc.2007.10.046
[22]	A. Kusiak, X. Wei, A.P. Verma , et al. Modeling and prediction of rainfall using radar reflectivity data: a data-mining approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013,51(4):2337-2342. doi: 10.1109/TGRS.2012.2210429
[23]	X. Shi, Z. Chen, H. Wang, et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting [C]. International Conference on Neural Information Processing Systems, 2015, 802-810.
[24]	X. Shi, Z. Gao, L. Lausen, et al. Deep learning for precipitation nowcasting: a benchmark and a new model [C]. International Conference on Neural Information Processing Systems, 2017, 5617-5627.
[25]	L. Breiman . Random forests[J]. Machine Learning, 2001,45(1):5-32. doi: 10.1023/A:1010933404324
[26]	M. Fernàndez-Delgado, E. Cernadas, S. Barro , et al. Do we need hundreds of classifiers to solve real world classification problems?[J]. Journal of Machine Learning Research, 2014,15(1):3133-3181.
[27]	B. Xu, J.Z. Huang, G. Williams , et al. Classifying very high-dimensional data with random forests built from small subspaces[J]. International Journal of Data Warehousing and Mining, 2012,8(2):44-63. doi: 10.4018/jdwm.2012040103
[28]	E. Richard, N. Chaumerliac, J.F. Mahfouf , et al. Numerical simulation of orographic enhancement of rain with a mesoscale model[J]. Journal of Applied Meteorology, 1987,26(6):661-669.
[29]	V. Lakshmanan, A. Fritz, T. Smith , et al. An automated technique to quality control radar reflectivity data[J]. Journal of Applied Meteorology and Climatology, 2007,46(3):288-305. doi: 10.1175/JAM2460.1
[30]	P.P. Mapiam, N. Sriwongsitanon . Climatological Z-R relationship for radar rainfall estimation in the upper Ping river basin[J]. ScienceAsia, 2008,34(2):215-222.
[31]	F. Fabry, A. Bellon, M.R. Duncan , et al. High resolution rainfall measurements by radar for very small basins: the sampling problem reexamined[J]. Journal of Hydrology, 1994,161:415-428. doi: 10.1016/0022-1694(94)90138-4

方法	RMSE (mm h^-1)	MAE (mm h^-1)	CC
Z-R关系	2.318	1.132	0.756
RF	2.101	1.040	0.801
WRF	2.046	1.022	0.812
TWRF	1.991	0.997	0.823

气象大数据超短临精准降水机器学习与典型应用

Accurate Precipitation Nowcasting with Meteorological Big Data: Machine Learning Method and Application

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 31

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	阿依吐拉·买买提祖农null, 帅艳菊, 魏浩东, 何真, 肖沁茜, 胡琼, 徐保东, 游良志, 曹凑贵, 凌霖. 基于遥感识别与DNDC模型的不同稻作模式评价——以潜江市为例[J]. 农业大数据学报, 2021, 3(3): 33-44.
[2]	李晓曼,张扬,徐倩,谢能付. 基于文献计量的植物表型组学研究进展分析[J]. 农业大数据学报, 2019, 1(2): 64-75.
[3]	吴蕾,梁晓贺,乌吉斯古楞,王瑞. 基于词向量的检索扩展方法与农业领域实证[J]. 农业大数据学报, 2019, 1(2): 114-120.
[4]	崔运鹏, 王健, 刘娟. 基于深度学习的自然语言处理技术的发展及其在农业领域的应用[J]. 农业大数据学报, 2019, 1(1): 38-44.