Analysis of the Simulation Performances of Precipitation Statistical Forecasting Models

Yiqi CHEN; Xianghua WU; Peng LIU; Duanyang LIU

doi:10.3878/j.issn.1006-9585.2022.21058

Volume 27 Issue 5

Sep. 2022

Turn off MathJax

Article Contents

Article Navigation > Climatic and Environmental Research > 2022 > 27(5): 578-590

CHEN Yiqi, WU Xianghua, LIU Peng, et al. 2022. Analysis of the Simulation Performances of Precipitation Statistical Forecasting Models [J]. Climatic and Environmental Research (in Chinese), 27 (5): 578−590 doi: 10.3878/j.issn.1006-9585.2022.21058

Citation:

PDF( 3222 KB)

Analysis of the Simulation Performances of Precipitation Statistical Forecasting Models

doi: 10.3878/j.issn.1006-9585.2022.21058

1.
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044
2.
School of Atmospheric Sciences, Nanjing University of Information Science and Technology, Nanjing 210044
3.
Nanjing Institute of Transportation Meteorology, Nanjing 210008

Funds: National Key Research and Development Program of China (Grant 2018YFC1507905), National Natural Science Foundation of China (Grants 42075068, 41505118, 41975087, and 41605045)

Received Date: 2021-03-20
Available Online: 2022-05-17
Publish Date: 2022-09-25

Abstract

Abstract

The performance of a precipitation forecast model is related to many factors. In addition to research areas and research data characteristics, it is also affected by the model's algorithm, statistical simulation methods, and performance metrics. This paper is based on the daily rainfall, average temperature, and average relative humidity of 28 stations in Heilongjiang Province in China from 2015 to 2019, using Monte Carlo statistical simulation methods such as Hold-out, Bootstrap, and machine learning methods. For the first time, this paper systematically studied the performances of daily precipitation forecast models in Heilongjiang Province in the summer and the spatial distribution characteristics of the model performances. The results show that for the entire study area, the overall prediction performance of a BP (Back Propagation) neural network and support vector machine is not significantly different, and the value of the area under ROC cuvre is higher than 76%, which is significantly better than that of the decision tree. The prediction performance of the model estimated by Bootstrap is always better than that of Hold-out, and it helps improve the fidelity of the evaluation results. For a single station in the study area, except for certain stations, the value of accuracy and the area under ROC cuvre of the support vector machine are higher than 80%, and the spatial distribution trend is larger in the southeast and smaller in the northwest. This trend is basically consistent with the distribution of precipitation frequency. The overall prediction effect of the SVM (Support Vector Machine) model is better in the Xiaokingan and Zhangguangcai Mountains, followed by the Sanjiang and Songnen Plains. The sensitivity is higher in mountainous areas than in plain areas. The central and southern regions are larger, followed by the eastern region and then the western and northern regions. The spatial distribution of specificity is simply the opposite of that of sensitivity.
- Summer precipitation forecast,
- Machine learning,
- Hold-out method,
- Cross-validation,
- Bootstrap method

FullText(HTML)

References(38)

References

[1]	Aparna S G, D’Souza S, Arjun N B. 2018. Prediction of daily sea surface temperature using artificial neural networks [J]. Int. J. Remote Sens., 39(12): 4214−4231. doi: 10.1080/01431161.2018.1454623
[2]	白杨, 李威, 邵祺. 2020. 基于经验正交函数和机器学习的南海海面高度异常预测 [J]. 海洋通报, 39(6): 678−688. doi: 10.11840/j.issn.1001-6392.2020.06.005 Bai Yang, Li Wei, Shao Qi. 2020. A prediction model of sea surface height anomaly based on empirical orthogonal function and machine learning [J]. Marine Science Bulletin (in Chinese), 39(6): 678−688. doi: 10.11840/j.issn.1001-6392.2020.06.005
[3]	陈超辉, 李崇银, 谭言科, 等. 2010. 基于交叉验证的多模式超级集合预报方法研究 [J]. 气象学报, 68(4): 464−476. doi: 10.11676/qxxb2010.045 Chen Chaohui, Li Congyin, Tan Yanke, et al. 2010. Research of the multi-model super-ensemble prediction based on cross-validation [J]. Acta Meteorologica Sinica (in Chinese), 68(4): 464−476. doi: 10.11676/qxxb2010.045
[4]	陈茜, 欧阳绳武, 马新宇, 等. 2018. 基于BP神经网络的心电信号智能诊断设计 [J]. 现代电子技术, 41(1) 76–80. Chen Qian, Ouyang Shengwu, Ma Xinning, et al. 2018. Design of electrocardiosignal intelligent diagnosis based on BP neural network[J]. Modern Electronics Technique, 41(1): 76−80. doi: 10.16652/j.issn.1004-373x.2018.01.017
[5]	Choubin B, Zehtabian G, Azareh A, et al. 2018. Precipitation forecasting using classification and regression trees (CART) model: A comparative study of different approaches [J]. Environmental Earth Sciences, 77(8): 314. doi: 10.1007/s12665-018-7498-z
[6]	范科科, 段利民, 张强, 等. 2017. 基于多种高分辨率卫星数据的TRMM降水数据降尺度研究——以内蒙古地区为例 [J]. 地理科学, 37(9): 1411−1421. doi: 10.13249/j.cnki.sgs.2017.09.014 Fan Keke, Duan Limin, Zhang Qiang, et al. 2017. Downscaling analysis of TRMM precipitation based on multiple high-resolution satellite data in the Inner Mongolia, China [J]. Scientia Geographica Sinica, 37(9): 1411−1421. doi: 10.13249/j.cnki.sgs.2017.09.014
[7]	葛彩莲, 蔡焕杰, 王健, 等. 2010. 基于BP神经网络的降雨量预测研究 [J]. 节水灌溉, (11): 7−10. Ge Cailian, Cai Huanjian, Wang Jian, et al. 2010. Study on rainfall forecast based on BP neural network [J]. Water Saving Irrigation (in Chinese), (11): 7−10.
[8]	Hamidi O, Poorolajal J, Sadeghifar M, et al. 2015. A comparative study of support vector machines and artificial neural networks for predicting precipitation in Iran [J]. Theor. Appl. Climatol. , 119(3–4): 723–731. doi: 10.1007/s00704-014-1141-z
[9]	韩玉梅. 2008. 黑龙江省年降水量时空分布分析 [J]. 黑龙江水利科技, 36(3): 4−5. doi: 10.3969/j.issn.1007-7596.2008.03.003 Han Yumei. 2008. Spatial and temporal distribution of annual precipitation in Heilongjiang Province [J]. Heilongjiang Science and Technology of Water Conservancy (in Chinese), 36(3): 4−5. doi: 10.3969/j.issn.1007-7596.2008.03.003
[10]	何东坡. 2016. 基于数据挖掘方法的长江中下游夏季降水等级预测模型研究与应用 [D]. 南京信息工程大学硕士学位论文. He Donhpo. 2016. Research and application of the forecast model of summer precipitation in the middle and lower reaches of the Yangtze River based on data mining method [D]. M. S. thesis (in Chinese), Nanjing University of Information Science and Technology.
[11]	He X G, Chaney N W, Schleiss M, et al. 2016. Spatial downscaling of precipitation using adaptable random forests [J]. Water Resour. Res., 52(10): 8217−8237. doi: 10.1002/2016WR019034
[12]	Ho H C, Knudby A, Sirovyak P, et al. 2014. Mapping maximum urban air temperature on hot summer days [J]. Remote Sensing of Environment, 154: 38−45. doi: 10.1016/j.rse.2014.08.012
[13]	Hecht-Nielsen R. 1989. Theory of the backpropagation neural network[C]. International 1989 Joint Conference on Neural Networks, 593-605 vol. 1.
[14]	胡凤良, 王丽琼, 左瑞亭, 等. 2017. 几种统计预测方法对1998年南京降水的跨季节预测试验及分析 [J]. 气候与环境研究, 22(1): 23−34. doi: 10.3878/j.issn.1006-9585.2016.15251 Hu Fengliang, Wang Liqiong, Zuo Ruiting, et al. 2017. Extra-seasonal predicting tests and analyses of several statistical forecasting methods on precipitation over Nanjing in 1998 [J]. Climatic and Environmental Research (in Chinese), 22(1): 23−34. doi: 10.3878/j.issn.1006-9585.2016.15251
[15]	孔德萌, 李维德, 吴金冉. 2017. 基于协整理论的极限学习机模型在降水预测中的应用 [J]. 水电能源科学, 35(9): 1−3, 12. Kong Demeng, Li Weide, Wu Jinran. 2017. Application of extreme learning machine model in precipitation prediction based on cointegration theory [J]. Water Resources and Power (in Chinese), 35(9): 1−3, 12.
[16]	Kusiak A, Zheng H Y, Song Z. 2009. Wind farm power prediction: A data-mining approach [J]. Wind Energy, 12(3): 275−293. doi: 10.1002/we.295
[17]	李嘉康, 赵颖, 廖洪林, 等. 2017. 基于改进EMD算法和BP神经网络的SST预测研究 [J]. 气候与环境研究, 22(5): 587−600. doi: 10.3878/j.issn.1006-9585.2017.16180 Li Jiakang, Zhao Ying, Liao Honglin, et al. 2017. SST forecast based on BP neural network and improved EMD algorithm [J]. Climatic and Environmental Research (in Chinese), 22(5): 587−600. doi: 10.3878/j.issn.1006-9585.2017.16180
[18]	李宁. 2011. BP神经网络在水文数据中的应用研究 [D]. 山西财经大学硕士学位论文. Li Ning. 2011. Research on the application of BP-neural network in the hydrologic data [D]. M. S. thesis (in Chinese), Shanxi University of Finance and Economics.
[19]	李万庆, 李海涛, 孟文清. 2007. 基于支持向量机的降水量混沌时间序列预测 [J]. 统计与决策, (19): 9−11. doi: 10.3969/j.issn.1002-6487.2007.19.004 Li Wanqing, Li Haitao, Meng Wenqing. 2007. Prediction of precipitation chaotic time series based on support vector machine [J]. Statistics and Decision (in Chinese), (19): 9−11. doi: 10.3969/j.issn.1002-6487.2007.19.004
[20]	梁子超, 李智炜, 赖铿, 等. 2020. 10折交叉验证用于预测模型泛化能力评价及其R软件实现 [J]. 中国医院统计, 27(4): 289−292. doi: 10.3969/j.issn.1006-5253.2020.04.001 Liang Zichao, Li Zhiwei, Lai Keng, et al. 2020. Application of 10-fold cross-validation in the evaluation of generalization ability of prediction models and the realization in R [J]. Chinese Journal of Hospital Statistics (in Chinese), 27(4): 289−292. doi: 10.3969/j.issn.1006-5253.2020.04.001
[21]	刘莉, 叶文. 2010. 基于BP神经网络时间序列模型的降水量预测 [J]. 水资源与水工程学报, 21(5): 156−159. Liu Li, Ye Wen. 2010. Precipitation prediction of time series model based on BP artificial neural network [J]. Journal of Water Resources and Water Engineering (in Chinese), 21(5): 156−159.
[22]	黎玥君, 郭品文, 2017. 基于BP神经网络的浙北夏季降尺度降水预报方法的应用[J]. 大气科学学报, 40(3): 425-432 Li Yuejun, Guo Pinwen, 2017. Application of downscaling forecast for the North of Zhejiang precipitation in summer based on the BP neural network model [J]. Trans Atmos Sci (in Chinese), 40(3): 425-432. doi: 10.13878/j.cnki.Dqkxxb.20140324001.
[23]	倪远臣. 2014. 基于支持向量机的东港市降水量预测模型研究 [J]. 陕西水利, (2): 134−135. doi: 10.3969/j.issn.1673-9000.2014.02.067 Ni Yuanchen. 2014. Research on precipitation forecast model of Donggang city based on support vector machine [J]. Shaanxi Water Resources (in Chinese), (2): 134−135. doi: 10.3969/j.issn.1673-9000.2014.02.067
[24]	Ortiz-García E G, Salcedo-Sanz S, Casanova-Mateo C. 2014. Accurate precipitation prediction with support vector classifiers: A study including novel predictive variables and observational data [J]. Atmospheric Research, 139: 128−136. doi: 10.1016/j.atmosres.2014.01.012
[25]	Schuldt C, Laptev I, Caputo B. 2004. Recognizing human actions: A local SVM approach [E]. International Conference on Pattern Recognition. IEEE Computer Society. doi: 10.1109/ICPR.2004.1334462
[26]	沈皓俊, 罗勇, 赵宗慈, 等. 2020. 基于LSTM网络的中国夏季降水预测研究 [J]. 气候变化研究进展, 16(3): 263−275. doi: 10.12006/j.issn.1673-1719.2019.067 Shen Haojun, Luo Yong, Zhao Zongci, et al. 2020. Prediction of summer precipitation in China based on LSTM network [J]. Climate Change Research (in Chinese), 16(3): 263−275. doi: 10.12006/j.issn.1673-1719.2019.067
[27]	石晓燕, 郑庆康, 杨涛. 2013. 基于BP神经网络对黄河源区降水的降尺度模拟研究 [J]. 三峡大学学报(自然科学版), 35(5): 37−41. Shi X Y, Zheng Q K, Yang T. 2013. Downscaling analysis of precipitation in source region of Yellow River simulated by using BP neural network [J]. Journal of China Three Gorges University (Natural Sciences) (in Chinese), 35(5): 37−41.
[28]	史逸民, 史达伟, 郝玲, 等. 2018. 基于数据挖掘CART算法的区域夏季降水日数分类与预测模型研究 [J]. 南京信息工程大学学报(自然科学版), 10(06): 760−765. doi: 10.13878/j.cnki.jnuist.2018.06.015 Shi Yimin, Shi Dawei, Hao Linh, et al. 2018. Model prediction of regional summer precipitation days based on CART algorithm [J]. Journal of Nanjing University of Information Science and Technology (Natural Sciences) (in Chinese), 10(06): 760−765. doi: 10.13878/j.cnki.jnuist.2018.06.015
[29]	孙健, 曹卓, 李恒, 等. 2021. 人工智能技术在数值天气预报中的应用 [J]. 应用气象学报, 32(1): 1−11. doi: 10.11898/1001-7313.20210101 Sun Jian, Cao Zhuo, Li Heng, et al. 2021. Application of artificial intelligence technology to numerical weather prediction [J]. Journal of Applied Meteorological Science (in Chinese), 32(1): 1−11. doi: 10.11898/1001-7313.20210101
[30]	Voyant C, Notton G, Kalogirou S, et al. 2017. Machine learning methods for solar radiation forecasting: A review [J]. Renewable Energy, 105: 569−582. doi: 10.1016/j.renene.2016.12.095
[31]	许晓宁. 2018. 基于支持向量机的逐日降水预报模型研究 [D]. 华东师范大学硕士学位论文. Xu Xiaoning. 2018. Research on day-by-day precipitation forecast model based on support vector machine [D]. M. S. thesis (in Chinese), East China Normal University.
[32]	杨淑群, 芮景析, 冯汉中. 2006. 支持向量机(SVM)方法在降水分类预测中的应用 [J]. 西南农业大学学报(自然科学版), 28(2): 252−257. doi: 10.3969/j.issn.1673-9868.2006.02.020 Yang Shuqun, Rui Jingxi, Feng Hanzhong. 2006. Application of support vector machine (SVM) in rainfall categorical forecast [J]. Journal of Southwest Agricultural University (Natural Science) (in Chinese), 28(2): 252−257. doi: 10.3969/j.issn.1673-9868.2006.02.020
[33]	杨永生, 何平. 2008. 投影寻踪回归与BP神经网络方法在前汛期降水预测中的比较研究 [J]. 气象与环境学报, 24(1): 14−17. doi: 10.3969/j.issn.1673-503X.2008.01.004 Yang Yongsheng, He Ping. 2008. Comparison on early flood season precipitation prediction between projection pursuit regression method and back propagation neural network method [J]. Journal of Meteorology and Environment (in Chinese), 24(1): 14−17. doi: 10.3969/j.issn.1673-503X.2008.01.004
[34]	曾晓青, 邵明轩, 王式功, 等. 2008. 基于交叉验证技术的KNN方法在降水预报中的试验 [J]. 应用气象学报, 19(4): 471−478. doi: 10.3969/j.issn.1001-7313.2008.04.011 Zeng Xiaoqing, Shao Mingxuan, Wang Shigong, et al. 2008. Forecasting precipitation experiment with KNN based on crossing verification technology [J]. Journal of Applied Meteorological Science (in Chinese), 19(4): 471−478. doi: 10.3969/j.issn.1001-7313.2008.04.011
[35]	张辉, 2013. 基于BP神经网络的遥感影像分类研究 [D]. 山东师范大学硕士学位论文. Zhang Hui. 2013. Research on back-propagation neural network-based remote sensing image classification [D]. M. S. thesis (in Chinese), Shandong Normal University.
[36]	张佳华, 姚宜斌, 曹娜. 2017. 基于决策树对有无降水进行预测 [J]. 测绘地理信息, 42(5): 107−109. doi: 10.14188/j.2095-6045.2015261 Zhang Jiahua, Yao Yibin, Cao Na. 2017. Prediction of whether precipitation based on decision tree [J]. Journal of Geomatics (in Chinese), 42(5): 107−109. doi: 10.14188/j.2095-6045.2015261
[37]	周丽莉, 胡军, 章昊. 2017. 具有学习过程的贝叶斯决策模型与统计模拟 [J]. 统计与决策, (23): 22−26. doi: 10.13546/j.cnki.tjyjc.2017.23.005 Zhou Lili, Hu Jun, Zhang Hao. 2017. Bayesian decision model with learning process and statistical simulation [J]. Statistics and Decision (in Chinese), (23): 22−26. doi: 10.13546/j.cnki.tjyjc.2017.23.005
[38]	朱连华, 江志红, 刘征宇. 2015. 春季陆面植被对长江流域夏季降水可预报性的影响分析 [J]. 气象学报, 73(5): 895−909. doi: 10.11676/qxxb2015.063 Zhu Lianhua, Jiang Zhihong, Liu Zhengyu. 2015. The impact analysis of spring vegetation on the summer precipitation predictability over the Yangtze River basin [J]. Acta Meteorologica Sinica (in Chinese), 73(5): 895−909. doi: 10.11676/qxxb2015.063