西北干旱地区气象干旱风险预测模型研究

doi:10.16843/j.sswc.2023096

摘要
图/表
参考文献
相关文章 (2)

全文: HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要中国西北干旱地区由于严重的降水不足与水分流失等问题，导致干旱事件频发。为探究适用于西北干旱地区气象干旱预测的神经网络模型，以西北干旱地区12个气象站点降水量数据为基础，采用标准化降水指数（SPI）作为指标，根据输入变量的不同分别基于反向传播神经网络（BPNN）、极限学习机（ELM）、长短期记忆网络（LSTM）建立9组模型进行气象干旱预测，并通过GLDAS数据集验证模型稳定性。LSTM的预测精度高于BPNN与ELM，且在输入变量较少的情况下仍能保持较高的预测精度。其中精度最高模型M7的决定系数 R²=0.965、均方根误差RMSE=0.175；LSTM在不同典型年的预测中表现良好，R²均 > 0.8，RMSE均 < 0.132，且枯水年与特枯水年的预测精度略高于丰水年与平水年的预测精度。LSTM在中国西北干旱地区气象干旱预测方面有良好的适用性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王文玉
	李涛
	高泽海
	卢颖杰

关键词 ：西北干旱地区, 气象干旱预测, 神经网络模型, 反向传播神经网络, 极限学习机, 长短期记忆网络

Abstract：Background Drought is a temporary and recurring meteorological event that has the most serious impact on human society. The arid region of Northwest China is located in the hinterland of the Eurasian continent. Due to severe insufficient precipitation and high evaporation, the arid region of Northwest China often suffers from the impact of drought, seriously affecting local agricultural production and life, and causing serious social and economic impacts. Establishing a drought prediction model applicable to the arid region of Northwest China will effectively reduce the impact of varying degrees of drought on these areas. Methods In order to explore the neural network model suitable for meteorological drought prediction in the arid region of Northwest China, based on the precipitation data of twelve meteorological stations in the arid region of Northwest China from 1987 to 2016, the standardized precipitation index (SPI) was used as an indicator. According to the different input variables, nine groups of models were established based on the back-propagation neural network (BPNN), the extreme learning machine (ELM), and the long short-term memory network (LSTM) to predict the meteorological drought. And the stability of the model through the GLDAS dataset was verified.Results 1) The prediction accuracy of ELM is slightly improved compared to BPNN, and the training time is shorter. However, ELM and BPNN have low prediction accuracy in some regions, low reliability of the model, and poor applicability. And the two models are difficult to maintain good prediction accuracy in the case of a single input variable.2) The analysis of the results of the meteorological drought prediction model show that the prediction accuracy of LSTM is higher than that of BPNN and ELM. The coefficient of determination (R²) of the highest accuracy model M7 is 0.965, and the root mean square error(RMSE) is 0.175. The R² in typical years are all greater than 0.8, and the RMSE is less than 0.132. 3)The analysis of the prediction results of typical years shows that LSTM performs well in the prediction of different typical years, and the prediction accuracy of dry year and extremely dry year is slightly higher than that of wet year and normal year. Meanwhile, validation of the GLDAS (global land data assimilation system) dataset showed that the best performing model M7 maintained an R² of 0.9 or above, indicating that LSTM can ensure stable and high-precision prediction of drought conditions in the arid region of Northwest China. Conclusions Compared with BPNN and ELM, LSTM has stronger applicability and can still maintain higher prediction accuracy with fewer input variables. It shows stable predictive ability when facing different datasets. The above results indicate that the prediction model using LSTM has good applicability in the meteorological drought prediction of the arid region of Northwest China.

Key words： arid region of Northwest China meteorological drought prediction neural network model back-propagation neural network extreme learning machine long short-term memory network

收稿日期: 2023-06-16

PACS:	S157
	S166

基金资助:陕西省自然科学基础研究计划“新型高效节水灌溉喷头”（2021JM-337）

通讯作者: 李涛(1984—)，男，博士，副教授。主要研究方向：节水灌溉理论与新技术。E-mail：litao@xaut.edu.cn E-mail: litao@xaut.edu.cn

作者简介: 王文玉（1999—），男，硕士研究生。主要研究方向：农业水土资源与生态环境。E-mail：1873357146@qq.com

引用本文:

王文玉, 李涛, 高泽海, 卢颖杰. 西北干旱地区气象干旱风险预测模型研究[J]. 中国水土保持科学, 2025, 23(1): 117-130.
WANG Wenyu, LI Tao, GAO Zehai, LU Yingjie. Research on meteorological drought risk prediction model in the arid region of Northwest China. SSWC, 2025, 23(1): 117-130.

链接本文:

http://journal12.magtechjournal.com/Jweb_stbc/CN/10.16843/j.sswc.2023096 或 http://journal12.magtechjournal.com/Jweb_stbc/CN/Y2025/V23/I1/117

[1]	MORID S，SMAKHTIN V，BAGHERZADEH K. Drought forecasting using artificial neural networks and time series of drought indices[J]. International Journal of Climatology，2007，27（15）：2103.
[2]	HAO Zengchao，SINGH V P，XIA Youlong. Seasonal drought prediction：Advances，challenges，and future prospects[J]. Reviews of Geophysics，2018，56（1）：108.
[3]	XU Dehe，ZHANG Qi，DING Yan，et al. Application of a hybrid ARIMA–SVR model based on the SPI for the forecast of drought: A case study in Henan province，China[J]. Journal of Applied Meteorology and Climatology，2020，59（7）：1239.
[4]	SUN Liu，MITCHELL S W，DAVIDSON A. Multiple drought indices for agricultural drought risk assessment on the Canadian prairies[J]. International Journal of Climatology，2012，32（11）：1628.
[5]	HAO Zengchao，HAO Fanghua，SINGH V P，et al. A theoretical drought classification method for the multivariate drought index based on distribution properties of standardized drought indices[J]. Advances in Water Resources，2016，92：240.
[6]	XU Dehe，ZHANG Qi，DING Yan，et al. Application of a hybrid ARIMA-LSTM model based on the SPEI for drought forecasting[J]. Environmental Science and Pollution Research，2022，29（3）：4128.
[7]	NANDGUDE N，SINGH T P，NANDGUDE S，et al. Drought prediction：A comprehensive review of different drought prediction models and adopted technologies[J]. Sustainability，2023，15（15）：11684.
[8]	MULUALEM G M，LIOU Y A. Application of artificial neural networks in forecasting a standardized precipitation evapotranspiration index for the Upper Blue Nile Basin[J]. Water，2020，12（3）：643.
[9]	SANTOS J F，PORTELA M M，PULIDO‐CALVO I. Spring drought prediction based on winter NAO and global SST in Portugal[J]. Hydrological Processes，2014，28（3）：1009.
[10]	WANG Guochun，ZHANG Qian，BAND S S，et al. Monthly and seasonal hydrological drought forecasting using multiple extreme learning machine models[J]. Engineering Applications of Computational Fluid Mechanics，2022，16（1）：1364.
[11]	TIAN Ye，XU Yueping，WANG Guoqing. Agricultural drought prediction using climate indices based on support vector regression in Xiangjiang River Basin[J]. Science of the Total Environment，2018，622-623：710.
[12]	COŞKUN Ö，CITAKOGLU H. Prediction of the standardized precipitation index based on the long short-term memory and empirical mode decomposition-extreme learning machine models：the case of Sakarya，Türkiye[J]. Physics and Chemistry of the Earth，Parts A/B/C，2023，131：103418.
[13]	POORNIMA S，PUSHPALATHA M. RETRACTED ARTICLE：Drought prediction based on SPI and SPEI with varying timescales using LSTM recurrent neural network[J]. Soft Computing，2019，23（18）：8399.
[14]	KADAM C M，BHOSLE U V，HOLAMBE R S. Deep learning-driven regional drought assessment：An optimized perspective[J]. Earth Science Informatics，2024，17（2）：1523.
[15]	PARISOUJ P，MOHEBZADEH H，LEE T. Employing machine learning algorithms for streamflow prediction：A case study of four river basins with different climatic zones in the United States[J]. Water Resources Management，2020，34（13）：4113.
[16]	LALIKA C，MUJAHID A U H，JAMES M，et al. Machine learning algorithms for the prediction of drought conditions in the Wami River sub-catchment，Tanzania[J]. Journal of Hydrology：Regional Studies，2024，53：101794.
[17]	HAM Y S，SONU K B，PAEK U S，et al. Comparison of LSTM network，neural network and support vector regression coupled with wavelet decomposition for drought forecasting in the western area of the DPRK[J]. Natural Hazards，2023，116（2）：2619.
[18]	KATIPOĞLU O M. Integration of extreme learning machines with CEEMDAN and VMD techniques in the prediction of the multiscalar standardized runoff index and standardized precipitation evapotranspiration index[J]. Natural Hazards，2024，120（1）：825.
[19]	赵松乔. 中国综合自然地理区划的一个新方案[J]. 地理学报，1983，38（1）：1.ZHAO Songqiao. A new scheme for comprehensive physical regionalization in China[J]. Acta Geographica Sinica，1983，38（1）：1.
[20]	姚俊强，杨青，陈亚宁，等. 西北干旱区气候变化及其对生态环境影响[J]. 生态学杂志，2013，32（5）：1283.YAO Junqiang，YANG Qing，CHEN Yaning，et al. Climate change in arid areas of Northwest China in past 50 years and its effects on the local ecological environment[J]. Chinese Journal of Ecology，2013，32（5）：1283.
[21]	MCKEE T B，DOESKEN N J，KLEIST J. The relationship of drought frequency and duration to time scales[C]//Proceedings of the 8th conference on applied climatology. Anaheim, American Meteorological Society, 1993：179.
[22]	PATEL N R，CHOPRA P，DADHWAL V K. Analyzing spatial patterns of meteorological drought using standardized precipitation index[J]. Meteorological Applications，2007，14（4）：329.
[23]	MONDOL A H，ARA I，DAS S C. Meteorological drought index mapping in Bangladesh using standardized precipitation index during 1981–2010[J]. Advances in Meteorology，2017，2017（1）：4642060.
[24]	CHEN Shaodan，ZHANG Liping，ZHANG Yanjun，et al. Evaluation of Tropical Rainfall Measuring Mission （TRMM） satellite precipitation products for drought monitoring over the middle and lower reaches of the Yangtze River Basin，China[J]. Journal of Geographical Sciences，2020，30（1）：53.
[25]	BOUAZIZ M，MEDHIOUB E，CSAPLOVISC E. A machine learning model for drought tracking and forecasting using remote precipitation data and a standardized precipitation index from arid regions[J]. Journal of Arid Environments，2021，189：104478.
[26]	RUMELHART D E，HINTON G E，WILLIAMS R J. Learning internal representations by error propagation[M]//RUMELHART D E，MCCLELLAND J L. Parallel distributed processing：Explorations in the microstructures of cognition. Cambridge：MIT Press，1986：599.
[27]	MISHRA A K，DESAI V R. Drought forecasting using feed-forward recursive neural network[J]. Ecological Modelling，2006，198（1/2）：127.
[28]	HUANG Guangbin，ZHU Qinyu，SIEW C K. Extreme learning machine：Theory and applications[J]. Neurocomputing，2006，70（1/3）：489.
[29]	DEO R C，ŞAHIN M. Application of the extreme learning machine algorithm for the prediction of monthly effective drought index in eastern Australia[J]. Atmospheric Research，2015，153：512.
[30]	HOCHREITER S，SCHMIDHUBER J. Long short-term memory[J]. Neural Computation，1997，9（8）：1735.
[31]	谢培，顾艳玲，张玉虎，等. 1961—2015年新疆降水及干旱特征分析[J]. 干旱区地理，2017，40（2）：332.XIE Pei，GU Yanling，ZHANG Yuhu，et al. Precipitation and drought characteristics in Xinjiang during 1961–2015[J]. Arid Land Geography，2017，40（2）：332.
[32]	王澄海，张晟宁，李课臣，等. 1961-2018年西北地区降水的变化特征[J]. 大气科学，2021，45（4）：713.WANG Chenghai，ZHANG Shengning，LI Kechen，et al. Change characteristics of precipitation in Northwest China from 1961 to 2018[J]. Chinese Journal of Atmospheric Sciences，2021，45（4）：713.
[33]	张强，姚玉璧，李耀辉，等. 中国干旱事件成因和变化规律的研究进展与展望[J]. 气象学报，2020，78（3）：500.ZHANG Qiang，YAO Yubi，LI Yaohui，et al. Progress and prospect on the study of causes and variation regularity of droughts in China[J]. Acta Meteorologica Sinica，2020，78（3）：500.
[34]	陆晓娟，李忆平，王劲松. 中国北方干旱多发带极端春夏连旱的主要影响因子特征[J]. 高原气象，2025，44（1）：67.LU Xiaojuan，LI Yiping，WANG Jinsong. Characteristics of the main factors affecting prolonged spring-summer extreme drought events in northern drought-prone belt[J]. Plateau Meteorology，2025，44（1）：67.
[35]	张建海，张棋，许德合，等. ARIMA-LSTM组合模型在基于SPI干旱预测中的应用：以青海省为例[J]. 干旱区地理，2020，43（4）：1004.ZHANG Jianhai，ZHANG Qi，XU Dehe，et al. Application of a combined ARIMA-LSTM model based on SPI for the forecast of drought：A case study in Qinghai province[J]. Arid Land Geography，2020，43（4）：1004.
[36]	丁严，许德合，曹连海，等. 基于CEEMD的LSTM和ARIMA模型干旱预测适用性研究：以新疆为例[J]. 干旱区研究，2022，39（3）：734.DING Yan，XU Dehe，CAO Lianhai，et al. Applicability of the LSTM and ARIMA model in drought prediction based on CEEMD：A case study of Xinjiang[J]. Arid Zone Research，2022，39（3）：734.
[37]	APURV T，SIVAPALAN M，CAI Ximing. Understanding the role of climate characteristics in drought propagation[J]. Water Resources Research，2017，53（11）：9304.