Collect ｜ Homepage Advertisement ｜ Contact us ｜ Message
Adv. search

Arid Land Geography >

2018 , Vol. 41 >Issue 5: 945 - 953

DOI: https://doi.org/10.12118/j.issn.1000-6060.2018.05.06

Applicability of ARIMA and ANN models for drought forecasting

Expand
  • 1 School of Mathematical Sciences, Capital Normal University, Beijing 100048, China;
    2 College of Resources Environment & Tourism, Capital Normal University, Beijing 100048, China

Received date: 2018-05-02

  Revised date: 2018-07-11

Fold

Abstract

Drought is one of the major natural disasters,whose occurrence is linked to a sustained lack of precipitation.The drought forecast provides vital evidence and support for preventing losses of drought disasters,and therefore it is of great significance.In this study,a series of the standard precipitation evapotranspiration index (SPEI) at different time scales were calculated based on the daily precipitation and temperature data from 7 meteorological stations in Sanjiang Plain,northeast China from 1960 to 2016 and were used to forecast the drought using ARIMA and ANN models.In the stage of training and testing,the fitting degrees of the models were evaluated and validated and the optimal ARIMA and ANN models were chosen with the help of 6 fitting evaluation methods:the correlation coefficient (R),Nash-Sutcliffe efficiency coefficient (NSE),Kendall,rank correlation coefficient,the mean square error (MSE) and Kolmogorov-Smirnov (K-S) test.Then 12 values for the 12 months in 2016 were predicted by the optimal models and were compared with the corresponding observations.The results are shown as follows:(1) The prediction ability of ARIMA and ANN models based on SPEI were both increased with the increase of time scale in Sanjiang Plain.(2) The two models had poor prediction accuracy for SPEI 3 and SPEI 6.For the SPEI value of 9,12 and 24 months,all models worked well with accuracy more than 70%.(3) For the SPEI value of 9,12 and 24 months,the prediction accuracy of ANN model is better than that of ARIMA model.In particular,the prediction accuracy for one month forecast of SPEI 12 and 24 at all stations were more than 80%.All these showed that the prediction model of ANN has strong maneuverability and can effectively predict the drought at a large time scale in Sanjiang Plain.The drought prediction at small time scale (3 and 6 months) needs to be improved in future studies.

Key words： drought; ARIMA model; ANN model; SPEIs; Sanjiang Plain

Cite this article

YANG Hui-rong, ZHANG Yu-hu, CUI Heng-jian, GAO Feng, CHEN Qiu-hua . Applicability of ARIMA and ANN models for drought forecasting[J]. Arid Land Geography, 2018 , 41(5) : 945 -953 . DOI: 10.12118/j.issn.1000-6060.2018.05.06

References

[1] 王利娜,苏静,郑晓东,等.我国农业干旱风险研究进展简述[J].水科学与工程技术,2011,(2):3-7.[WANG Lina,SU Jing,ZHENG Xiaodong,et al.Research progress of agricultural drought risk in China[J].Water Sciences and Engineering Technology,2011,(2):3-7.]
[2] 张玉虎,刘凯利,陈秋华,等.区域气象干旱特征多变量Copula分析——以阿克苏河流域为例[J].地理科学,2014,34(12):1480-1487.[ZHANG Yuhu,LIU Kaili,CHEN Qiuhua,et al.Bivariate probability distribution of meteorological drought characteristics in the Aksu Basin using Copula[J].Scientia Geographica Sinica,2014,34(12):1480-1487.]
[3] 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):332-339.[XIE Pei,GU Yanling,ZHANG Yuhu,et al.Precipitation and drought characteristics in Xinjiang during 1961-2015[J].Arid Land Geography,2017,40(2):332-339.]
[4] 张玉虎,向柳,孙庆,等.贝叶斯框架的Copula季节水文干旱预报模型构建及应用[J].地理科学,2016,36(9):1437-1444.[ZHANG Yuhu,XIANG Liu,SUN Qing,et al.Construction and application of hydrological drought prediction model for Copula in Bayesian framework[J].Scientia Geographica Sinica, 2016,36(9):1437-1444.]
[5] 吴晶,罗毅,李佳,等.CMIP5模式对中国西北干旱区模拟能力评价[J].干旱区地理,2014,37(3):499-508.[WU Jing,LUO Yi,LI Jia,et al.The evaluation of CMIP5 model for simulation ability in China's northwest arid region[J].Arid Land Geography,2014,37(3):499-508.]
[6] 韩萍,王鹏新,王彦集,等.多尺度标准化降水指数的ARIMA模型干旱预测研究[J].干旱地区农业研究,2008,26(2):212-218.[HAN Ping,WANG Pengxin,WANG Yanji,et al.Drought forecasting based on the standardized precipitation index at different temporal scales using ARIMA models[J].Agricultural Research in the Arid Areas,2008,26(2):212-218.]
[7] ZHANG Y,LI W,CHEN Q,et al.Multi-models for SPI drought forecasting in the north of Haihe River Basin, China[J].Stochastic Environmental Research & Risk Assessment,2017,31(10):2471-2481.
[8] 刘海萍.中国主要股指的分形分析与BP神经网络预测[D].大连:大连理工大学,2013.[LIU Haiping.The fractal analysis of major indexes and BP neural network prediction in China[D].Dalian:Dalian University of Technology,2013.]
[9] XIN R B,JIANG Z F,LI N,et al.An air quality predictive model of Licang of Qingdao City based on BP neural network[J].Advanced Materials Research,2013,756-759:3366-3371.
[10] 张皓.基于MATLAB动态神经网络进行时间序列预测房地产价格的研究[J].经济师,2015,(9):284-286.[ZHANG Hao. Based on MATLAB dynamic neural network time series forecast real estate price research[J].China Economist,2015,(9):284-286.]
[11] DJERBOUAI S,SOUAG-GAMANE D.Drought forecasting using neural networks,wavelet neural networks and stochastic models:A case of the Algerois Basin in north Algeria[J].Water Resources Management,2016,30(7):2445-2464.
[12] BARUA S,PERERA B J C,NG A W M,et al.Drought forecasting using an aggregated drought index and artificial neural network[J].Journal of Water & Climate Change,2010,1(3):193.
[13] BELAYNEH A,ADAMOWSKI J,KHALIL B,et al.Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models[J].Journal of Hydrology,2014,508(2):418-429.
[14] 罗明美.基于AMSR-E和ANN人工神经网络的淮河流域土壤水分反演研究[D].成都:四川农业大学,2013.[LUO Mingmei.Study on soil water inversion in huai river basin based on AMSR-E and ANN artificial neural network[D].Chengdu:Sichuan Agricultural University,2013.]
[15] 沈国强,郑海峰,雷振锋.SPEI指数在中国东北地区干旱研究中的适用性分析[J].生态学报,2017,37(11):3787-3795.[SHEN Guoqiang,ZHENG Haifeng,LEI Zhenfeng.Applicability analysis of SPEI for drought research in northeast China[J].Acta Ecologica Sinica,2017,37(11):3787-3795.]
[16] 王媛媛,张勃.基于标准化降水指数的近40年陇东地区旱涝时空特征[J].自然资源学报,2012,27(12):2135-2144.[WANG Yuanyuan,ZHANG Bo.The spatial and temporal characteristics of drought and waterlogging in Longdong area based on standardized precipitation index in recent 40 years[J].Journal of Natural Resources,2012,27(12):2135-2144.]
[17] 张岳军,郝智文,王雁,等.基于SPEI和SPI指数的太原多尺度干旱特征与气候指数的关系[J].生态环境学报,2014,23(9):1418-1424.[ZHANG Yuejun,HAO Zhiwen,WANG Yan,et al.Multiscale characteristics of drought based on SPEI and SPI in association with climate index in Taiyuan[J].Ecology and Environmental Sciences,2014,23(9):1418-1424.]
[18] 李伟光,侯美亭,陈汇林,等.基于标准化降水蒸散指数的华南干旱趋势研究[J].自然灾害学报,2012,21(4):84-90.[LI Weiguang,HOU Meiting,CHEN Huilin,et al.Study on drought trend in south China based on standardized precipitation evapotranspiration index[J].Journal of Natural Disasters,2012,21(4):84-90.]
[19] 王林,陈文.近百年西南地区干旱的多时间尺度演变特征[J].气象科技进展,2012,2(4):21-26.[WANG Lin,CHEN Wen.The multi-temporal scale evolution characteristics of drought in southwest China in the past 100 years[J].Advances in Meteorological Science and Technology,2012,2(4):21-26.]
[20] ADAMOWSIKI J,CHAN H F,PRASHER S O,et al.Comparison of multiple linear and nonlinear regression,autoregressive integrated moving average,artificial neural network and wavelet artificial neural network methods for urban water demand forecasting in Montreal,Canada[J].Water Resources Research,2012,48(1):273-279.
[21] 岳新征,李磊民,孙飞.基于NAR动态神经网络的石英挠性加速度表参数建模与预测[J].西南科技大学学报,2016,31(1):88-92.[YUE Xinzheng,LI Leimin,SUN Fei.Parametric modeling and prediction of quartz flexible accelerometer based on NAR dynamic neural network[J].Journal of Wuhan university,2016,31(1):88-92.]
[22] 邓兴升,王新洲.动态神经网络在变形预报中的应用[J]. 武汉大学学报,2008,33(1):93-96.[DENG Xingsheng,WANG Xinzhou.Application of dynamic neural network in deformation prediction[J].Journal of Wuhan University,2008,33(1):93-96.]
[23] VICEBTESERRANO S M,BEGUERIA S,LOPEZMORENO J I.A multi-scalar drought index sensitive to global warming:The standardized precipitation evapotranspiration index[J].Journal of Climate,2010,23(7):1696-1718.
[24] 刘珂,姜大膀.基于两种潜在蒸散发算法的SPEI对中国干湿变化的分析[J].大气科学,2015,39(1):23-36.[LIU Ke,JIANG Dabang.Analysis of dryness/wetness over China using standardized precipitation evapotranspiration index based on two evapotranspiration algorithms[J].Chinese Journal of Atmospheric Sciences,2015,39(1):23-36.]
[25] GB/T20481-2006,气象干旱等级[S].北京:中国标准出版社,2006.[GB/T 20481-2006,Classification of meteorological drought[S].Beijing:Standards Press of China,2006.]
[26] PEARSON E S,HARTLEY H O.Biometrika tables for statisticians[M].London:Cambridge University Press,1956.
[27] 李宝林,周成虎.东北平原西部沙地的气候变异与土地荒漠化[J].自然资源学报,2001,16(3):234-239.[LI Baolin,ZHOU Chenghu.Climatc variation and desertification in west sandy land of Northeast China Plain[J].Journal of Natural Resources,2001,16(3):234-239.]
[28] 王春乙,蔡菁菁,张继权.基于自然灾害风险理论的东北地区玉米干旱、冷害风险评价[J].农业工程学报,2015,31(6):238-245.[WANG Chunyi,CAI Jingjing,ZHANG Jiquan. Risk assessment of drought and chilling injury of maize in northeast China[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(6):238-245.]
[29] 胡欣欣,张玉虎,向柳.新疆阿克苏地区气象干旱特征研究[J].安徽农业科学,2015,43(35):96-100+104.[HU Xinxin,ZHANG Yuhu,XIANG Liu.Study on the characteristics of meteorological drought in Aksu region of Xinjiang[J].Journal of Anhui Agricultural Sciences,2015,43(35):96-100+104.]
[30] MISHRA A K,DESAI V R.Drought forecasting using stochastic models[J].Stochastic Environmental Research and Risk Assessment,2005,19(5):326-339.
Options
Outlines

/

〈 〉