Combining BPANN and wavelet analysis to simulate hydro-climatic processes a case study of the Kaidu River, North-west China  

作　　者：Jianhua XU Yaning CHEN Weihong LI Paul Y. PENG Yang YANG Chunan SONG Chunmeng-WEI Yulian HONG 

机构地区：[1]The Key Laboratory of GIScience of the Education Ministry of China, The Research Center for East-West Cooperation in China, East China Normal University, Shanghai 200241, China [2]The Key Laboratory of Oasis Ecology and Desert Environment, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, China [3]Department of Community Health and Epidemiology, Queen's University, Kingston, K7L 3N6, Canada

出　　处：《Frontiers of Earth Science》2013年第2期227-237,共11页地球科学前沿（英文版）

摘　　要：Using the hydrological and meteorological data in the Kaidu River Basin during 1957-2008, we simulated the hydro-climatic process by back-propagation artificial neural network （BPANN） based on wavelet analysis （WA）, and then compared the simulated results with those from a multiple linear regression （MLR）. The results show that the variation of runoff responded to regional climate change. The annual runoff （AR） was mainly affected by annual average temperature （AAT） and annual precipitation （AP）, which revealed different varia- tion patterns at five time scales. At the time scale of 32-years, AR presented a monotonically increasing trend with the similar trend of AAT and AP. But at the 2-year, 4- year, 8-year, and 16-year time-scale, AR presented non-linear variation with fluctuations of AAT and AP. Both MLR and BPANN successfully simulated the hydro- climatic process based on WA at each time scale, but the simulated effect from BPANN is better than that from MLR.Using the hydrological and meteorological data in the Kaidu River Basin during 1957-2008, we simulated the hydro-climatic process by back-propagation artificial neural network （BPANN） based on wavelet analysis （WA）, and then compared the simulated results with those from a multiple linear regression （MLR）. The results show that the variation of runoff responded to regional climate change. The annual runoff （AR） was mainly affected by annual average temperature （AAT） and annual precipitation （AP）, which revealed different varia- tion patterns at five time scales. At the time scale of 32-years, AR presented a monotonically increasing trend with the similar trend of AAT and AP. But at the 2-year, 4- year, 8-year, and 16-year time-scale, AR presented non-linear variation with fluctuations of AAT and AP. Both MLR and BPANN successfully simulated the hydro- climatic process based on WA at each time scale, but the simulated effect from BPANN is better than that from MLR.

关 键 词：hydro-climatic process Kaidu River simulation wavelet analysis （WA） back-propagation artificial neural network （BPANN） multiple linear regression （MLR） 

分 类 号：P445.4[天文地球—大气科学及气象学] TP183[自动化与计算机技术—控制理论与控制工程]