STUDY ON MIXED MODEL OF NEURAL NETWORK FOR FARMLAND FLOOD/DROUGHT PREDICTION

作     者：金龙 罗莹 郭光 林振山 

作者机构：Jiangsu Meteorological InstituteNanjing 210008 Jiangsu Institute of Climate ApplicationNanjing 210009 Nanjing Institute of MeteorologyNanjing 210044 Department of Atmospheric SciencesNanjing UniversityNanjing 210093 

出 版 物：《Acta meteorologica Sinica》 (Acta Meteorologica Sinica)

年 卷 期：1997年第11卷第3期

页      面：364-373页

学科分类：07[理学] 070601[理学-气象学] 0706[理学-大气科学] 

基　　金：the Excellent Talent Foundation of the State Education Commission 

主　　题：flood/drought prediction mixed model nonlinear mapping soil humidity neural network 

摘      要：The paper concerns a flood/drought prediction model involving the continuation of time series of a predictand and the physical factors influencing the change of *** is made to construct the model by the neural network scheme for the nonlinear mapping relation based on multi-input and single *** model is found of steadily higher predictive accuracy by testing the output from one and multiple stepwise predictions against observations and comparing the results to those from a traditional statistical model.