Efficiency enhancement of a process-based rainfall–runoff modelusing a new modified AdaBoost.pdfVIP

E u S a b c a A R R A A K A P P I r d d v f t t h 1Applied Soft Computing 23 (2014) 521–529 Contents lists available at ScienceDirect Applied Soft Computing j ourna l h o mepage: www.elsev ier .com/ locate /asoc fficiency enhancement of a process-based rainfall–runoff model sing a new modified AdaBoost.RT technique huang Liua, Jingwen Xua,?, Junfang Zhaob, Xingmei Xiea, Wanchang Zhangc College of Resources and Environment, Sichuan Agricultural University, Chengdu 611130, PR China Chinese Academy of Meteorological Sciences, Beijing 100081, PR China Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, PR China r t i c l e i n f o rticle history: eceived 3 July 2013 eceived in revised form 5 May 2014 ccepted 23 May 2014 vailable online 5 June 2014 eywords: daBoost.RT algorithm article swarm optimization rocess-based hydrologic model a b s t r a c t High-efficiency rainfall–runoff forecast is extremely important for flood disaster warning. Single process- based rainfall–runoff model can hardly capture all the runoff characteristics, especially for flood periods and dry periods. In order to address the issue, an effective multi-model ensemble approach is urgently required. The Adaptive Boosting (AdaBoost) algorithm is one of the most robust ensemble learning meth- ods. However, it has never been utilized for the efficiency improvement of process-based rainfall–runoff models. Therefore AdaBoost.RT (Adaptive Boosting for Regression problems and “T” for a threshold demarcating the correct from the incorrect) algorithm, is innovatively proposed to make an aggregation (AdaBoost- XXT) of a process-based rainfall–runoff model called XXT (a hybrid of TOPMODEL and Xinanjing model). To adapt to hydrologic situation, some modifications were made in AdaBoost.RT.