文献类型：期刊文献

英文题名：Comparing Machine-Learning Models for Drought Forecasting in Vietnam's Cai River Basin

作者：Liu, Zhen Nan Li, Qiong Fang Luong Bang Nguyen Xu, Gui Hong

第一作者：刘振男;Liu, Zhen Nan

通信作者：Liu, ZN[1];Liu, ZN[2]

机构：[1]Hohai Univ, Coll Hydrol & Water Resources, Nanjing, Jiangsu, Peoples R China;[2]Guizhou Inst Technol, Sch Civil Engn, Guiyang, Guizhou, Peoples R China;[3]Thuyloi Univ, Hanoi, Vietnam

第一机构：Hohai Univ, Coll Hydrol & Water Resources, Nanjing, Jiangsu, Peoples R China

通信机构：corresponding author), Hohai Univ, Coll Hydrol & Water Resources, Nanjing, Jiangsu, Peoples R China;corresponding author), Guizhou Inst Technol, Sch Civil Engn, Guiyang, Guizhou, Peoples R China.|贵州理工学院土木工程学院;贵州理工学院;

年份：2018

卷号：27

期号：6

起止页码：2633-2646

外文期刊名：POLISH JOURNAL OF ENVIRONMENTAL STUDIES

收录：;Scopus(收录号：2-s2.0-85049850654);WOS:【SCI-EXPANDED(收录号:WOS:000439622000023)】；

基金：This work was supported by the National Natural Science Foundation of China (No. 51508121) and the Guizhou Province Science and Technology Fund (Nos. LH [2016]7096, J [2015]2063, and LH [2014]7374).

语种：英文

外文关键词：drought indices; drought forecast; extreme learning machine; online sequential extreme learning machine; self-adaptive evolutionary extreme learning machine; sea surface temperature anomalies

摘要：Drought occurs throughout the world, affecting people more than any other major natural hazards -especially in the agriculture industry. An effective and timely monitoring system is required to mitigate the impacts of drought. Meanwhile, extreme learning machine (ELM), online sequential extreme learning machine (OS-ELM), and self-adaptive evolutionary extreme learning machine (SADE-ELM) are rarely applied as the alternative drought-forecasting tools in the meantime. The present study aims to evaluate the ability of these models to predict drought and the quantitative value of drought indices, the standardized precipitation index (SPI), and the standardized precipitation evapotranspiration index (SPEI). For this purpose, the sea surface temperature anomalies (SSTA) events at NinoW and Nino4 zones were selected for input variables to forecast drought. The SPI/SPEI values may contain a one/three/six-month dry and a one/three/six-month wet period in short-term periods, and this causes instability. For this reason, 4 models for SPI/SPEI (12 months) were trained and tested by these methods, respectively. According to two statistical indices (RMSE and CORR) and stability of these methods, the SADE-ELM models perform the best, and the performance of the OS-ELM models are better than the ELM models.