首页|期刊导航|大气和海洋科学快报（英文版）|A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis
大气和海洋科学快报（英文版）2021，Vol.14Issue(5)：13-18,6.
A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis
A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis
摘要
Abstract
暴雨是我国最重要的自然灾害之一.大量的研究表明,暴雨的频率和强度在全球变暖的背景下正在逐年增强.但是如何成功的预测短期暴雨,特别是发生在复杂地形下的暴雨,仍然是一个巨大的挑战.本项研究采用BP神经网络和天气学诊断相结合的方法,探索了一种四川盆地西部复杂地形下的暴雨预报模型.该模型有效改善了喇叭口地形下,受低层偏东风影响的暴雨预报准确性.机器学习与天气学理论的结合,提升了模型的物理基础和预测成功率,同时该方法也为发展具有本地特征的暴雨预报客观工具,提供了一定的参考价值.关键词
暴雨/短期预测方法/BP神经网络/复合预测模型Key words
Rainstorm/Short-term prediction method/Back-propagation neural network/Hybrid forecast model引用本文复制引用
Guolu Gao,Yang Li,Jiaqi Li,Xueyun Zhou,Ziqin Zhou..A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis[J].大气和海洋科学快报（英文版）,2021,14(5):13-18,6.基金项目
This work was jointly supported by the National Key Research and Development Program on Monitoring,Early Warning and Pre-vention of Major Natural Disasters[grant number 2018YFC1506006]and the National Natural Science Foundation of China[grant numbers 41805054 and U20A2097]. （）
