Application of the improved dung beetle optimizer,muti-head attention and hybrid deep learning algorithms to groundwater depth prediction in the Ningxia area,China

作     者：Jiarui Cai Bo Sun Huijun Wang Yi Zheng Siyu Zhou Huixin Li Yanyan Huang Peishu Zong Jiarui Cai;Bo Sun;Huijun Wang;Yi Zheng;Siyu Zhou;Huixin Li;Yanyan Huang;Peishu Zong

作者机构：Collaborative Innovation Center on forecast and Evaluation of Meteorological Disasters/Key Laboratory of Meteorological DisasterMinistry of Education/Joint International Research Laboratory of Climate and Environment ChangeNanjing University of Information Science and TechnologyNanjingChina Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)ZhuhaiChina China Meteorological AdministrationKey Laboratory of Transportation MeteorologyNanjingChina Jiangsu Meteorological ObservatoryNanjingChina 

出 版 物：《Atmospheric and Oceanic Science Letters》 (大气和海洋科学快报（英文版）)

年 卷 期：2025年第18卷第1期

页      面：18-23页

核心收录：

学科分类：081803[工学-地质工程] 08[工学] 0818[工学-地质资源与地质工程] 

基　　金：supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048] 

主　　题：Groundwater depth Multi-head attention Improved dung beetle optimizer CNN-LSTM CNN-GRU Ningxia 

摘      要：Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical *** learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many *** this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,*** two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction *** addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.