干旱区生态环境知识资源中心(Arid): Daily Groundwater Level Prediction and Uncertainty Using LSTM Coupled with PMI and Bootstrap Incorporating Teleconnection Patterns Information

Arid

DOI	10.3390/su141811598
	Daily Groundwater Level Prediction and Uncertainty Using LSTM Coupled with PMI and Bootstrap Incorporating Teleconnection Patterns Information
	Chu, Haibo; Bian, Jianmin; Lang, Qi; Sun, Xiaoqing; Wang, Zhuoqi
通讯作者	Bian, JM ; Sun, XQ
来源期刊	SUSTAINABILITY
EISSN	2071-1050
出版年	2022
卷号	14 期号:18
英文摘要	Daily groundwater level is an indicator of groundwater resources. Accurate and reliable groundwater level (GWL) prediction is crucial for groundwater resources management and land subsidence risk assessment. In this study, a representative deep learning model, long short-term memory (LSTM), is adopted to predict groundwater level with the selected predictors by partial mutual information (PMI), and bootstrap is employed to generate different samples combination for training many LSTM models, and the predicted values by many LSTM models are used for the uncertainty assessment of groundwater level prediction. Two wells of different climate zones in the USA were used as a case study. Different significant predictors of GWL for two wells were identified by PMI from candidate predictors incorporating teleconnection patterns information. The results show that GWL is significantly affected by antecedent GWL, AO, Nino 3.4, Nino 1 + 2, and precipitation in humid areas, and by antecedent GWL, AO, Nino 3.4, Nino 3, Nino 1 + 2, and PNA in arid areas. Predictor selection can assist in improving the prediction performance of the LSTM model. The relationship between GWL and significant predictors were modeled by the LSTM model, and it achieved higher accuracy in humid areas, while the performance in arid areas was poorer due to limited precipitation information. The performance of LSTM was improved by increasing correlation coefficient (R-2) values by 10% and 25% for 2 wells compared to generalized regression neural network (GRNN). Three uncertainty evaluation metrics indicate that LSTM reduced the uncertainty compared to GRNN model. LSTM coupling with PMI and bootstrap can be a promising approach for accurate and reliable groundwater level prediction for different climate zones.
英文关键词	long short-term memory bootstrap teleconnection patterns groundwater level prediction uncertainty
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E ; SSCI
WOS记录号	WOS:000856767300001
WOS关键词	ARTIFICIAL NEURAL-NETWORKS ; VARIABLE SELECTION ; MODEL
WOS类目	Green & Sustainable Science & Technology ; Environmental Sciences ; Environmental Studies
WOS研究方向	Science & Technology - Other Topics ; Environmental Sciences & Ecology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/394640
推荐引用方式 GB/T 7714	Chu, Haibo,Bian, Jianmin,Lang, Qi,et al. Daily Groundwater Level Prediction and Uncertainty Using LSTM Coupled with PMI and Bootstrap Incorporating Teleconnection Patterns Information[J],2022,14(18).
APA	Chu, Haibo,Bian, Jianmin,Lang, Qi,Sun, Xiaoqing,&Wang, Zhuoqi.(2022).Daily Groundwater Level Prediction and Uncertainty Using LSTM Coupled with PMI and Bootstrap Incorporating Teleconnection Patterns Information.SUSTAINABILITY,14(18).
MLA	Chu, Haibo,et al."Daily Groundwater Level Prediction and Uncertainty Using LSTM Coupled with PMI and Bootstrap Incorporating Teleconnection Patterns Information".SUSTAINABILITY 14.18(2022).