An Integrated Approach for Optimizing Streamflow Prediction in Mid-High Latitude Catchments by Employing Terrestrial Ecosystem Modelling and Interpretable Machine Learning DOI
Hao Zhou, Jing Tang, Stefan Olin

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

A deep learning-based probabilistic approach to flash flood warnings in mountainous catchments DOI
Yuting Zhao, Xuemei Wu,

Wenjiang Zhang

и другие.

Journal of Hydrology, Год журнала: 2025, Номер 652, С. 132677 - 132677

Опубликована: Янв. 10, 2025

Язык: Английский

Процитировано

2
Revolutionizing water quality management the impact of machine learning and artificial intelligence DOI
Richa Sharma, Aparna Satapathy,

Vaishnavi Srivastava

и другие.

Elsevier eBooks, Год журнала: 2025, Номер unknown, С. 27 - 42

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Long-term prediction of Poyang Lake water level by combining multi-scale isometric convolution network with quantile regression DOI
Ying Jian, Yong Zheng,

Gang Li

и другие.

Journal of Hydrology Regional Studies, Год журнала: 2025, Номер 59, С. 102365 - 102365

Опубликована: Апрель 17, 2025

Язык: Английский

Процитировано

0
Multiple Types of Missing Precipitation Data Filling Based on Ensemble Artificial Intelligence Models DOI Open Access
Qiu He, Hao Chen,

Bingjiao Xu

и другие.

Water, Год журнала: 2024, Номер 16(22), С. 3192 - 3192

Опубликована: Ноя. 7, 2024

The completeness of precipitation observation data is a crucial foundation for hydrological simulation, water resource analysis, and environmental assessment. Traditional imputation methods suffer from poor adaptability, lack precision, limited model diversity. Rapid accurate using available key challenge in monitoring. This study selected the Jiaojiang River basin southeastern Zhejiang Province China 1991 to 2020. were categorized based on various missing rates scenarios, namely MCR (Missing Completely Random), MR MNR Not Random). Imputation was conducted three types Artificial Intelligence (AI) (Backpropagation Neural Network (BPNN), Random Forest (RF), Support Vector Regression (SVR)), along with novel Multiple Linear (MLR) method built upon these algorithms. results indicate that constructed MLR achieves an average Pearson’s correlation coefficient (PCC) 0.9455, Nash–Sutcliffe Efficiency (NSE) 0.8329, Percent Bias (Pbias) 10.5043% across different rates. simulation higher NSE lower Pbias than other single AI models, thus effectively improving estimation performance. proposed this can be applied river basins improve quality support management.

Язык: Английский

Процитировано

0
Security constrained optimal power system dispatch considering stochastic power facility failures under extreme precipitation DOI
Licheng Wang,

Chendong Su,

Bomiao Liang

и другие.

Electric Power Systems Research, Год журнала: 2024, Номер 239, С. 111214 - 111214

Опубликована: Ноя. 8, 2024

Язык: Английский

Процитировано

0
An Integrated Approach for Optimizing Streamflow Prediction in Mid-High Latitude Catchments by Employing Terrestrial Ecosystem Modelling and Interpretable Machine Learning DOI
Hao Zhou, Jing Tang, Stefan Olin

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0