Medium- and Long-Term Hydrological Process Study in the Karst Watershed of the Lijiang River Basin DOI Open Access
W. Li,

Song Luan,

Yuqing Zhao

et al.

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3424 - 3424

Published: Nov. 28, 2024

The hydrological processes in karst watersheds are influenced by various factors, including climate characteristics, underlying surface properties, and human activities. Existing watershed models primarily rely on theoretical concepts or empirical function relationships for simulation, resulting insufficient accuracy process analysis study areas with limited data. structure of artificial neural networks is similar to the watersheds. Based characteristics Lijiang River, a BP network model configured structural parameters set 13-9-1. Using data from River 1995 2020 as foundational dataset, trained tested prediction accuracy. results show that coefficient determination monthly runoff basin, based network, 0.942. This suggests it feasible use historical predict future flow changes assuming due exclusively precipitation evapotranspiration, but no significant occur land uses. findings hold importance water resource management typical

Language: Английский

Medium- and Long-Term Hydrological Process Study in the Karst Watershed of the Lijiang River Basin DOI Open Access
W. Li,

Song Luan,

Yuqing Zhao

et al.

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3424 - 3424

Published: Nov. 28, 2024

The hydrological processes in karst watersheds are influenced by various factors, including climate characteristics, underlying surface properties, and human activities. Existing watershed models primarily rely on theoretical concepts or empirical function relationships for simulation, resulting insufficient accuracy process analysis study areas with limited data. structure of artificial neural networks is similar to the watersheds. Based characteristics Lijiang River, a BP network model configured structural parameters set 13-9-1. Using data from River 1995 2020 as foundational dataset, trained tested prediction accuracy. results show that coefficient determination monthly runoff basin, based network, 0.942. This suggests it feasible use historical predict future flow changes assuming due exclusively precipitation evapotranspiration, but no significant occur land uses. findings hold importance water resource management typical

Language: Английский

Citations

0