Runoff simulation and prediction of typical basins in the Jiziwan Region of the Yellow River Basin based on Long Short-Term Memory (LSTM) neural network

This study employs the Long Short-Term Memory (LSTM) rainfall-runoff model to simulate and predict runoff in typical basins of the Jiziwan Region of the Yellow River, aiming to overcome the shortcomings of traditional hydrological models in complex nonlinear environments. The Jiziwan Region of the Yellow River is affected by human activities such as urbanization, agricultural development, and water resource management, leading to increasingly complex hydrological processes. Traditional hydrological models struggle to effectively capture the relationship between rainfall and runoff. The LSTM rainfall-runoff model, using deep learning techniques, automatically extracts features from data, identifies complex patterns and long-term dependency in time series, and provides more accurate and reliable runoff predictions. The results demonstrate that the LSTM rainfall-runoff model adapts well to the complex hydrological characteristics of the Jiziwan Region, showing superior performance over traditional hydrological models, especially in addressing the changing trends under the influence of climate change and human activities. By analyzing the interannual and within-year variations of runoff under different climate change scenarios, the model can predict the evolution trends of runoff under future climate conditions, providing a scientific basis for water resource management and decision-making. The results indicate that under different climate change scenarios, the runoff in several typical basins of the Jiziwan Region exhibits different variation trends. Under SSP1-2.6 and SSP2-4.5, some basins, such as the Wuding River Basin, Tuwei River Basin, and Gushanchuan Basin, show a decreasing trend in annual runoff. For example, in the Wuding River Basin, the average runoff from 2025 to 2040 is 12.48 m³/s (SSP1-2.6), with an annual decrease of 0.10 m³/s; in the Tuwei River Basin, the runoff from 2025 to 2040 is 12.96 m³/s (SSP1-2.6), with an annual decrease of 0.10 m³/s. In contrast, under SSP3-7.0 and SSP5-8.5, with climate warming and changes in precipitation patterns, runoff in some basins shows an increasing trend, particularly during the snowmelt period and with increased summer precipitation, leading to a significant rise in runoff.