2026-10-12T10:48:36Z https://www.scidb.cn/oai

10.57760/sciencedb.28196 2025-07-25T09:18:46Z

2025-07-25 WRF-ML Coupling Toolkit: Machine Learning-Based Optimization Code (XGBoost/RF/LSTM) for Extreme Event Simulation in Wanzhou Section of Three Gorges Reservoir Area doi:10.57760/sciencedb.28196 en This dataset provides Jupyter Notebook (.ipynb) scripts for post-processing optimization of WRF model outputs. It integrates XGBoost, Random Forest (RF), and Long Short-Term Memory (LSTM) algorithms to correct systematic biases in high-resolution simulations (focusing on extreme events: heavy rainfall, heatwaves) over the complex terrain of Wanzhou, Three Gorges Reservoir Area. The code enables intelligent calibration of meteorological variables (temperature, precipitation, wind speed) and supports climate resilience studies in the Yangtze River Basin. WRF model coupling with machine learning; Extreme weather bias correction; XGBoost/RF/LSTM optimization; Meteorological post-processing 周育琳 RESTRICTED dataset Science Data Bank