2026-10-13T01:42:24Z https://www.scidb.cn/oai

10.57760/sciencedb.0125j 2026-09-10T14:05:30Z

2026-09-10 Code and processed data for: Physics-guided graph attention networks for multi-horizon PM2.5 forecasting on the northern slope of the Tianshan Mountains doi:10.57760/sciencedb.0125j en This archive contains the complete code and processed data supporting the paper "Physics-guided graph attention networks for multi-horizon PM2.5 forecasting on the northern slope of the Tianshan Mountains" . It includes the full analysis pipeline (data cleaning, feature engineering, baseline models, Physics-GAT training, ablations, adaptive prediction-level fusion, and bootstrap significance tests), saved model outputs and weights, the final figures, and the processed hourly dataset cleaned_data.csv for 16 stations. See README.md in the archive for step-by-step reproduction instructions. A CUDA GPU is recommended for full retraining; all figures and the attention-weight extraction can be regenerated on a CPU-only machine from the saved results. PM2.5 forecasting; physics-guided deep learning; Tianshan Mountains 陈慧 鲁建江 PUBLIC https://mit-license.org dataset Science Data Bank