TPHH: A long-term (1901--2023) high-resolution (1/30°) near-surface humidity dataset for the Tibetan Plateau generated via spatial downscaling based on hybrid-structure deep learning

# TPHH Dataset: Long-term High-resolution Meteorological Reconstruction over the Tibetan Plateau (1901-1978)## OverviewThis dataset (TPHH v1.0) provides reconstructed monthly meteorological fields over the Tibetan Plateau at a high spatial resolution (1/30 degree, approx. 3 km) for the period 1901–1978. The reconstruction is generated using a FourCastNet-based deep learning framework, fusing the long-term consistency of CRU TS 4.08 with the high-resolution spatial patterns of the TPMFD dataset.This dataset accompanies the paper: "TPHH: A long-term (1901–1978) high-resolution (1/30°) reconstruction of meteorological variables over the Tibetan Plateau" ## File Description1. **TPHH_1901-1978_monthly.nc**  - Content: The main reconstructed historical dataset.  - Period: Jan 1901 - Dec 1978.  - Format: NetCDF4.  - Resolution: 1/30 degree (~3 km).2. **TPHH_validation_1979-2023_monthly.nc**  - Content: The reconstruction results for the modern period (validation set) generated via K-Fold cross-validation.  - Period: Jan 1979 - Dec 2023.  - Use case: For validation and comparison purposes.3. **Auxiliary_Data.zip**  - Contains the static DEM file, study area boundary shapefiles (TPBoundary_HF), and sample data used for the model inference code.