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

Jin, Zheng; Chen, Zezhou; You, Qinglong; Liu, Zhaoxiang; Zhang, Jintao; Hu, Huan; Chen, Ping; Liu, Xiang; Wang, Zipeng; Wang, Kai; Lian, Shiguo; Kang, Shichang

doi:10.5194/essd-18-6763-2026

Articles | Volume 18, issue 9

https://doi.org/10.5194/essd-18-6763-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-18-6763-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 9

Data description article

|

14 Sep 2026

Data description article |

| 14 Sep 2026

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

Zheng Jin, Zezhou Chen, Qinglong You, Zhaoxiang Liu, Jintao Zhang, Huan Hu, Ping Chen, Xiang Liu, Zipeng Wang, Kai Wang, Shiguo Lian, and Shichang Kang

Supplement

https://doi.org/10.5194/essd-18-6763-2026-supplement

Data sets

TPHH: A long-term (1901–1978) high-resolution (1/30°) reconstruction of meteorological variables over the Tibetan Plateau Zezhou Chen https://doi.org/10.57760/sciencedb.36169

Model code and software

Sawyer000/TPHH: First release (Version v1.0.0) Zheng Jin and Zezhou Chen https://doi.org/10.5281/zenodo.22690805

Download

Article (9460 KB)
Full-text XML

Short summary

This study presents the TPHH (Tibetan Plateau Historical High) dataset, a high-resolution (1/30°) monthly climate dataset for the Tibetan Plateau spanning 1901–2023, featuring 2 m temperature, specific humidity, and surface pressure. By employing a hybrid deep learning framework (FourCastNet), we downscaled coarse historical data through the synergistic mapping of total-field signals and terrain constraints. Validated against independent observations, this physically-consistent dataset bridges the pre-satellite data gap.