Skip to content
Open access

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

Sep 2026 · Earth System Science Data · Vol 18, pp. 6763-6781 · 0 citations · 25 references

TL;DR

This study implements a hybrid-structure-based deep learning framework to generate monthly 2 m specific humidity, 2 m temperature and surface pressure at 1/30° × 1/30° horizontal resolution during 1901–2023, and reproduces learned terrain-related spatial gradients without explicitly enforcing physical equations or terrain constraints.

Abstract

The Tibetan Plateau acts as the “Asian Water Tower” and faces regional amplified warming compared to the global climate change baseline. Given the Tibetan Plateau's pronounced alpine terrain, i.e., significant elevation gradients within short horizontal distances, studies on climate changes/dynamics over this mountainous region fundamentally depend on spatially high-resolution datasets. However, most currently available high-resolution datasets only extend back to the 1980s, while records extending into the pre-satellite era remain scarce, especially for near-surface atmospheric humidity. Thus, our study implements a hybrid-structure-based deep learning framework to generate monthly 2 m specific humidity, 2 m temperature and surface pressure at 1/30° × 1/30° horizontal resolution during 1901–2023. Briefly, employing a hybrid-structure model (FourCastNet by NVIDIA ® ), historical high-resolution fields (1/30° × 1/30° covering 1901–2023) are generated based on long-range low-resolution (0.5° × 0.5° covering 1901–2023 from Climatic Research Unit Time-Series, CRU_TS) and short-range high-resolution fields (1/30° × 1/30° covering 1979–2023 from the Tibetan Plateau Multi-source Meteorological Forcing Dataset; TPMFD) via spatial downscaling. The reconstructed fields were evaluated using target-referenced performance metrics, inter-product comparisons, and station-based consistency assessments. FourCastNet provides a data-driven statistical mapping from coarse CRU_TS predictors to high-resolution TPMFD target fields and reproduces learned terrain-related spatial gradients without explicitly enforcing physical equations or terrain constraints. The pre-1950 reconstruction remains less observationally constrained, and fine-scale early-century variability should be interpreted cautiously. Open access to this dataset is at https://doi.org/10.57760/sciencedb.36169 (Chen, 2026).

Read PDF

Similar papers

Open access Oct 2026

Early warning of meteorological drought in Morocco’s Atlas mountains: a multi-paradigm benchmark of satellite-augmented deep learning and tree-based models

Meteorological drought monitoring in Morocco’s High Atlas and Anti-Atlas Mountains remains reactive, yet few predictive studies have combined satellite observations with spatiotemporal deep learning in mountainous terrain. We develop a Convolutional Gated Recurrent Unit (ConvGRU) framework to forecast the 6-month Stand...

Nacer Aderdour, M. Maanan, H. Rueff et al. · 0 citations
Open access Sep 2026

PERFORMANCE OF U-NET AND CONVLSTM FOR 850 HPA WIND FORECASTING IN JAKARTA

Results show that model selection should consider spatial, temporal, and physical diagnostics alongside global accuracy metrics alongside global accuracy metrics in very short-range forecasting of 850-hPa winds over tropical urban-coastal regions.

Gatot Andriyanto, A. Susanto, A. A. Waskita · 0 citations
Sep 2026

14-Day PM2.5 and O3 Forecasting over Eastern China Using a Hybrid CNN-Transformer Architecture Driven by Multilevel Meteorological Fields.

Air pollution is modulated by multiscale meteorological processes spanning from local to regional domains and extending from the near-surface layer to the upper troposphere. However, existing data-driven models often neglect these complex spatiotemporal dependencies, limiting medium- to long-term forecast accuracy. The...

Lei Zhang, An-Bao Gong, Tong Wu et al. · 0 citations
Open access Sep 2026

An NWP-Free, Observation-Driven Deep Learning Approach to Heavy-Rainfall Nowcasting Beyond the Three-Hour Limit

FlowsNet is presented, an observation-based multisensor fusion model that learns directly from radar/rain gauge-analyzed precipitation, surface variables from ground stations, geostationary satellite imagery, and satellite-derived precipitation context and outperforms a leading extrapolation-based method and state-of-t...

Ryu Shimabukuro, Tomohiko Tomita, Tsuyoshi Yamaura et al. · 0 citations
Open access Sep 2026

Estimating Ground-Level PM2.5 over Beijing–Tianjin–Hebei from DQ-1 Wide-Swath Imager Signals and ERA5 Meteorology Using Physics-Guided Feature Engineering

The DaQi-1 (DQ-1) Wide-Swath Imager (WSI) combines an approximately 2300 km swath with 15 visible-to-shortwave-infrared channels at 75–600 m resolution, providing broad regional coverage and flexible spectral support. We developed an ExtraTrees estimator from WSI signals and ERA5 planetary boundary-layer height, winds,...

Rui-Jie Zhang, Hui Chen, Chun-Yan Zhou et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.