Zhang et al. (2026) Daily Snow Depth Fusion Products for Arid Regions of Central Asia

Identification

• Journal: Mendeley Data
• Year: 2026
• Date: 2026-03-24
• Authors: Liancheng Zhang, Guli Jiapaer, Tao Yu, Xiapeng Jiang, Hongwu Liang, Pingping Feng, Tongwei Ju, Jingxin Zhang, Philippe De Maeyer, Tim VandeVoorde
• DOI: 10.17632/ngp35c3x9n.2

Research Groups

Liancheng Zhang, Guli Jiapaer, Tao Yu, Xiapeng Jiang, Hongwu Liang, Pingping Feng, Tongwei Ju, Jingxin Zhang, Philippe De Maeyer, Tim VandeVoorde

Short Summary

This study developed a high-precision daily snow depth fusion product for Central Asia (1980–2023) by integrating multiple existing snow depth products and in-situ observations using an XGBoost machine learning model, achieving significantly improved accuracy.

Objective

• To develop a high-precision daily snow depth fusion model and product for Central Asia by integrating multiple daily snow depth products and in-situ observations using a machine learning approach.

Study Configuration

• Spatial Scale: Central Asia (CA), 0.1° spatial resolution.
• Temporal Scale: Daily, spanning 1980–2023, with a seasonal modeling strategy (winter, spring, and autumn).

Methodology and Data

• Models used: XGBoost (XGB) machine learning model.
• Data sources: In-situ snow depth observations; ERA5-Land, MERRA-2, and GLDAS snow depth products; multi-dimensional covariates including topography, meteorological factors, temporal variables, land use, and snow-related parameters.

Main Results

• The generated daily snow depth fusion product for Central Asia achieved an RMSE of 6.5 cm, MAE of 3.9 cm, and an R of 0.86.
• The accuracy of the fusion product is significantly improved compared to other existing snow depth products across the Central Asia region.

Contributions

• Development of a novel high-precision daily snow depth fusion product for Central Asia using an XGBoost machine learning model, integrating multiple data sources and covariates.
• Significant improvement in snow depth accuracy compared to existing products, providing reliable data support for climate change studies, water resource management, and disaster early warning systems in arid Central Asia.

Funding

• Natural Science Foundation of Xinjiang Uygur Autonomous Region (Grant ID: 2025D01A104).

Citation

@article{Zhang2026Daily,
  author = {Zhang, Liancheng and Jiapaer, Guli and Yu, Tao and Jiang, Xiapeng and Liang, Hongwu and Feng, Pingping and Ju, Tongwei and Zhang, Jingxin and Maeyer, Philippe De and VandeVoorde, Tim},
  title = {Daily Snow Depth Fusion Products for Arid Regions of Central Asia},
  journal = {Mendeley Data},
  year = {2026},
  doi = {10.17632/ngp35c3x9n.2},
  url = {https://doi.org/10.17632/ngp35c3x9n.2}
}