What does this research mean for the field?

The ChinaAI-FSC dataset provides the first large-scale, standardized, AI-ready fractional snow cover sample collection for China, enabling reliable AI-driven snow cover mapping and benchmarking of machine learning models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to develop a comprehensive, standardized dataset for fractional snow cover in China to enhance long-term monitoring efforts.

March 19, 2026Earth system science data0 citationsOpen Access

ChinaAI-FSC: a comprehensive AI-ready MODIS fractional snow cover dataset for China (2000–2022)

JHJinliang HouNorthwest Institute of Eco-Environment and Resources MZMingkai ZhangNorthwest Institute of Eco-Environment and Resources XHXiaohua HaoNorthwest Institute of Eco-Environment and Resources

Key Points

The aim is to develop a comprehensive, standardized dataset for fractional snow cover in China to enhance long-term monitoring efforts.
Created a dataset spanning 22 snow seasons from 2000 to 2022.
Extracted 20 feature variables using high-resolution images from Landsat and Sentinel satellites.
Applied a rigorous quality control and systematic sample preparation process.
Evaluated data reliability using a novel assessment protocol covering multiple dimensions.
Dataset includes 47,728 samples organized as 128 × 128 MODIS pixel tiles.
Demonstrated dataset reliability through benchmarking of six machine learning and deep learning models.
Validated against standard MODIS fractional snow cover products and provided seamless nationwide mapping.

Abstract

Abstract. We present ChinaAI-FSC, the first large-scale, standardized, AI-ready fractional snow cover (FSC) sample collection for China, spanning 22 snow seasons from 2000 to 2022 and addressing a critical gap in long-term snow monitoring. The dataset consists of 47 728 samples (each 128 × 128 MODIS-pixel tiles), where high-resolution Landsat-5/7/8/9 and Sentinel-2 imagery provide consistent FSC reference labels. A total of 20 feature variables, including MODIS surface reflectance (bands 1–7), topographic attributes, forest and land cover information, and geolocation factors, were extracted to enable both point-scale and tile-scale spatially contextualized AI modelling. A structured and transparent workflow, encompassing systematic sample preparation, rigorous quality control, spatiotemporal sample partitioning, and standardized metadata, ensures reproducibility, physical consistency, and interoperability across machine learning and deep learning applications. Dataset reliability and AI-readiness were systematically evaluated using a novel “Four Layers-Four Domains-Fifteen Attributes (4L-4D-15A)” assessment protocol, covering data, information, system, and application dimensions. The quality, reliability, and usability of ChinaAI-FSC were demonstrated through three representative use cases: (1) benchmarking of six ML/DL models (ANN, SVR, RF, CNN, UNet, and ResNet), (2) validation of the standard MODIS FSC product, and (3) nationwide seamless FSC mapping. By providing harmonized, validated, and well-documented samples, ChinaAI-FSC establishes a unified foundation for AI-driven snow cover mapping, long-term monitoring, and cryosphere–hydrological modelling, promoting reproducible, interoperable, and next-generation research in cryospheric science. The dataset is publicly available from the National Tibetan Plateau Data Center (TPDC) (Hou et al., 2025a) at https://doi.org/10.11888/Cryos.tpdc.303034 (also accessible via https://cstr.cn/18406.11.Cryos.tpdc.303034, last access: 24 February 2026) and from Zenodo (Hou et al., 2025b) at https://doi.org/10.5281/zenodo.17707386.

AI에게 질문

Bookmark

View Full Paper