CRLC: Cross-resolution national-scale land-cover mapping based on noisy label learning: a case study of China
CRLC are the 10-m resolution land cover maps for China in 2020 achieved by the deep classification network, the estimated overall accuracy is 84.35% ± 0.92%.
The CRLC maps include eight land cover classes:
- Cropland
- Forest
- Grass/shrubland
- Wetland
- Water bodies
- Impervious
- Bareland
- Snow/ice
Each file name corresponds to a specific region and is structured as follows: N_<lower left longitude>_<lower left latitude>.tif
You can download the CRLC maps from the following links:
Baidu Drive (Code: idea)
If you use the CRLC dataset in your research, please cite the following article:
Liu, Yinhe, et al. "Cross-resolution national-scale land-cover mapping based on noisy label learning: A case study of China." International Journal of Applied Earth Observation and Geoinformation 118 (2023): 103265.
You can find more resources and datasets from our group on our website: http://rsidea.whu.edu.cn/resource_sharing.htm.