Pakistan LULC and Deforestation Dataset (2001–2021): Derived LULC Maps, Forest Fragmentation, and ML-Based Risk Layers
Description
This dataset contains land use/land cover (LULC) maps, deforestation and forest gain transitions, forest fragmentation layers (MSPA), proximity rasters, and machine learning-based deforestation risk prediction maps for Pakistan from 2001 to 2021. Data were derived using Landsat 5, 7, and 8 imagery, processed in R, Google Earth Engine, and Python. The dataset supports reproducibility of the associated manuscript submitted to Earth’s Future journal, and facilitates forest degradation monitoring under climate and anthropogenic pressures.
Key components:
- LULC classification maps for 2001, 2005, 2010, 2015, and 2021
- Deforestation and forest gain transition rasters
- Forest fragmentation maps using GUIDOS MSPA
- Proximity rasters: distance from roads, built-up areas, and water
- Model prediction outputs with SHAP interpretation
Scripts and workflows are hosted at: https://github.com/gohar147/Assessing-Deforestation-and-Degradation-Risks-in-Pakistan-2001-2021-
Please cite this dataset if used in your research.
Files
ReadMe.md
Additional details
Dates
- Submitted
-
2025-03
Software
- Repository URL
- https://github.com/gohar147/Assessing-Deforestation-and-Degradation-Risks-in-Pakistan-2001-2021-
- Programming language
- R , JavaScript
References
- de Sousa, K., Sparks, A., Ashmall, W., van Etten, J., Solberg, S., 2020. chirps: API Client for the CHIRPS Precipitation Data in R. J Open Source Softw 5. https://doi.org/10.21105/joss.02419
- Du, H., Tan, M.L., Zhang, F., Chun, K.P., Li, L., Kabir, M.H., 2024. Evaluating the effectiveness of CHIRPS data for hydroclimatic studies. Theor Appl Climatol. https://doi.org/10.1007/s00704-023-04721-9
- Hossain, M.S., Bujang, J.S., Zakaria, M.H., Hashim, M., 2015. Assessment of Landsat 7 Scan Line Corrector-off data gap-filling methods for seagrass distribution mapping. Int J Remote Sens 36, 1188–1215.