Downscale Anything with Random Forest
Plugin ID: 4139
Downscale Anything with Random Forest is a QGIS Processing plugin that allows
flexible dasymetric downscaling of coarse rasters to user-defined resolutions.
The algorithm uses high-resolution covariates and Random Forest regression to redistribute values.
Key features include:
1. User-defined target resolution.
2. Random Forest regression with fast pixel sampling.
3. Support for random or spatial-block splitting.
4. Evaluation metrics (R², RMSE, MAE) and OOB score.
5. Outputs raster, CSV (evaluation + feature importance), and PNG plots.
(1) votes
Download latest
This plugin provides a practical way to perform machine-learning-based downscaling in QGIS.
It is suitable for spatial analysis, environmental modeling, and urban/regional studies.
Example use cases include downscaling VIIRS Nighttime Lights (avg_rad), Land Surface Temperature (LST),
population density (e.g., WorldPop), and other gridded indicators (e.g., PM2.5, precipitation,
socio-economic indices).
Created by Firman Afrianto.
| Version | QGIS >= | QGIS <= | Date | |||
|---|---|---|---|---|---|---|
| 1.0.0 | - | 3.0.0 | 3.99.0 | 24 | firmanafrianto | 2025-08-20T16:38:43.012008+00:00 |
