Articles | Volume 28, issue 11
https://doi.org/10.5194/hess-28-2357-2024
https://doi.org/10.5194/hess-28-2357-2024
Research article
 | 
05 Jun 2024
Research article |  | 05 Jun 2024

Machine learning and global vegetation: random forests for downscaling and gap filling

Barry van Jaarsveld, Sandra M. Hauswirth, and Niko Wanders

Data sets

MOD13A2 MODIS/Terra Vegetation Indices 16-Day L3 Global 1 km SIN Grid V006 K. Didan https://doi.org/10.5067/MODIS/MYD13A2.061

MCD12C1 v061 MODIS/Terra+Aqua Land Cover Type Yearly L3 Global 0.05 Deg CMG USGS https://doi.org/10.5067/MODIS/MCD12C1.061

ERA5-Land hourly data from 1950 to present J. Muñoz Sabater https://doi.org/10.24381/cds.e2161bac

Hourly potential evapotranspiration (hPET) at 0.1degs grid resolution for the global land surface from 1981-present Michael Singer et al. https://doi.org/10.5523/bris.qb8ujazzda0s2aykkv0oq0ctp

Download
Short summary
Drought often manifests itself in vegetation; however, obtaining high-resolution remote-sensing products that are spatially and temporally consistent is difficult. In this study, we show that machine learning (ML) can fill data gaps in existing products. We also demonstrate that ML can be used as a downscaling tool. By relying on ML for gap filling and downscaling, we can obtain a more holistic view of the impacts of drought on vegetation.