This repository contains the data, trained models, and results from the Random Forest analysis to predict water table depth (WTD) in the Pampean Region, Argentina:
Title: Modelling shallow groundwater level fluctuations in very flat landscapes based on satellite data and machine learning
## Authors
Javier Houspanossian¹, Francisco Diez¹, Raul Rivas¹, Esteban Jobbagy², Mauro Holzman¹, Gabriëlle J. M. De Lannoy³
**Affiliations:**¹ Institute of Hydrology of Plains "Dr. Eduardo Jorge Usunoff" (IHLLA), CONICET – Comisión de Investigaciones Científicas de la Provincia de Buenos Aires (CIC PBA), Argentina.
² Group of Environmental Studies (GEA), National University of San Luis (UNSL) – CONICET, Argentina.
³ Remote Sensing and Data Assimilation research group, Department of Earth and Environmental Sciences, KU Leuven, Heverlee, Belgium.
**Corresponding author:** Javier Houspanossian - jhouspa@gmail.com
This repository contains the data, trained models, and results from the Random Forest analysis to predict water table depth (WTD) in the Pampean Region, Argentina.
The optimal model (Full\_2) uses climatic variables (precipitation and evapotranspiration accumulated over multiple temporal windows) and the Surface Water Coverage Index (SWCI) as predictors.