Preprints
https://doi.org/10.5194/egusphere-2023-1898
https://doi.org/10.5194/egusphere-2023-1898
06 Oct 2023
 | 06 Oct 2023

High-resolution long-term average groundwater recharge in Africa estimated using random forest regression and residual interpolation

Anna Pazola, Richard G. Taylor, Mohammad Shamsudduha, Jon French, Alan M. MacDonald, Tamiru Abiye, and Ibrahim Baba Goni

Abstract. Groundwater recharge is a key hydrogeological variable that informs the renewability of groundwater resources. Long-term average (LTA) groundwater recharge provides a measure of replenishment under the prevailing climatic and landuse conditions and is therefore of considerable interest in assessing the sustainability of groundwater withdrawals globally. This study builds on the modelling results of MacDonald et al. (2021) who produced the first LTA groundwater recharge map across Africa using a linear mixed model (LMM) rooted in 134 ground-based studies. Here, continent-wide predictions of groundwater recharge were generated using Random Forest (RF) regression employing five variables (precipitation, potential evapotranspiration, soil moisture, NDVI and aridity index) at a higher spatial resolution (0.1° resolution) to explore whether an improved model might be achieved through machine learning. Through the development of a series of RF models, we confirm that a RF model is able to generate maps of higher spatial variability than LMM; the performance of final RF models in terms of the goodness of fit (R2 = 0.83, 0.88 with residual kriging) is comparable to the LMM (R2 = 0.86). The higher spatial scale of the predictor data (0.1°) in RF models better preserves small-scale variability from predictor data, than the values provided via interpolated LMM; these may provide useful in testing global-to-local scale models. The RF model remains, nevertheless, constrained by its representation of focused recharge and by the limited range of recharge studies in tropical Africa, especially in the areas of high precipitation. This confers substantial uncertainty in model estimates.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Anna Pazola, Richard G. Taylor, Mohammad Shamsudduha, Jon French, Alan M. MacDonald, Tamiru Abiye, and Ibrahim Baba Goni

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-1898', Anonymous Referee #1, 06 Nov 2023
    • AC1: 'Reply on RC1', Anna Pazola, 08 Feb 2024
  • RC2: 'Comment on egusphere-2023-1898', Anonymous Referee #2, 21 Nov 2023
    • AC2: 'Reply on RC2', Anna Pazola, 08 Feb 2024
Anna Pazola, Richard G. Taylor, Mohammad Shamsudduha, Jon French, Alan M. MacDonald, Tamiru Abiye, and Ibrahim Baba Goni

Data sets

High-resolution long-term average groundwater recharge in Africa estimated using random forest regression and residual interpolation Anna Pazola https://doi.org/10.6084/m9.figshare.22591375.v1

Model code and software

Application of random forest regression in modelling long-term average groundwater recharge in Africa Anna Pazola https://github.com/pazolka/rf-groundwater-recharge-africa

Anna Pazola, Richard G. Taylor, Mohammad Shamsudduha, Jon French, Alan M. MacDonald, Tamiru Abiye, and Ibrahim Baba Goni

Viewed

Total article views: 483 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
296 164 23 483 41 15 19
  • HTML: 296
  • PDF: 164
  • XML: 23
  • Total: 483
  • Supplement: 41
  • BibTeX: 15
  • EndNote: 19
Views and downloads (calculated since 06 Oct 2023)
Cumulative views and downloads (calculated since 06 Oct 2023)

Viewed (geographical distribution)

Total article views: 496 (including HTML, PDF, and XML) Thereof 496 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 18 May 2024
Download
Short summary
This study advances groundwater research using a high-resolution Random Forest model, revealing new recharge areas and spatial variability, mainly in humid regions. Limited data in rainy zones is a constraint for the model. Our findings underscore machine learning's promise for large-scale groundwater modelling, while further emphasizing the importance of data collection for robust results.