Preprints
https://doi.org/10.5194/hess-2022-430
https://doi.org/10.5194/hess-2022-430
08 Feb 2023
 | 08 Feb 2023
Status: a revised version of this preprint is currently under review for the journal HESS.

Machine learning and Global Vegetation: Random Forests for Downscaling and Gapfilling

Barry van Jaarsveld, Sandra Hauswirth, and Niko Wanders

Abstract. Drought is a devastating natural disaster, where water shortage often manifests itself in the health of vegetation. Unfortunately, it is difficult to obtain high-resolution vegetation drought impact, which is spatially and temporally consistent. While remotely sensed products can provide part of this information, they often suffer from data gaps and limitations in spatial or temporal resolutions. A persistent feature among remote sensing products is tradeoffs between spatial resolution and revisiting times, where high temporal resolution is met by coarse spatial resolution and vice verse. Machine learning methods have been successfully applied in a wide range of remote sensing and hydrological studies. However, global applications to resolve drought impacts on vegetation dynamics still need to be made available, while there is significant potential for such a product to aid improved drought impact monitoring. To this end, this study predicted global vegetation dynamics based on the Enhanced Vegetation Index (evi) and the popular Random Forest algorithm (RF) at 0.1°. We assessed the applicability of RF as a gap filling and downscaling tool to generate spatial and temporal consistent global evi estimates. To do this, we trained an RF regressor with 0.1° evi data using a host of features indicative of water and energy balances experienced by vegetation and we evaluated the performance of this new product. Next, to test whether the RF is robust in terms of spatial resolution, we downscale global evi, the model trained on 0.1° data is used to predict evi at 0.01° resolution. The results show that the RF can capture global evi dynamics at both the 0.1° (RMSE: 0.02–0.4) and at the finer 0.01° (RMSE: 0.04–0.6) resolution. Overall errors were higher in the down-scaled 0.01° compared to the 0.1° product. Yet, relative increases remained small, thus demonstrating that RF can be used to create downscaled and temporally consistent evi products. Additional error analysis reveals that errors vary spatiotemporally, with underrepresented landcover types and periods of extreme vegetation conditions having the highest errors. Finally, this model is used to produce global spatially continuous evi products at both the 0.1° and 0.01° spatial resolution for 2003–2013 at an 8-day frequency.

Barry van Jaarsveld, Sandra Hauswirth, and Niko Wanders

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2022-430', Anonymous Referee #1, 15 May 2023
    • AC1: 'Reply on RC1', Barry van Jaarsveld, 21 Jul 2023
  • RC2: 'Comment on hess-2022-430', Anonymous Referee #2, 05 Jun 2023
    • AC2: 'Reply on RC2', Barry van Jaarsveld, 21 Jul 2023
Barry van Jaarsveld, Sandra Hauswirth, and Niko Wanders
Barry van Jaarsveld, Sandra Hauswirth, and Niko Wanders

Viewed

Total article views: 710 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
473 218 19 710 10 8
  • HTML: 473
  • PDF: 218
  • XML: 19
  • Total: 710
  • BibTeX: 10
  • EndNote: 8
Views and downloads (calculated since 08 Feb 2023)
Cumulative views and downloads (calculated since 08 Feb 2023)

Viewed (geographical distribution)

Total article views: 681 (including HTML, PDF, and XML) Thereof 681 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 14 Feb 2024
Download
Short summary
Drought often manifests itself in vegetation, yet, obtaining high-resolution remote sensing products which are spatially and temporally consistent is difficult. In this study, we show that machine learning can fill data gaps in existing products. We also demonstrate that machine learning can be used as a downscaling tool. By relying on machine learning for gap filling and downscaling, we produce 8-daily global maps of vegetation indices at the 0.1⁰ and 0.01⁰ spatial resolution.