Preprints
https://doi.org/10.5194/egusphere-2023-2368
https://doi.org/10.5194/egusphere-2023-2368
17 Oct 2023
 | 17 Oct 2023

Learning Extreme Vegetation Response to Climate Forcing: A Comparison of Recurrent Neural Network Architectures

Francesco Martinuzzi, Miguel D. Mahecha, Gustau Camps-Valls, David Montero, Tristan Williams, and Karin Mora

Abstract. Vegetation state variables are key indicators of land-atmosphere interactions characterized by long-term trends, seasonal fluctuations, and responses to weather anomalies. This study investigates the potential of neural networks in capturing vegetation state responses, including extreme behavior driven by atmospheric conditions. While machine learning methods, particularly neural networks, have significantly advanced in modeling nonlinear dynamics, it has become standard practice to approach the problem using recurrent architectures capable of capturing nonlinear effects and accommodating both long and short-term memory. We compare four recurrence-based learning models, which differ in their training and architecture: 1) recurrent neural networks (RNNs), 2) long short-term memory-based networks (LSTMs), 3) gated recurrent unit-based networks (GRUs), and 4) echo state networks (ESNs). While our results show minimal quantitative differences in their performances, ESNs exhibit slightly superior results across various metrics. Overall, we show that recurrent network architectures prove generally suitable for vegetation state prediction yet exhibit limitations under extreme conditions. This study highlights the potential of recurrent network architectures for vegetation state prediction, emphasizing the need for further research to address limitations in modeling extreme conditions within ecosystem dynamics.

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.
Francesco Martinuzzi, Miguel D. Mahecha, Gustau Camps-Valls, David Montero, Tristan Williams, and Karin Mora

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-2023-2368', Anonymous Referee #1, 23 Jan 2024
    • AC1: 'Reply on RC1', Francesco Martinuzzi, 21 May 2024
  • RC2: 'Comment on egusphere-2023-2368', Anonymous Referee #2, 10 May 2024
    • AC2: 'Reply on RC2', Francesco Martinuzzi, 21 May 2024
Francesco Martinuzzi, Miguel D. Mahecha, Gustau Camps-Valls, David Montero, Tristan Williams, and Karin Mora

Model code and software

Code for machine learning models Francesco Martinuzzi https://github.com/MartinuzziFrancesco/rnn-ndvi

Francesco Martinuzzi, Miguel D. Mahecha, Gustau Camps-Valls, David Montero, Tristan Williams, and Karin Mora

Viewed

Total article views: 599 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
386 176 37 599 24 18
  • HTML: 386
  • PDF: 176
  • XML: 37
  • Total: 599
  • BibTeX: 24
  • EndNote: 18
Views and downloads (calculated since 17 Oct 2023)
Cumulative views and downloads (calculated since 17 Oct 2023)

Viewed (geographical distribution)

Total article views: 572 (including HTML, PDF, and XML) Thereof 572 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 25 Jul 2024
Download
Short summary
We investigated how machine learning can forecast extreme vegetation responses to weather. Examining four models, no single one stood out as the best, though "echo state networks" showed minor advantages. Our results indicate that while these tools are able to generally model vegetation states, they face challenges under extreme conditions. This underlines the potential of artificial intelligence in ecosystem modeling, also pinpointing areas that need further research.