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

Abstract

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.

SpectralIndices.jl: Streamlining spectral indices access and computation for Earth system research

“…With the growing availability of optical Earth observation data, researchers have developed many spectral indices (SI) to analyze specific surface features and phenomena in areas such as vegetation (Zeng et al, 2022), water bodies (Ma et al, 2019), urban environments (Zha et al, 2003), and snow-covered regions (Salomonson and Appel, 2004). Additionally, these indices are used as a basis for environmental machine learning (ML) applications either as targets (Li et al, 2022;Luo et al, 2022;Martinuzzi et al, 2023) or as features (Pabon-Moreno et al, 2022;Montero et al, 2024).…”