Global Vegetation Modeling with Pre-Trained Weather Transformers

TL;DR

This paper adapts a pre-trained weather forecasting Transformer to model vegetation activity globally using meteorological data, demonstrating improved NDVI predictions over models trained from scratch.

Contribution

It introduces a novel approach of transferring a pre-trained weather Transformer to vegetation modeling, enhancing NDVI estimation accuracy.

Findings

Pre-trained weather models improve NDVI estimates.

Global vegetation activity can be modeled at 0.25° resolution.

Transfer learning reduces data and training time requirements.

Abstract

Accurate vegetation models can produce further insights into the complex interaction between vegetation activity and ecosystem processes. Previous research has established that long-term trends and short-term variability of temperature and precipitation affect vegetation activity. Motivated by the recent success of Transformer-based Deep Learning models for medium-range weather forecasting, we adapt the publicly available pre-trained FourCastNet to model vegetation activity while accounting for the short-term dynamics of climate variability. We investigate how the learned global representation of the atmosphere's state can be transferred to model the normalized difference vegetation index (NDVI). Our model globally estimates vegetation activity at a resolution of \SI{0.25}{\degree} while relying only on meteorological data. We demonstrate that leveraging pre-trained weather models improves the NDVI estimates compared to learning an NDVI model from scratch. Additionally, we compare our results to other recent data-driven NDVI modeling approaches from machine learning and ecology literature. We further provide experimental evidence on how much data and training time is necessary to turn FourCastNet into an effective vegetation model. Code and models will be made available upon publication.