How well can plant CO₂ uptake be predicted?
A new study involving the Environment Agency Austria investigates whether vegetation CO₂ uptake can be reliably modeled using satellite and measurement data—across different ecosystems. The study was recently published in the international scientific journal ScienceDirect.
Predicting Gross Primary Productivity (GPP) is key for understanding ecosystem health and quantifying the global carbon cycle. While data-driven models have shown strong performance in capturing GPP dynamics at specific sites, their ability to generalize across ecosystems without site-specific recalibration remains largely untested.
This study addresses this gap by evaluating the applicability of XGBoost and LSTM models in estimating GPP across different European ecosystems. It shows that a data-driven model combining satellite and measurement data can reliably predict plant CO₂ uptake across different sites. XGBoost delivered the best and most consistent performance, including for previously unseen ecosystems, while LSTM was better at capturing peak productivity. Overall, the results demonstrate that transferable predictions of plant productivity without site-specific recalibration are feasible.
