A Footprint-Aware, High-Resolution Approach for Carbon Flux Prediction Across Diverse Ecosystems
This addresses the problem of high-resolution carbon flux prediction for environmental scientists and policymakers, offering a novel method for ecosystem monitoring.
The paper tackles the challenge of monitoring carbon drawdown across large ecosystems by introducing Footprint-Aware Regression (FAR), a deep-learning framework that predicts spatial footprints and pixel-level carbon flux at 30 m scale, achieving an R2 of 0.78 on test sites.
Natural climate solutions (NCS) offer an approach to mitigating carbon dioxide (CO2) emissions. However, monitoring the carbon drawdown of ecosystems over large geographic areas remains challenging. Eddy-flux covariance towers provide ground truth for predictive 'upscaling' models derived from satellite products, but many satellites now produce measurements on spatial scales smaller than a flux tower's footprint. We introduce Footprint-Aware Regression (FAR), a first-of-its-kind, deep-learning framework that simultaneously predicts spatial footprints and pixel-level (30 m scale) estimates of carbon flux. FAR is trained on our AMERI-FAR25 dataset which combines 439 site years of tower data with corresponding Landsat scenes. Our model produces high-resolution predictions and achieves R2 = 0.78 when predicting monthly net ecosystem exchange on test sites from a variety of ecosystems.