Unified Deep Learning Model for Global Prediction of Aboveground Biomass, Canopy Height and Cover from High-Resolution, Multi-Sensor Satellite Imagery

TL;DR

This paper introduces a deep learning model that uses multi-sensor satellite imagery to accurately predict aboveground biomass, canopy height, and cover globally, improving scalability and temporal resolution for forest carbon monitoring.

Contribution

The authors develop a unified deep learning model trained on global GEDI data that simultaneously predicts multiple forest metrics with high accuracy and transferability.

Findings

Achieves a mean absolute error of 26.1 Mg/ha for biomass

Demonstrates high correlation with independent ground measurements

Improves prediction accuracy over previous methods

Abstract

Regular measurement of carbon stock in the world's forests is critical for carbon accounting and reporting under national and international climate initiatives, and for scientific research, but has been largely limited in scalability and temporal resolution due to a lack of ground based assessments. Increasing efforts have been made to address these challenges by incorporating remotely sensed data. We present a new methodology which uses multi-sensor, multi-spectral imagery at a resolution of 10 meters and a deep learning based model which unifies the prediction of above ground biomass density (AGBD), canopy height (CH), canopy cover (CC) as well as uncertainty estimations for all three quantities. The model is trained on millions of globally sampled GEDI-L2/L4 measurements. We validate the capability of our model by deploying it over the entire globe for the year 2023 as well as annually from 2016 to 2023 over selected areas. The model achieves a mean absolute error for AGBD (CH, CC) of 26.1 Mg/ha (3.7 m, 9.9 %) and a root mean squared error of 50.6 Mg/ha (5.4 m, 15.8 %) on a globally sampled test dataset, demonstrating a significant improvement over previously published results. We also report the model performance against independently collected ground measurements published in the literature, which show a high degree of correlation across varying conditions. We further show that our pre-trained model facilitates seamless transferability to other GEDI variables due to its multi-head architecture.