Innovative AI-Driven Approach Enhances Carbon Sequestration Measurement in Semi-Arid Regions

A recent study published in the Journal of Remote Sensing introduces a groundbreaking method for estimating above-ground carbon (AGC) at an individual tree level, particularly in semi-arid regions. Developed by researchers at Lobelia Earth S.L., this approach leverages very high-resolution (VHR) satellite imagery and machine learning algorithms to provide a more accurate tool for measuring carbon sequestration. The study, titled 'Unlocking precision in carbon stock mapping: a new AI-driven approach,' details an Artificial Neural Network (ANN) model trained on over 400 individual tree crowns, achieving AGC estimates with notable accuracy.

The research team constructed a comprehensive AGC reference database from ground measurements, applying species-specific allometric equations to convert these into biomass. Deep learning models were then used to segment individual tree crowns and extract spectral information from VHR imagery, training and validating the ANN model. This resulted in a highly accurate model with a tree-level RMSE of just 373.85 kg, marking a significant improvement over previous technologies that often underestimated carbon stocks in dryland regions.

Martí Perpinyana-Vallès, the study's lead author, highlighted the importance of integrating field data with advanced Earth observation techniques. This innovation not only enhances our understanding of carbon sequestration dynamics but also improves land management practices globally. The use of Pléiades Neo satellite imagery, with its exceptional 30cm native resolution, played a crucial role in achieving this precision, enabling the accurate geolocation of individual trees and addressing previous limitations in carbon stock estimation.

The implications of this technology are vast, offering improvements in global carbon cycle assessments, land use optimization, and reforestation initiatives. It also provides essential data for climate change mitigation strategies, supporting policymakers in addressing environmental challenges. As this method gains wider adoption, it could harmonize carbon estimation discrepancies, offering invaluable support for international climate agreements and global sustainability efforts.

This research marks a significant advancement in the fight against climate change, providing a more accurate means of quantifying carbon within trees. Such precision is vital for developing effective climate adaptation and land management strategies worldwide. Funded by various organizations, including Intermon Oxfam Spain and the European Union, this study underscores the potential of AI-driven approaches in enhancing our planet's carbon resource management.