Tackling the Overestimation of Forest Carbon with Deep Learning and Aerial Imagery
This addresses the issue of inaccurate carbon offset measurements for climate mitigation and forest conservation, though it is incremental as it builds on existing ML methods for carbon estimation.
The paper tackled the problem of overestimating forest carbon in tropical reforestation projects by comparing deep learning-based estimates from aerial imagery, satellite imagery, and ground-truth measurements, finding that satellite imagery can overestimate above-ground biomass by up to 10 times.
Forest carbon offsets are increasingly popular and can play a significant role in financing climate mitigation, forest conservation, and reforestation. Measuring how much carbon is stored in forests is, however, still largely done via expensive, time-consuming, and sometimes unaccountable field measurements. To overcome these limitations, many verification bodies are leveraging machine learning (ML) algorithms to estimate forest carbon from satellite or aerial imagery. Aerial imagery allows for tree species or family classification, which improves the satellite imagery-based forest type classification. However, aerial imagery is significantly more expensive to collect and it is unclear by how much the higher resolution improves the forest carbon estimation. This proposal paper describes the first systematic comparison of forest carbon estimation from aerial imagery, satellite imagery, and ground-truth field measurements via deep learning-based algorithms for a tropical reforestation project. Our initial results show that forest carbon estimates from satellite imagery can overestimate above-ground biomass by up to 10-times for tropical reforestation projects. The significant difference between aerial and satellite-derived forest carbon measurements shows the potential for aerial imagery-based ML algorithms and raises the importance to extend this study to a global benchmark between options for carbon measurements.