Contextualizing Pan-Tropical Allometric Models for Biomass Estimation

Abstract

Allometric Models (AMs) play a central role in monitoring and mitigating climate change as they provide accurate estimation of biomass and carbon sequestered by trees from nonAllometric Models (AMs) play a central role in monitoring and mitigating climate change as they provide accurate estimation of biomass and carbon sequestered by trees from non-destructive, easy to obtain physical measurements. Unfortunately, practitioners spend considerable effort in researching, qualifying and choosing AMs for specific growth conditions. To overcome this situation Chave et al. (2014) developed a pan-tropical AM with equivalent accuracy to local, site-specific AMs. We build upon this work to study how contextualizing AMs can improve predictive power but also provide safety checks for their application. Our first contribution is a family of Machine Learning (ML) models that incorporate additional context pertaining to growth conditions. Evaluation shows statistically significant improvements in predictive power over a range of metrics. These models bring additional choice for practitioners in important applications such as national forest inventories, carbon certifications and calibration of satellite based biomass maps to field data. Our second contribution proposes a principled method to estimate how much additional error one can expect when applying a given AM under new, shifting conditions - without access to ground truth biomass measurements. This method provides practitioners with a practical, data-driven safety check to qualify the risk of AMs usage in new study sites.