PROJECTION OF CLIMATE CHANGE IMPACTS ON NET PRIMARY PRODUCTIVITY OF THE LEGAL AMAZON – BRAZIL

Abstract

The Amazon Rainforest is one of the main carbon sinks (CO2) on the planet. However, recently, due to anthropic activities and climate change, it has lost its stability in CO2 absorption. Therefore, understanding the dynamics of future climate change scenarios becomes essential. We assess the influence of future climate change scenarios on NPP (biomass) levels in the Amazon Forest using ML models. The tested models were Bayesian, Linear Model, and Random Forest. The current scenario was evaluated using 19 bioclimatic covariates (worldclim dataset). While the future scenarios were based on RCPs 2.6 and 8.5 (based on the models of the MIROC5 and HadGEM2-ES models). Random Forest had the best performance statistic (R² = 0.71 in training and 0.68 in holdout-test). The climate change scenarios will imply an increase in the average NPP for the Amazon forest, especially with greater intensification in RCP 2.6 (2 and 7.69 % for the HadGEM2-ES and MIROC5 models, respectively). Forests (Evergreen Broadleaf Forests areas) will have greater carbon fixation capacity. In general, the Amazon forest will have increased carbon fixation capacity by the end of the century.