Estimating hourly air temperature in an Amazon-Cerrado transitional forest in Brazil using Machine Learning regression models

Abstract

Air temperature holds significant importance in microclimate and environmental health studies, playing a crucial role in weather regulation. There is a need to develop a reliable model capable of accurately capturing air temperature variations. In this study, we focused on the Amazon-Cerrado transitional forest, constructing a robust predictive model for hourly temperature fluctuations. This forest, situated approximately 50 km northwest of Sinop, Mato Grosso, Brazil, is a transitional area, making it important to investigate its climatic behavior and ecosystems. We estimated air temperature using machine learning techniques such as Random Forest, Gradient Boosting, Multilayer Perceptron, and Support Vector Regressor, aiming to evaluate the most effective models based on relevant metrics. Performance assessments were conducted during both dry and rainy seasons to verify their adaptability. The top-performing Random Forest model demonstrated Willmott and Spearman indexes above 0.97. The air relative humidity, solar radiation, and volumetric soil water content were identified as the most important features, evaluated with Willmott and Spearman indexes above 0.95 in a model with such dimensionality reduction. These results underscore the efficacy of machine learning techniques in accurately estimating air temperature.