Terrestrial Energy, Water, and Carbon Flux Estimation Using Machine Learning Algorithms

Abstract

Using the machine learning technique with the wider availability of various observation data, the integration of ground observation data and satellite observation data has been advancing. In recent years, these techniques were applied to studies of terrestrial energy, water, and carbon cycles to estimate their spatial and temporal variations by upscaling. In this article, we provide an overview of the upscaling technique using machine learning and discuss potential applications of the dataset to terrestrial biosphere studies.