Evaluation of natural disasters using machine learning and big data for Georgia

The purpose of the presented paper is to estimate and analyze the distribution of precipitation over the territory of Georgia to study drought related processes and other natural hazards, as well as to evaluate the possibility of environment hazard detection at the early stage of their evolution, monitoring and prediction. We intend in our study to apply the Machine Learning, the branch of computer science which focuses on the use of big data and algorithms to imitate the way that humans learn, gradually improving its accuracy. Such analysis allows developing a Combined Drought Index (CDI) and corresponding drought hazard 5km resolution map