An integrated, automated and modular approach for real-time weather monitoring of surface meteorological variables and short-range forecasting using machine learning

Weather monitoring and forecasting plays a vital role in a great variety of human activities such as agriculture, transportation, and extreme weather phenomena. This study presents the first outcomes of the development of a fully automated system regarding the real-time recording of basic meteorological parameters and their short-range forecasting (nowcasting). The system itself is divided into five core components: a hardware system for monitoring atmospheric conditions (Commercial Off-The-Shelf structures), a system for storing and managing data, a module for distributing data to support applications, a machine learning algorithm for nowcasting, and a user-friendly interface, all made by modern tools and methods, described analytically. Finally, the nowcasting procedure along with the relative accuracy results, is presented. The nowcasting procedure is based on a Long Short-Term Memory (LSTM) model scheme which is parametrized in such a way that reliable forecasts, up to 2 h ahead of time, can be provided.