Processing urban weather data with artificial intelligence to support energy communities.

• Grant number: 25/25597-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2025
• End date: November 30, 2026
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Joel David Melo Trujillo
• Grantee: Pedro Vieira Colombo
• Host Institution: Centro de Engenharia, Modelagem e Ciências Sociais Aplicadas (CECS). Universidade Federal do ABC (UFABC). Santo André , SP, Brazil
• Associated research grant: 25/13023-6 - Energy and Climate Data Visualization and Analysis for Energy Communities Using Artificial Intelligence Techniques, AP.R

Abstract

Several municipal governments have installed weather stations in urban areas to monitor microclimates and mitigate the effects of urban heat islands. However, communication failures, temporary data loss, and sensor limitations compromise the integrity of the collected time series, especially regarding temperature, solar irradiance, wind speed, and rainfall. This data is directly related to the operation of energy communities with photovoltaic systems, storage, and demand management. This undergraduate research project proposes the application of artificial intelligence (AI) techniques to fill in missing data and verify the physical consistency of these meteorological variables, through the processing and analysis of records from 25 public stations in the city of Santo André, available in the Open Energy Data Lake. The scholarship recipient will be responsible for organizing, validating, and improving the time series, with the support of expert researchers from the main project, using approaches based on historical data from neighboring stations and supervised and unsupervised learning algorithms. It is expected that improving this data will enable its use in real time, expanding its applicability in local climate change adaptation actions and in supporting decision-making by urban energy communities. (AU)