Spatiotemporal Machine Learning for Detection and Prediction of Infectious Diseases

By: Atiye Sadat Hashemi, Jonas Björk, Dominik Dietler, and Mattias Ohlsson

The growing complexity and frequency of infectious disease outbreaks underscore the need for data-driven approaches to surveillance. This project explores the integration of spatiotemporal machine learning techniques for detecting and predicting disease patterns over time and across geographic regions. By leveraging diverse data sources, including epidemiological records, this research aims to develop models capable of capturing both temporal trends and spatial correlations in disease transmission.