A multivariable sensor-agnostic framework for spatio-temporal air quality forecasting based on Deep Learning

Download PDF
Open Webpage

Ignacio-Iker Prado-Rujas, Antonio García Dopico, Emilio Serrano, M. Luisa Córdoba, María S. Pérez

Published: 01 Jan 2024, Last Modified: 14 May 2024Eng. Appl. Artif. Intell. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•This AI framework can be deployed for anticipating high air pollution episodes.•ST-AQF can work with a variable set of sensors and recover from sensor failures.•Careful combination of variables can improve the forecasting results.•Interpolated mesh-grids are a valuable tool for spatio-temporal forecasting.