Global forecasting of aerosol optical depth through a deep learning spatiotemporal modeling
International Journal of Environmental Science and Technology, vol. 23, no. 1, article 69, 2026
← Research programme
04
Research area
Environmental forecasting
AI methods for air quality, atmospheric aerosols, greenhouse-gas concentrations, urban noise and other environmental phenomena.
Rationale
The research problem.
This application area develops spatiotemporal forecasts from monitoring networks, satellite observations, CAMS products, ERA5 meteorology and contextual variables. The goal is to represent the relevant spatial structure and temporal scale while keeping evaluation tied to the intended environmental decision.
Research questions
Questions that guide this area.
- 01
How should global and urban environmental observations be represented?
- 02
Which temporal scales matter for aerosols, gases, air quality and noise?
- 03
How can forecasts support monitoring and environmental management?
Methods, systems and sources
Concrete research elements.
- CAMS
- ERA5
- Satellite observations
- Environmental sensor networks
- Air quality
- Climate data
- Decision support
Evidence
Publications in this area.
Spatio-temporal graph neural network for inter-city air quality forecasting
International Journal of Environmental Science and Technology, vol. 23, no. 1, article 63, 2026
Noise Pollution Prediction in a Densely Populated City Using a Spatio-Temporal Deep Learning Approach
Applied Sciences, vol. 15, no. 10, article 5576, 2025
Global forecasting of carbon concentration through a deep learning spatiotemporal modeling
Journal of Environmental Management, vol. 371, article 122922, 2024