Deep learning for air pollutant forecasting: opportunities, challenges, and future directions
Authors:
Open Access
- 30 September 2025
- journal article
- review article
- Published by Springer Nature in Frontiers of Environmental Science & Engineering
- Vol. 19 (12) , 1-15
Abstract
Deep learning methods are increasingly employed to forecast air quality from an ever-increasing stream of data and algorithms. However, the efficacy of current approaches may be questionable when evaluated not solely in terms of greater forecasting fidelity, but also concerning the decision-making process in pollution early warning. Here, rather than amending classical machine learning algorithms, we argue that now is the time to push the frontiers of air pollutant forecasting beyond state-of-the-art approaches. This can be achieved through near real-time assimilation of multi-scale observations for laying the foundation of training data, enhanced attribution methods for impending heavy pollution, diagnostics for forecasting uncertainty, and advanced climate-chemistry emulators for improving seasonal forecasting. To harness this potential, it is essential to address several key challenges in deep learning methods, particularly generalization ability in extreme events, physics-informed interpretable approaches, and the mitigation technology of cumulative errors in multi-process coupled systems. This interdisciplinary endeavor will remain a central pursuit in the quest to anticipate and manage environmental change.Keywords
This publication has 98 references indexed in Scilit:
- Modeling the formation of aerosols and their interactions with weather and climate: critical review and future perspectivesFrontiers of Environmental Science & Engineering, 2025
- Nonlinear relationship between air pollution and precursor emissions in Qingdao, eastern ChinaFrontiers of Environmental Science & Engineering, 2024
- Needs and challenges of optical atmospheric monitoring on the background of carbon neutrality in ChinaFrontiers of Environmental Science & Engineering, 2024
- Modeling air quality PM2.5 forecasting using deep sparse attention-based transformer networksInternational Journal of Environmental Science and Technology, 2023
- Effect of urban morphology on air pollution distribution in high-density urban blocks based on mobile monitoring and machine learningBuilding and Environment, 2022
- Estimation of high spatial resolution ground-level ozone concentrations based on Landsat 8 TIR bands with deep forest modelChemosphere, 2022
- High temporal and spatial resolution PM2.5 dataset acquisition and pollution assessment based on FY-4A TOAR data and deep forest model in ChinaAtmospheric Research, 2022
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Improved pollution forecasting hybrid algorithms based on the ensemble methodApplied Mathematical Modelling, 2019
- Introduction to the special issue on “25 years of ensemble forecasting”Quarterly Journal of the Royal Meteorological Society, 2018