The future of environmental health modeling: leveraging artificial intelligence to combat air pollution challenges

Abstract

Recent advancements in artificial intelligence (AI), particularly large-scale multimodal models, are transforming various sectors by surpassing human performance in a wide range of tasks. Although AI is increasingly applied to tackle environmental issues such as air pollution, its use in analyzing the relationship between pollution and human health remains limited. Given AI’s growing capabilities in real-time human-environment monitoring, multimodal data integration, predictive health modeling, and intelligent data processing, this perspective explores AI’s potential in advancing research on the health effects of air pollution. We emphasize the role of AI in enabling personalized risk assessments, supporting informed decision making, and uncovering previously hidden mechanisms linking the environment to health. By synthesizing current research, this article highlights how AI can accelerate scientific discovery and inform targeted public health interventions and policies, offering a paradigm shift in addressing this pressing global challenge.

Keywords

AI-driven / human health / air pollution / modeling and analysis

References

[1] Shin HH,Maquiling A,Haque L.Comparison of hospitalization and mortality associated with short-term exposure to ambient ozone and PM_2.5 in Canada.Chemosphere2021;265:128683

[2] Sejnowski TJ. ChatGPT and the future of AI: the deep language revolution. 2024. https://mitpress.mit.edu/9780262049252/chatgpt-and-the-future-of-ai/. (accessed 3 Jun 2025)

[3] Landrigan PJ.Air pollution and health.Lancet Public Health2017;2:e4-5

[4] Jiang K,Luo Z.Unclean but affordable solid fuels effectively sustained household energy equity.Nat Commun2024;15:9761

[5] Wang H,Li YF.An intelligent industrial visual monitoring and maintenance framework empowered by large-scale visual and language models.IEEE Trans Ind Cyber Phys Syst2024;2:166-75

[6] Acharya K,Song HH.A survey on symbolic knowledge distillation of large language models.IEEE Trans Artif Intell2024;5:5928-48

[7] Ferrer-Cid P,Garcia-Vidal J.Graph signal reconstruction techniques for IoT air pollution monitoring platforms.IEEE Internet Things J2022;9:25350-62

[8] Ali S,Parr B,Alam F.Low cost sensor with IoT LoRaWAN connectivity and machine learning-based calibration for air pollution monitoring.IEEE Trans Instrum Meas2021;70:1-11

[9] Wang Z,Wu F.A lightweight air quality monitoring method based on multiscale dilated convolutional neural network.IEEE Trans Ind Inf2024;20:14184-92

[10] Shi, T.; Li, P.; Yang, W.; Qi, A.; Qiao, J. Research on air quality monitoring system based on STM32 single chip microcomputer. In 2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Penang, Malaysia. Nov 22-25, 2022. IEEE; 2022. p. 1-4.

[11] Che W,Fung JCH.PRAISE-HK: a personalized real-time air quality informatics system for citizen participation in exposure and health risk management.Sustain Cities Soc2020;54:101986

[12] Ali S,Ali F,Abuhmed T.Multitask deep learning for cost-effective prediction of patient’s length of stay and readmission state using multimodal physical activity sensory data.IEEE J Biomed Health Inform2022;26:5793-804

[13] Raimondi PM,Vitale MC.A CNN adaptive model to estimate PM10 monitoring. In 2005 IEEE Conference on Emerging Technologies and Factory Automation, Catania, Italy. Sep 19-22, 2005. IEEE; 2005. p. 6 pp. -810.

[14] National Health Commission of the People’s Republic of China. https://en.nhc.gov.cn/. (accessed 3 Jun 2025)

[15] Kavathekar V,Chettri SK.Assessment and prediction of urban pollutants and its influence on human health using deep learning algorithm. In 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), Pune, India. Apr 05-07, 2024. IEEE; 2024. p. 1-7.

[16] Nguyen-Tan T.Lightweight model using graph neural networks for air quality impact assessment on human health. In 2022 RIVF International Conference on Computing and Communication Technologies (RIVF), Ho Chi Minh City, Vietnam. Dec 20-22, 2022. IEEE; 2022. p. 1-6.

[17] Pandey G,Shikhola T.Improving PM 2.5 prediction accuracy with a hybrid EEMD-CNN-BiLSTM approach. In 2024 11th International Conference on Advances in Computing and Communications (ICACC), Kochi, India. Nov 06-08, 2024. IEEE; 2024. p. 1-6.

[18] Wang D,Zhang Q.Winter brown carbon over six of China’s megacities: lightabsorption, molecularcharacterization, and improved source apportionment revealed by multilayer perceptron neural network.Atmos Chem Phys2022;22:14893-904