An Investigation of Federated Learning for Air Quality Forecasting and Monitoring

Yuhao Wu

doi:10.54097/magrka10

Authors

Yuhao Wu Department of Statistic and Data Science, Capital University of Economics and business, Beijing, China

DOI:

https://doi.org/10.54097/magrka10

Keywords:

Federated learning, Air quality forecasting, Air quality monitoring, Spatio-temporal graph neural networks.

Abstract

Air quality, as a global issue, impacts people’s health and daily life. It requires precise prediction and monitoring for sustainable urban management. Conventional centralized air quality prediction methods are limited by data privacy, high communication costs, and low scalability in distributed environments. Federated learning offers a solution that collaboratively trains global models without sharing raw data. The passage conducted a comprehensive literature analysis to categorize FL applications in air quality research into four technical streams: Probabilistic Graphical Models (Federated Bayesian Networks) for causal inference; Time-series Deep Learning (integrating LSTM/CNN with FedAvg/FedProx) for temporal pattern extraction; Spatio-temporal Graph Neural Networks (GC-LSTM) for capturing complex spatial dependencies; and Multi-model Ensemble with Transfer Learning for heterogeneous client adaptation. Nevertheless, there are significant gaps that remain in terms of model interpretability and the ability to generalize across climate variations. All in all, this article provides a relatively comprehensive overview of the application of federated learning in air quality forecasting and monitoring. It will assist researchers in advancing this field in the future.

References

[1] Zhang XX, et al. Aeolian dust in Central Asia: Spatial distribution and temporal variability. Atmos Environ. 2020;238:117734.

[2] McMahan B, et al. Communication-efficient learning of deep networks from decentralized data. In: Proc Artif Intell Stat (AISTATS); 2017.

[3] Li T, et al. Federated optimization in heterogeneous networks. Proc Mach Learn Syst. 2020;2:429–450.

[4] Nguyen DV, Zettsu K. Spatially-distributed federated learning of convolutional recurrent neural networks for air pollution prediction. In: Proc IEEE Int Conf Big Data; 2021.

[5] Zhou X, et al. Federated conditional generative adversarial nets imputation method for air quality missing data. Knowl Based Syst. 2021;228:107261.

[6] Ramadan MNA, Ali MAH, Alkhedher M. Development of a federated learning-enabled IoT framework for indoor air quality and HVAC optimization in healthcare buildings. J Build Eng. 2025;107:112758.

[7] Bian C, Huang G. Federated Bayesian network approach for cross-regional air pollution classification: A case study of the Beijing–Tianjin–Hebei region. Environ Monit Assess. 2024;196(7):668.

[8] Ramadan MNA, et al. SecureIoT-FL: A federated learning framework for privacy-preserving real-time environmental monitoring in industrial IoT applications. Alex Eng J. 2025;114:681–701.

[9] Roy S, Kandhoul N, Dhurandher SK. Generative adversarial network-based imputation and personalized federated learning with convolutional neural network-long short-term memory for air quality index prediction. Eng Appl Artif Intell. 2025;158:111300.

[10] Liu Y, et al. Federated learning in the sky: Aerial-ground air quality sensing framework with UAV swarms. IEEE Internet Things J. 2020;8(12):9827–9837.

[11] Le DD, et al. Insights into multi-model federated learning: An advanced approach for air quality index forecasting. Algorithms. 2022;15(11):434.

[12] Swetha G, Datla R, Mohan CK. Federated learning to categorize air quality using satellite images. IEICE Proc Ser. 2024;81:57–60.