Implementation and Validation of an Air Quality Prediction Model Based on Federated Learning

Jiaxuan Xu

doi:10.54097/7bq52c49

Authors

Jiaxuan Xu School of Economics and Management, Harbin Institute of Technology, Harbin, China

DOI:

https://doi.org/10.54097/7bq52c49

Keywords:

Federated Learning, Air Quality Prediction, FedAvg, Non-IID Data.

Abstract

Ground ozone and other air pollutants pose a great threat to the health. Because the data of different monitoring stations are scattered, it is very complicated to accurately predict the ozone level. Federated Learning (FL) allows everyone to train models together without exchanging raw data, thus protecting privacy. This paper uses FL to predict air quality, and the key point is to establish a prediction model, not to change the algorithm. This paper used UCI air quality data set (with 8,762 records, each with four attributes) to simulate the situation of five users, and the data were separated by independent identically distributed (IID) and non-independent identically distributed (Non-IID). This paper trained 50 communication rounds with a multi-layer perceptron (MLP) and Federal Average (FedAvg) method. The model of centralized training and local training is also used to compare. The experimental results show that the average absolute error (MAE) of FedAvg is 48.9 under IID data and 58.3 under Non-IID data, which is much better than the local training models (MAE 78.5 and 85.2) and close to the effect of centralized training (MAE 42.3 and 51.6). This method of federated learning adapts well to different data. This study confirms that FL is a feasible method for distributed air quality prediction.

References

[1] Jumin E, Zaini N, Ahmed AN, Abdullah S, Ismail M, Sherif M, et al. Machine learning versus linear regression modelling approach for accurate ozone concentrations prediction. Eng Appl Comput Fluid Mech. 2020;14(1):713–725.

[2] Mao W, Wang W, Jiao L, Zhao S, Liu A. Modeling air quality prediction using a deep learning approach: Method optimization and evaluation. Sustain Cities Soc. 2021;65:102567.

[3] Navares R, Aznarte JL. Predicting air quality with deep learning LSTM: Towards comprehensive models. Ecol Inform. 2020;55:101019.

[4] Zhang Z, Zhang S, Chen C, Yuan J. A systematic survey of air quality prediction based on deep learning. Alex Eng J. 2024;93:128–141.

[5] Du S, Li T, Yang Y, Horng SJ. Deep air quality forecasting using hybrid deep learning framework. IEEE Trans Knowl Data Eng. 2021;33(6):2412–2424.

[6] Carbajal-Hernández JJ, Sánchez-Fernández LP, Carrasco-Ochoa JA, Martínez-Trinidad JF. Assessment and prediction of air quality using fuzzy logic and autoregressive models. Atmos Environ. 2012;60:37–50.

[7] Zheng Y, et al. Forecasting fine-grained air quality based on big data. In: Proc 21st ACM SIGKDD Int Conf Knowl Discov Data Min; 2015. p. 2267–2276.

[8] Jin N, Zeng Y, Yan K, Ji Z. Multivariate air quality forecasting with nested long short-term memory neural network. IEEE Trans Ind Inform. 2021;17(12):8514–8522.

[9] Yi X, Zhang J, Wang Z, Li T, Zheng Y. Deep distributed fusion network for air quality prediction. In: Proc 24th ACM SIGKDD Int Conf Knowl Discov Data Min; 2018. p. 965–973.

[10] 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).

[11] Putra KT, et al. Federated compressed learning edge computing framework with ensuring data privacy for PM2.5 prediction in smart city sensing applications. Sensors. 2021;21(13):4586.

[12] Kok I, Simsek MU, Ozdemir S. A deep learning model for air quality prediction in smart cities. In: IEEE Int Conf Big Data; 2017. p. 1983–1990.

[13] Chhikara P, Tekchandani R, Kumar N, Guizani M, Hassan MM. Federated learning and autonomous UAVs for hazardous zone detection and AQI prediction in IoT environment. IEEE Internet Things J. 2021;8(20):15456–15467.

[14] Liu Y, Nie J, Li X, Ahmed SH, Lim WYB, Miao C. Federated learning in the sky: aerial-ground air quality sensing framework with UAV swarms. IEEE Internet Things J. 2021;8(12):9827–9837.

[15] Roy S, Kandhoul N, Dhurandher SK. Generative adversarial network-based imputation and personalized federated learning with CNN-LSTM for AQI prediction. Eng Appl Artif Intell. 2025;158.

[16] Yang K, Jiang T, Shi Y, Ding Z. Federated learning via over-the-air computation. IEEE Trans Wirel Commun. 2020;19(3):2022–2035.

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

[18] Li X, Peng L, Hu Y, Shao J, Chi T. Deep learning architecture for air quality predictions. Environ Sci Pollut Res. 2016;23(22):22408–22417.

[19] Wardana INK, Gardner JW, Fahmy SA. Collaborative learning at the edge for air pollution prediction. IEEE Trans Instrum Meas. 2024;73:1–12.

[20] Gilik A, Ogrenci AS, Ozmen A. Air quality prediction using CNN+LSTM-based hybrid deep learning architecture. Environ Sci Pollut Res. 2021;29(8):11920–11938.

[21] Dey S, Raina R, Mishra S, Prasad AS, Dharavath R. GreenEdge AI: sustainable federated learning for smart city air quality prediction. J Ind Inf Integr. 2026;50:101081.

[22] Chhikara P, Tekchandani R, Kumar N, Tanwar S, Rodrigues JJPC. Federated learning for AQI prediction using UAV swarm networks. In: IEEE GLOBECOM; 2021.

[23] Feng Y. Participant privacy protection and air quality prediction based on FCM, PFI, LSTM, and DBN. Results Eng. 2025;26:105496.

[24] Dey S, Pal S. Federated learning-based air quality prediction for smart cities using BGRU model. In: ACM MobiCom; 2022.

[25] Beriwal S, Ayeelyan J. Decoding pollution: a federated learning-based pollution prediction study with health ramifications using causal inferences. Electronics. 2025;14(2):350.

[26] Huang W, Wang F, Chen J, Liu J, Liu Z, Li T. A federated framework for air quality prediction with predefined graph and adaptive graph. IEEE Internet Things J. 2025;12(14):27606–27617.

[27] Song M, Zhao X, Pedrycz W. A robust federated biased learning algorithm for time series forecasting. Cluster Comput. 2025;28(4).

[28] Sery T, Shlezinger N, Cohen K, Eldar YC. Over-the-air federated learning from heterogeneous data. IEEE Trans Signal Process. 2021;69:3796–3811.