TimeGAN-based generative modelling for air quality index forecasting and missing data imputation in Indian cities
Open Access
- 14 August 2026
- journal article
- research article
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1) , 799
Abstract
Air pollution remains a pressing public-health issue in Indian metropolitan cities, where elevated levels of particulate matter (PM2.5 and PM10), carbon monoxide, nitrogen dioxide, sulphur dioxide and ozone regularly exceed safe thresholds. Air Quality Index offers a convenient single-number summary of these hazards, building accurate forecasts with this data not straightforward. The monitoring stations produce records riddled with missing values, high-pollution events are rare enough to create severe class imbalance, and the temporal dependencies. This paper proposes a framework built around a Time-series Generative Adversarial Network (TimeGAN) that simultaneously tackles AQI forecasting, missing-data imputation, and synthetic scenario generation. The pipeline combines Synthetic Minority Oversampling (SMOTE) for class balancing with TimeGAN's adversarial and supervised objectives, and is trained on hourly observations from the Central Pollution Control Board covering six major Indian cities over 2018–2023. Forecasting is framed primarily as a regression problem, while predicted AQI values are additionally mapped to discrete categories (Good, Moderate, Poor, Severe) for a secondary classification evaluation. The proposed model is compared against benchmark ARIMA, Support Vector Machine, Random Forest, and Long Short-Term Memory. The experimental results revealed that the proposed model reported better performance on both regression metrics (MAE, MSE, R 2 ) and classification metrics (Accuracy, Precision, Recall, F1-score). It achieved R 2 = 0.94, MAE = 3.72, and MSE = 4.25 alongside a secondary classification accuracy of 95.8% and F1-score of 0.946. A paired Wilcoxon signed-rank test confirms statistically significant improvement over LSTM ( p < 0.01), and fivefold cross-validation yields R 2 = 0.93 ± 0.012, indicating stable generalisation across temporal partitions.Keywords
Funding Information
- Manipal University Jaipur
This publication has 16 references indexed in Scilit:
- Geochemical speciation, pollution assessment, and source identification of heavy metals in sediment cores of the Cau River basin, Hai Duong province, VietnamEnvironmental Science: Advances, 2025
- Air quality prediction by machine learning models: A predictive study on the indian coastal city of VisakhapatnamChemosphere, 2023
- Exploding the myths: An introduction to artificial neural networks for prediction and forecastingEnvironmental Modelling & Software, 2023
- Coupling ATR-FTIR spectroscopy with multivariate analysis for polymers manufacturing and control of polymers’ molecular weightDigital Chemical Engineering, 2023
- Predicting cyclone landfall using mutual information and dilated recurrent neural networkEnvironmental Data Science, 2022
- Remote sensing estimation of surface PM2.5 concentrations using a deep learning model improved by data augmentation and a particle size constraintAtmospheric Environment, 2022
- Passive sampler derived polychlorinated biphenyls (PCBs) in indoor and outdoor air in Bursa, Turkey: Levels and an assessment of human exposure via inhalationAtmospheric Pollution Research, 2020
- Spatial variation of sources and photochemistry of formaldehyde in Wuhan, Central ChinaAtmospheric Environment, 2019
- Random ForestsMachine Learning, 2001
- Learning representations by back-propagating errorsNature, 1986