Hybrid Quantum-Classical Machine Learning for Air Quality Prediction in Indian Cities

Short-term air-quality forecasting is important for environmental monitoring and public-health planning, particularly in Indian cities affected by persistent air pollution. This study presents a next-day air-quality prediction framework for seven pollutants (PM2.5, PM10, NO2, SO2, CO, NOx, and O3) across 11 Indian cities over the period 2019–2023, using daily observations from the Central Pollution Control Board (CPCB) and meteorological data from NASA POWER. Next-day pollutant concentrations are predicted using historical pollutant measurements, lagged and rolling features, calendar variables, and meteorological covariates available at the feature date. The study documents Variational Quantum Circuit (VQC) configurations implemented using PennyLane and Qiskit, alongside a candidate quantum-feature-augmentation approach for XGBoost. Quantitative evaluation is restricted to the XGBoost model, using mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination R2 over the common chronological final-test target window spanning 28 June 2022 to 31 March 2023. For the evaluated XGBoost predictions, the reported pollutant-specific R2 values range from 0.613 to 0.864. The quantum-circuit configurations and quantum-feature-augmentation approach are presented as candidate methods whose comparative predictive performance remains to be established through evaluation using aligned final-test predictions and observed targets.