Air Quality Prediction Using LOESS-ARIMA and Multi-Scale CNN-BiLSTM with Residual-Gated Attention

TL;DR

The paper tackles AQI forecasting in Indian megacities by combining LOESS-based decomposition with ARIMA for structured trend/seasonal components and a Multi-Scale CNN–BiLSTM featuring a residual-gated attention mechanism to capture volatile residuals. Hyperparameters are optimized using UAMMO, a unified framework that blends five metaheuristics. On CPCB data from 2021–2023 across PM$_{2.5}$, O$_3$, CO, and NOx, the proposed method consistently outperforms statistical, ML, DL, and other hybrid baselines, achieving $R^2 > 0.94$ and lower MSE/MAE. The approach demonstrates robustness to sudden pollution events and offers a practical, interpretable tool for urban air quality management and policy support. $

Abstract

Air pollution remains a critical environmental and public health concern in Indian megacities such as Delhi, Kolkata, and Mumbai, where sudden spikes in pollutant levels challenge timely intervention. Accurate Air Quality Index (AQI) forecasting is difficult due to the coexistence of linear trends, seasonal variations, and volatile nonlinear patterns. This paper proposes a hybrid forecasting framework that integrates LOESS decomposition, ARIMA modeling, and a multi-scale CNN-BiLSTM network with a residual-gated attention mechanism. The LOESS step separates the AQI series into trend, seasonal, and residual components, with ARIMA modeling the smooth components and the proposed deep learning module capturing multi-scale volatility in the residuals. Model hyperparameters are tuned via the Unified Adaptive Multi-Stage Metaheuristic Optimizer (UAMMO), combining multiple optimization strategies for efficient convergence. Experiments on 2021-2023 AQI datasets from the Central Pollution Control Board show that the proposed method consistently outperforms statistical, deep learning, and hybrid baselines across PM2.5, O3, CO, and NOx in three major cities, achieving up to 5-8% lower MSE and higher R^2 scores (>0.94) for all pollutants. These results demonstrate the framework's robustness, sensitivity to sudden pollution events, and applicability to urban air quality management.

Figures (18)

• Figure 1: Proposed Pipeline
• Figure 2: Residual Forecasting Network Architecture
• Figure 3: Bidirectional LSTM
• Figure 4: Field Map Of Delhi with Station Location OpenStreetMap
• Figure 5: Field Map Of Mumbai with Station Location OpenStreetMap