Air Quality Index prediction using an effective hybrid deep learning model. (15th December 2022)

• Record Type: Journal Article
• Authors: Sarkar, Nairita; Gupta, Rajan; Keserwani, Pankaj Kumar; Govil, Mahesh Chandra
• Is Part Of: Environmental pollution. Volume 315(2022)
• Publication Date: 2022-12-15
• Subjects: Air quality index -- Long short term memory -- Gated recurrent unit -- Linear regression -- K-nearest neighbor -- Support vector machine; Pollution -- Periodicals; Pollution -- Environmental aspects -- Periodicals; Environmental Pollution -- Periodicals; Pollution -- Périodiques; Pollution -- Aspect de l'environnement -- Périodiques; Pollution -- Effets physiologiques -- Périodiques; Pollution; Pollution -- Environmental aspects; Periodicals; Electronic journals; 363.73
• DOI: 10.1016/j.envpol.2022.120404
• Languages: English
• ISSNs: 0269-7491

Abstract

Abstract: Environmentalism has become an intrinsic part of everyday life. One of the greatest challenge to the environment's long-term existence is the air pollution. Delhi, the capital of India, has experienced decreasing of air quality for several years. The poor air quality has a significant impact on the lives of individuals. Air Quality Index (AQI) prediction can help to its beneficiaries in taking safeguards about their health before moving to any polluted area. In this study, a variety of data forecasting approaches is evaluated to predict the AQI value for Particulate Matter (PM2.5 ) μ m at a particular area of Delhi and several error-prone strategies such as R-Squared (R 2 ), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) methods are catalogued. In the proposed approach two deep learning models like Long-Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are combined to predict the AQI of the environment. Several stand alone machine learning (ML) and deep learning (DL) models such as LSTM, Linear-Regression (LR), GRU, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are also trained on the same dataset to compare their performances with the proposed hybrid (LSTM-GRU) model and it is found that the proposed hybrid model shows supremacy in the performance with the MAE value 36.11 and R 2 value 0.84. Graphical abstract: Image 1 Highlights: AQI dataset has been designed by pre-processing data collected from the official portal of CPCB, Government of India. Permutation Feature importance technique has been evaluated for feature selection. An improved hybrid LSTM-GRU model has been proposed to predict AQI accurately. LSTM-GRU model achieves better result in terms of MAE and R 2 than the other existing approaches.