Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India
This research presents an innovative hybrid deep learning architecture, CNN-LSTM-MHA+GRU, aimed at precise hourly predictions of the Air Quality Index (AQI) utilizing dataset derived from Visakhapatnam, India (October 2022–October 2024). The framework amalgamates one-dimensional Convolutional Neural...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025023758 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849468570888568832 |
|---|---|
| author | Sreenivasulu T Mokesh Rayalu G |
| author_facet | Sreenivasulu T Mokesh Rayalu G |
| author_sort | Sreenivasulu T |
| collection | DOAJ |
| description | This research presents an innovative hybrid deep learning architecture, CNN-LSTM-MHA+GRU, aimed at precise hourly predictions of the Air Quality Index (AQI) utilizing dataset derived from Visakhapatnam, India (October 2022–October 2024). The framework amalgamates one-dimensional Convolutional Neural Networks (1D CNN) for the extraction of short-term patterns, Long Short-Term Memory (LSTM) integrated with Multi-Head Attention (MHA) to encapsulate long-term dependencies, and Gated Recurrent Unit (GRU) for the refinement of residual errors. The model, trained on a dataset comprising 14,073 records and optimized through Bayesian parameter tuning, demonstrated robust performance on the test dataset (R² = 0.9757, RMSE = 6.29, MAPE = 7.07 %). The proposed model consistently surpassed six benchmark models by an impressive margin of 6.6–15.4 % in terms of R². The application of five-fold cross-validation substantiated the model’s stability (mean R² = 0.9551 ± 0.0052). Statistical analyses, including MANOVA, ANOVA, and t-tests, uncovered seasonal pollution patterns, notably peaks during the winter and reductions during the monsoon. The model exhibited commendable generalizability when applied to the cities of Delhi and Mumbai (R² > 0.97) without necessitating retraining, and it showcased real-time applicability (0.08s/sample) even amidst high-AQI occurrences (MAPE = 4.58 % for AQI > 150). Interpretability driven by SHAP reinforces the significance of features, thereby rendering the model beneficial for the formulation of targeted emission control strategies. This framework presents a scalable, interpretable, and transferable approach for urban air quality forecasting and informed decision-making. |
| format | Article |
| id | doaj-art-2acc010c70634ae093cb19261451553e |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-2acc010c70634ae093cb19261451553e2025-08-20T03:25:49ZengElsevierResults in Engineering2590-12302025-09-012710630310.1016/j.rineng.2025.106303Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, IndiaSreenivasulu T0Mokesh Rayalu G1School of Advanced Sciences, Vellore Institute of Technology, Vellore, IndiaCorresponding author.; School of Advanced Sciences, Vellore Institute of Technology, Vellore, IndiaThis research presents an innovative hybrid deep learning architecture, CNN-LSTM-MHA+GRU, aimed at precise hourly predictions of the Air Quality Index (AQI) utilizing dataset derived from Visakhapatnam, India (October 2022–October 2024). The framework amalgamates one-dimensional Convolutional Neural Networks (1D CNN) for the extraction of short-term patterns, Long Short-Term Memory (LSTM) integrated with Multi-Head Attention (MHA) to encapsulate long-term dependencies, and Gated Recurrent Unit (GRU) for the refinement of residual errors. The model, trained on a dataset comprising 14,073 records and optimized through Bayesian parameter tuning, demonstrated robust performance on the test dataset (R² = 0.9757, RMSE = 6.29, MAPE = 7.07 %). The proposed model consistently surpassed six benchmark models by an impressive margin of 6.6–15.4 % in terms of R². The application of five-fold cross-validation substantiated the model’s stability (mean R² = 0.9551 ± 0.0052). Statistical analyses, including MANOVA, ANOVA, and t-tests, uncovered seasonal pollution patterns, notably peaks during the winter and reductions during the monsoon. The model exhibited commendable generalizability when applied to the cities of Delhi and Mumbai (R² > 0.97) without necessitating retraining, and it showcased real-time applicability (0.08s/sample) even amidst high-AQI occurrences (MAPE = 4.58 % for AQI > 150). Interpretability driven by SHAP reinforces the significance of features, thereby rendering the model beneficial for the formulation of targeted emission control strategies. This framework presents a scalable, interpretable, and transferable approach for urban air quality forecasting and informed decision-making.http://www.sciencedirect.com/science/article/pii/S2590123025023758Air Quality Index (AQI)VisakhapatnamHybrid deep learning modelPollutant dynamicsSeasonal interventions |
| spellingShingle | Sreenivasulu T Mokesh Rayalu G Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India Results in Engineering Air Quality Index (AQI) Visakhapatnam Hybrid deep learning model Pollutant dynamics Seasonal interventions |
| title | Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India |
| title_full | Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India |
| title_fullStr | Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India |
| title_full_unstemmed | Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India |
| title_short | Accurate hourly AQI prediction using temporal CNN-LSTM-MHA+GRU: A case study of seasonal variations and pollution extremes in Visakhapatnam, India |
| title_sort | accurate hourly aqi prediction using temporal cnn lstm mha gru a case study of seasonal variations and pollution extremes in visakhapatnam india |
| topic | Air Quality Index (AQI) Visakhapatnam Hybrid deep learning model Pollutant dynamics Seasonal interventions |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025023758 |
| work_keys_str_mv | AT sreenivasulut accuratehourlyaqipredictionusingtemporalcnnlstmmhagruacasestudyofseasonalvariationsandpollutionextremesinvisakhapatnamindia AT mokeshrayalug accuratehourlyaqipredictionusingtemporalcnnlstmmhagruacasestudyofseasonalvariationsandpollutionextremesinvisakhapatnamindia |