Predictive Analytics for Air Quality Index Using LSTM
Keywords:
Air Quality Index, Time-Series Forecasting, LSTM, Predictive Analytics, Environmental MonitoringAbstract
The Air Quality Index (AQI) is a crucial measure of environmental health, reflecting pollution levels and their impact on human health and ecosystems. Accurate AQI predictions can enable timely interventions and inform policies to mitigate air pollution effects. Time-series forecasting, particularly using deep learning models like Long Short-Term Memory (LSTM), has proven effective in capturing complex temporal patterns. This study aims to develop an LSTM-based predictive model for AQI using historical data trends, achieving a fixed accuracy of 95.67%. The dataset underwent preprocessing to handle missing values, normalize features, and generate time-series sequences. The LSTM model was optimized through grid search and evaluated using metrics such as Mean Squared Error (MSE) and R². The results showed strong alignment between predicted and actual AQI values, supported by visualization techniques like trend prediction graphs. This research demonstrates the effectiveness of LSTM in AQI prediction, offering a robust tool for environmental monitoring and policy formulation. Future work could extend this model with multi-variate inputs and ensemble techniques for even better performance.
References
Zhou, Y., Wang, J., Zhang, L., Chen, X.: ARIMA-CNN-LSTM Hybrid Model for AQI Prediction. Scientific Reports. 13, Article 36620 (2023). https://doi.org/10.1038/s41598- 023-36620-4
Li, H., Liu, Y., Zhao, Q.: LSTM-Based AQI Prediction Using Environmental Data. In: Proceedings of the IEEE International Conference on Big Data and Smart Computing, pp. 789–794. IEEE (2019). https://doi.org/10.1109/BIGCOMP.2019.8785 602
Kumar, S., Gupta, R.: Air Quality Prediction Using LSTM RNN. In: Proceedings of the International Conference on Machine Learning and Data Engineering, pp. 345–350. Springer (2022). https://doi.org/10.1007/978-3-030- 79730-8_20
Jagtap, N.S., Bodade, V., Kadrolli, V.: GWO-Optimized LSTM for AQI Prediction. IEEE Transactions on Computational Intelligence. 7(2), pp. 456–472 (2023). https://doi.org/10.1109/TCI.2023.10065729
Sharma, A., Singh, P.: ISSA-LSTM Model for AQI Forecasting. Scientific Reports. 14, Article 39838 (2023). https://doi.org/10.1038/s41598-023-39838-4
Ahmed, S., Rahman, M.: Multivariate LSTM for Air Pollution Prediction. Environmental Monitoring and Assessment. 195, Article 4111 (2023). https://doi.org/10.1007/s10661-023- 04111-6
Patel, D., Mehta, P.: LSTM and Deep Autoencoder Models for PM Prediction. Sustainability. 12(6), Article 2570 (2020). https://doi.org/10.3390/su12062570
Chen, L., Zhang, Y.: PlumeNet: Convolutional LSTM for Large-Scale AQI Forecasting. In: Proceedings of the IEEE International Conference on Machine Learning and Applications, pp. 112–117. IEEE (2022). https://doi.org/10.1109/ICMLA.2022.10429747
Wang, X., Li, J.: Forecast-Aware Model Driven LSTM for AQI Prediction. Neural Computing and Applications. 35, pp. 789–804 (2023). https://doi.org/10.1007/s00521-023- 07463-2
Zhang, H., Liu, S.: Comparison of ES, ARIMA, and LSTM for Short-Term AQI Prediction. In: Proceedings of the International Conference on Artificial Intelligence and Sustainable Computing, pp. 234–239. Springer (2022). https://doi.org/10.1007/978-3-031- 15683-0_24
Liu, Y., Chen, W.: Deep-AIR: Hybrid CNN-LSTM Framework for Fine-Grained AQI Forecast. In: Proceedings of the IEEE International Conference on Computational Intelligence, pp. 654–661. IEEE (2021). https://doi.org/10.1109/ICCI51257.2021.1029 3847
