Enhancing Air Quality Prediction with an Adaptive PSO-Optimized CNN-Bi-LSTM Model
Source abstract
Abstract
Effective air quality prediction models are crucial for the timely prevention and control of air pollution. However, previous models often fail to fully consider air quality’s temporal and spatial distribution characteristics. In this study, Xi’an City is used as the study area. Data from 1 January 2019 to 31 October 2020 are used as the training set, while data from 1 November 2020 to 31 December 2020 are used as the test set. This paper proposes a multi-time and multi-site air quality prediction model for Xi’an, leveraging a deep learning network model based on APSO-CNN-Bi-LSTM. The CNN model extracts the spatial features of the input data, the Bi-LSTM model extracts the time series features, and the PSO algorithm with adaptive inertia weight (APSO) optimizes the model’s hyperparameters. The results show that the model achieves the best results in terms of MAE and RMSE. Compared to the PSO-SVR, BPTT, CNN-LSTM, and GA-ACO-BP models, the MAE improved by 9.375%, 6.667%, 2.276%, and 4.975%, while the RMSE improved by 8.371%, 8.217%, 6.327%, and 5.293%. These significant improvements highlight the model’s accuracy and its promising application prospects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Quality Monitoring and Forecasting · Air Quality and Health Impacts · Vehicle emissions and performance
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Innovation and Practice, Liaoning Technical University, Fuxin 123008, China
School of Software, Liaoning Technical University, Huludao 125105, China
References (46)
Show source-provided references
1. Air pollution and control action in Beijing10.1016/j.jclepro.2015.04.092 ↗
2. Efficient PM2.5 forecasting using geographical correlation based on integrated deep learning algorithms10.1007/s00521-021-06082-8 ↗
3. Semi-supervised air quality forecasting via self-supervised hierarchical graph neural network10.1109/TKDE.2022.3149815 ↗
4. Real-time air quality forecasting, part I: History, techniques, and current status10.1016/j.atmosenv.2012.06.031 ↗
5. Systematic Research Progress on Atmospheric PM2.5 and Health: From Exposure, Harm to Intervention
6. Recursive neural network model for analysis and forecast of PM10 and PM2.510.1016/j.apr.2016.12.014 ↗
7. Selection of key features for PM2.5 prediction using a wavelet model and RBF-LSTM10.1007/s10489-020-02031-5 ↗
8. Machine learning algorithms to forecast air quality: A survey10.1007/s10462-023-10424-4 ↗
9. An, J., Huang, M., Wang, Z., Zhang, X., Ueda, H., and Cheng, X. (2000, January 10–16). Numerical regional air quality forecast tests over the mainland of China. Proceedings of the Acid Rain 2000: Proceedings from the 6th International Conference on Acidic Deposition: Looking back to the Past and Thinking of the Future, Tsukuba, Japan. Volume III/III Conference Statement Plenary and Keynote Papers.10.1007/978-94-007-0810-5_144 ↗
10. Air quality during the 2008 Beijing Olympic games10.1016/j.atmosenv.2006.08.046 ↗
11. Characterizations of chemical oxidants in Mexico City: A regional chemical dynamical model (WRF-Chem) study10.1016/j.atmosenv.2006.10.053 ↗
12. ARIMA forecasting of ambient air pollutants (O3, NO, NO2 and CO)10.1007/s00477-009-0361-8 ↗
13. Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki10.1016/j.scitotenv.2010.12.040 ↗
14. A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain10.1016/0957-1272(93)90007-S ↗
15. Performance prediction of a ground-coupled heat pump system using artificial neural networks10.1016/j.eswa.2007.08.081 ↗
16. Evolving Differential evolution method with random forest for prediction of Air Pollution10.1016/j.procs.2018.05.094 ↗
17. Prediction of air pollution index (API) using support vector machine (SVM)10.1016/j.jece.2019.103208 ↗
18. Muhammad Adnan, R., Chen, Z., Yuan, X., Kisi, O., El-Shafie, A., Kuriqi, A., and Ikram, M. (2020). Reference evapotranspiration modeling using new heuristic methods. Entropy, 22.10.3390/e22050547 ↗
19. Daily air quality index forecasting with hybrid models: A case in China10.1016/j.envpol.2017.08.069 ↗
20. PM2.5 Air Quality Prediction Based on Image Quality Analysis
21. Septiawan, W.M., and Endah, S.N. (2018, January 30–31). Suitable recurrent neural network for air quality prediction with backpropagation through time. Proceedings of the 2018 2nd International Conference on Informatics and Computational Sciences (ICICoS), Semarang, Indonesia.10.1109/ICICOS.2018.8621720 ↗
22. Air quality prediction using CNN+ LSTM-based hybrid deep learning architecture10.1007/s11356-021-16227-w ↗
23. Research on Short-term Air Quality Prediction Based on Unequal Weight Clustering Hybrid PSO-SVR
24. Air Quality Prediction Using Hybrid Genetic Ant Colony Algorithm Optimized BP Neural Network
25. GA-BP air quality evaluation method based on fuzzy theory
26. Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering10.1016/j.eswa.2020.114513 ↗
27. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
28. Liu, Y., Wang, Z., and Zheng, B. (2019, January 6–9). Application of regularized GRU-LSTM model in stock price prediction. Proceedings of the 2019 IEEE 5th International Conference on Computer and Communications (ICCC), Chengdu, China.10.1109/ICCC47050.2019.9064035 ↗
29. A review of recurrent neural networks: LSTM cells and network architectures10.1162/neco_a_01199 ↗
30. A survey on LSTM memristive neural network architectures and applications10.1140/epjst/e2019-900046-x ↗
31. Bidirectional recurrent neural networks10.1109/78.650093 ↗
32. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM10.1016/j.chaos.2020.110212 ↗
33. Le, T., Vo, M.T., Vo, B., Hwang, E., Rho, S., and Baik, S.W. (2019). Improving electric energy consumption prediction using CNN and Bi-LSTM. Appl. Sci., 9.10.3390/app9204237 ↗
34. Li, C., Zhan, G., and Li, Z. (2018, January 19–21). News text classification based on improved Bi-LSTM-CNN. Proceedings of the 2018 9th International Conference on Information Technology in Medicine and Education (ITME), Hangzhou, China.10.1109/ITME.2018.00199 ↗
35. Jang, B., Kim, M., Harerimana, G., Kang, S.U., and Kim, J.W. (2020). Bi-LSTM model to increase accuracy in text classification: Combining Word2vec CNN and attention mechanism. Appl. Sci., 10.10.3390/app10175841 ↗
36. Particle swarm optimization10.1109/ICNN.1995.488968 ↗
37. Permanent magnet synchronous motor multiple parameter identification and temperature monitoring based on binary-modal adaptive wavelet particle swarm optimization10.3724/SP.J.1004.2013.02121 ↗
38. Performance Analysis and Parameter Selection of Particle Swarm Optimization Algorithm
39. A novel particle swarm optimization algorithm with adaptive inertia weight10.1016/j.asoc.2011.01.037 ↗
40. Qin, Z., Yu, F., Shi, Z., and Wang, Y. (2006, January 25–29). Adaptive inertia weight particle swarm optimization. Proceedings of the Artificial Intelligence and Soft Computing–ICAISC 2006: 8th International Conference, Zakopane, Poland. Proceedings 8.10.1007/11785231_48 ↗
41. A method of self-adaptive inertia weight for PSO10.1109/CSSE.2008.295 ↗
42. A novel stability-based adaptive inertia weight for particle swarm optimization10.1016/j.asoc.2015.10.004 ↗
43. Shi, Y., and Eberhart, R. (1998, January 4–9). A modified particle swarm optimizer. Proceedings of the 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No. 98TH8360), Anchorage, AK, USA.
44. Dynamic sine cosine algorithm for large-scale global optimization problems10.1016/j.eswa.2021.114950 ↗
45. Microarray data normalization and transformation10.1038/ng1032 ↗
46. Root mean square error (RMSE) or mean absolute error (MAE)