Deep Learning Based Air Quality Prediction: A Case Study for London

Abstract

Although states take various measures to prevent air pollution, air pollutants continue to exist as an important problem in the world. One air pollutant that seriously affects human health is called PM2.5 (particles smaller than 2.5 micrometers in diameter). These particles pose a serious threat to human health. For example, it can penetrate deep into the lung, irritate and erode the alveolar wall and consequently impair lung function. From this, the event PM2.5 prediction is very important. In this study, PM2.5 prediction was made using 12 models, namely, Decision Tree (DT), Extra Tree (ET), k-Nearest Neighbourhood (k-NN), Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) models. The LSTM model developed according to the results obtained achieved the best result in terms of MSE, RMSE, MAE, and R2 metrics.

Keywords

• Deep learning
• London
• PM_2.5 prediction
• Machine learning
• Air quality prediction

References

1. [1] Xing YF, Xu YH, Shi MH, The impact of PM2. 5 on the human respiratory system. J. Thorac. Dis. 2016;8(1), E69. https://doi.org/ 10.3978/j.issn.2072-1439.2016.01.19Lian YX.
2. [2] Hayes RB, Lim C, Zhang Y, Cromar K, Shao Y, Reynolds HR, et al. PM2. 5 air pollution and cause-specific cardiovascular disease mortality. Int. J. Epidemiol. 2020;49(1), 25-35.
3. [3] He K, Yang F, Ma Y, Zhang Q, Yao X, Chan CK, et al. The characteristics of PM2. 5 in Beijing, China. Atmos. Environ. 2001; 35(29), 4959-4970. https://doi.org/10.1016/S1352-2310(01)00301-6
4. [4] Ma J, Yu Z, Qu Y, Xu J, Cao Y. Application of the XGBoost machine learning method in PM2. 5 prediction: A case study of Shanghai. Aerosol Air Qual. Res. 2020; 20(1), 128-138. https://doi.org/10.4209/aaqr.2019.08.0408
5. [5] Masood A, Ahmad K. A model for particulate matter (PM2. 5) prediction for Delhi based on machine learning approaches. Procedia Comput. Sci. 2020; 167, 2101-2110. https://doi.org/10.1016/j.procs.2020.03.258
6. [6] Danesh Yazdi M, Kuang Z, Dimakopoulou K, Barratt B, Suel E, Amini H, et al. Predicting fine particulate matter (PM2. 5) in the greater London area: an ensemble approach using machine learning methods. Remote Sens. 2020; 12(6), 914. https://doi.org/10.3390/rs12060914
7. [7] Feng L, Yang T, Wang Z. Performance evaluation of photographic measurement in the machine-learning prediction of ground PM2. 5 concentrations. Atmos. Environ. 2021;262, 118623. https://doi.org/10.1016/j.atmosenv.2021.118623
8. [8] Lv L, Wei P, Li J, Hu J. Application of machine learning algorithms to improve numerical simulation prediction of PM2. 5 and chemical components. Atmos. Pollut. Res. 2021; 12(11), 101211. https://doi.org/10.1016/j.apr.2021.101211

9. [9] Enebish T, Chau K, Jadamba B, Franklin M. Predicting ambient PM2. 5 concentrations in Ulaanbaatar, Mongolia with machine learning approaches. J. Exposure Sci. Environ. Epidemiol. 2021; 31(4), 699-708. https://doi.org/10.1038/s41370-020-0257-8
10. [10] Karimian H, Li Q, Wu C, Qi Y, Mo Y, Chen G, et al. Evaluation of different machine learning approaches to forecasting PM2. 5 mass concentrations. Aerosol Air Qual. Res. 2019; 19(6), 1400-1410. https://doi.org/10.4209/aaqr.2018.12.0450
11. [11] Pak U, Ma J, Ryu U, Ryom K, Juhyok U, Pak K, et al. Deep learning-based PM2. 5 prediction considering the spatiotemporal correlations: A case study of Beijing, China. Sci. Total Environ. 2020;699, 133561. https://doi.org/10.1016/j.scitotenv.2019.07.367
12. [12] Xiao Q, Chang HH, Geng G, Liu Y. An ensemble machine-learning model to predict historical PM2. 5 concentrations in China from satellite data. Environ. Sci. Technol. 2018;52(22), 13260-13269. https://doi.org/10.1021/acs.est.8b0291
13. [13] Kleine Deters J, Zalakeviciute R, Gonzalez M, Rybarczyk Y. Modeling PM2. 5 urban pollution using machine learning and selected meteorological parameters. J. Electr. Comput. Eng. 2017: 5106045. https://doi.org/10.1155/2017/5106045
14. [14] Pollution PM2.5 data London 2019 Jan to Apr. Access time: 10 September 2022. https://www.kaggle.com/siddharthnobell/pollution-pm25-data-london-2019-jan-to-apr
15. [15] Charbuty B, Abdulazeez A. Classification based on decision tree algorithm for machine learning. J. Appl. Sci. Technol. Trends. 2021; 2(01), 20-28. https://doi.org/10.38094/jastt20165
16. [16] Brijain M, Patel R, Kushik MR, Rana K. A survey on decision tree algorithm for classification. Int. J. Eng. Dev. Res. 2014;2(1).
17. [17] Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach. Learn. 2006;63(1), 3-42. https://doi.org/10.1007/s10994-006-6226-1
18. [18] Sharaff A, Gupta H. Extra-tree classifier with metaheuristics approach for email classification. In Advances in computer communication and computational sciences. 2019. https://doi.org/189-197. 10.1007/978-981-13-6861-5_17
19. [19] Cover T, Hart P. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory, 1967;13(1), 21-27. https://doi.org/10.1109/TIT.1967.1053964
20. [20] Ali N, Neagu D, Trundle P. Evaluation of k-nearest neighbour classifier performance for heterogeneous data sets. SN Appl. Sci. 2019; 1(12), 1-15. https://doi.org/10.1007/s42452-019-1356-9
21. [21] Ertuğrul ÖF, Tağluk ME. A novel version of k nearest neighbor: Dependent nearest neighbor. Appl. Soft Comput, 2017;55,480-490. https://doi.org/10.1016/j.asoc.2017.02.020
22. [22] Vapnik VN. Statistical learning theory. Wiley;1998.
23. [23] Su X, Yan X, Tsai CL. Linear regression. Wiley Interdiscip. Rev. Comput Stat. 2012;4(3), 275-294. https://doi.org/10.1002/wics.1198
24. [24] Ho TK. Random decision forests. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, Montreal, Canada, 1995. pp. 278–282.
25. [25] Biau G, Scornet E. A random forest guided tour. Test. 2016;25(2), 197-227. https://doi.org/10.1007/s11749-016-0481-7
26. [26] Drucker H, Burges CJ, Kaufman L, Smola A, Vapnik V. Support vector regression machines. Adv. Neural Inf. Process. Syst. 1997; 9, 155-161.
27. [27] Pisner DA, Schnyer DM. Support vector machine. Mach. Learn. 2020. https://doi.org/10.1016/b978-0-12-815739-8.00006-7
28. [28] Suthaharan S. Support vector machine. Machine learning models and algorithms for big data classification, Springer, Boston, MA, 2016. pp. 207-235.
29. [29] Chen T, Guestrin C. XGBoost. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016. pp. 785–794.
30. [30] Osman AIA, Ahmed AN, Chow MF, Huang YF, El-Shafie A. Extreme gradient boosting (Xgboost) model to predict the groundwater levels in Selangor Malaysia. Ain Shams Eng. J. 2021; 12(2), 1545-1556. https://doi.org/10.1016/j.asej.2020.11.011
31. [31] Sagi O, Rokach L. Approximating XGBoost with an interpretable decision tree. Inf. Sci. 2021;572, 522-542. https://doi.org/10.1016/j.ins.2021.05.055
32. [32] Desai M, Shah M. An anatomization on breast cancer detection and diagnosis employing multi-layer perceptron neural network (MLP) and Convolutional neural network (CNN). Clin. eHealth. 2021; 4, 1-11. https://doi.org/10.1016/j.ceh.2020.11.002
33. [33] Abirami S, Chitra P. Energy-efficient edge based real-time healthcare support system. In Advances in computers. Elsevier; 2020, Vol. 117, No. 1, pp. 339-368. https://doi.org/10.1016/bs.adcom.2019.09.007
34. [34] Fukushima K. Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural Netw. 1988; 1, 119–130.
35. [35] Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J. Big Data. 2021;8(1), 1-74. https://doi.org/10.1186/s40537-021-00444-8
36. [36] Botalb A, Moinuddin M, Al-Saggaf UM, Ali SS. Contrasting convolutional neural network (CNN) with multi-layer perceptron (MLP) for big data analysis. In 2018 International conference on intelligent and advanced system (ICIAS), Kuala Lumpur, Malaysia: IEEE; 2018. pp. 1-5. https://doi.org/10.1109/ICIAS.2018.8540626
37. [37] Sutskever I, Martens J, Hinton GE. Generating text with recurrent neural networks. In ICML. 2011.
38. [38] Yu Y, Si X, Hu C, Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 2019;31(7), 1235-1270. https://doi.org/10.1162/neco_a_01199
39. [39] Yang S, Yu X, Zhou Y. Lstm and gru neural network performance comparison study: Taking yelp review dataset as an example. In 2020 International workshop on electronic communication and artificial intelligence (IWECAI). Shanghai, China: IEEE; 2020. pp. 98-101. https://doi.org/ 10.3978/10.1109/IWECAI50956.2020.00027
40. [40] Alom MZ, Taha TM, Yakopcic C, Westberg S, Sidike P, Nasrin MS, et al. A state-of-the-art survey on deep learning theory and architectures. Electron. 2019;8(3), 292. https://doi.org/10.3390/electronics8030292
41. [41] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
42. [42] Smagulova K, James AP. A survey on LSTM memristive neural network architectures and applications. Eur. Phys. J. Spec. Top. 2019;228(10), 2313-2324.