A Long Short-Term Memory (LSTM) Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea
Source abstract
Abstract
Air pollution not only damages the environment but also leads to various illnesses such as respiratory tract and cardiovascular diseases. Nowadays, estimating air pollutants concentration is becoming very important so that people can prepare themselves for the hazardous impact of air pollution beforehand. Various deterministic models have been used to forecast air pollution. In this study, along with various pollutants and meteorological parameters, we also use the concentration of the pollutants predicted by the community multiscale air quality (CMAQ) model which are strongly related to PM 2.5 concentration. After combining these parameters, we implement various machine learning models to predict the hourly forecast of PM 2.5 concentration in two big cities of South Korea and compare their results. It has been shown that Long Short Term Memory network outperforms other well-known gradient tree boosting models, recurrent, and convolutional neural networks.
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
School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea
Department of Chemical Engineering, COMSATS University Islamabad, Lahore Campus, Punjab 54000, Pakistan
Department of Computer Software Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad 44000, Pakistan
AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005, Korea
Funding
National Research Foundation of Korea · Institute of Information & communications Technology Planning & Evaluation (IITP)
References (40)
Show source-provided references
1. World Health Organization (WHO), and International Agency for Research on Cancer (2015). IARC Monographs on the Evaluation of Carcinogenic Risks to Humans, IARC.
2. World Health Organization (WHO), and International Agency for Research on Cancer (2016). IARC Outdoor Air Pollution, IARC.
3. Environmental risk factors for respiratory symptoms and childhood asthma
4. (2020, January 12). World Health Organization: Global Health Observatory (GHO) Data for Ambient Air Pollution. Available online: www.who.int/gho/phe/outdoor_air_pollution/en/.
5. Zannetti, P., Al-Ajmi, D., and Al-Rashied, S. (2007). Air pollution modeling—An Overview. Ambient Air Pollution, The Arab School for Science and Technology (ASST) and The EnviroComp Institute. Chapter 2.
6. (2020, January 12). Photochemical Modeling, Available online: www3.epa.gov/scram001/photochemicalindex.htm.
7. Random forests10.1023/A:1010933404324 ↗
8. Seal, H.L. (1968). Studies in the History of Probability and Statistics. XV: The Historical Development of the Gauss Linear Model, Yale University.
9. Support-vector networks10.1007/BF00994018 ↗
10. The use of random forests in modelling short-term air pollution effects based on traffic and meteorological conditions: A case study in Wroclaw10.1016/j.jenvman.2018.03.094 ↗
11. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
12. Qadeer, K., and Jeon, M. (2019, January 26–28). Prediction of PM10 Concentration in South Korea Using Gradient Tree Boosting Models. Proceedings of the 3rd International Conference on Vision, Image and Signal Processing (ICVISP 2019), Vancouver, BC, Canada.10.1145/3387168.3387234 ↗
13. Machine learning–XGBoost analysis of language networks to classify patients with epilepsy10.1007/s40708-017-0065-7 ↗
14. Pavlyshenko, B.M. (2016, January 23–27). Linear, machine learning and probabilistic approaches for time series analysis. Proceedings of the IEEE First International Conference on Data Stream Mining & Processing (DSMP), Lviv, Ukraine.10.1109/DSMP.2016.7583582 ↗
15. Pan, B. (2017, January 8–10). Application of XGBoost algorithm in hourly PM2.5 concentration prediction. Proceedings of the IOP Conference Series: Earth and Environmental Science (Vol. 113, No. 1, p. 012127), Harbin, China.10.1088/1755-1315/113/1/012127 ↗
16. Rencher, A.C., and Christensen, W.F. (2012). Multivariate regression. Methods of Multivariate Analysis, Wiley Series in Probability and Statistics. [3rd ed.]. Chapter 10.10.1002/9781118391686 ↗
17. Simplifying decision trees10.1016/S0020-7373(87)80053-6 ↗
18. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017, January 4–9). Lightgbm: A highly efficient gradient boosting decision tree. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
19. The Comparison of Machine-Learning Methods XGBoost and LightGBM to Predict Energy Development
20. Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks10.1016/S1364-8152(01)00077-9 ↗
21. Development of a daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model10.5194/acp-19-12935-2019 ↗
22. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
23. The importance of spatial resolutions of community multiscale air quality (CMAQ) models on health impact assessment10.1016/j.scitotenv.2018.01.228 ↗
24. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position10.1007/BF00344251 ↗
25. Jain, S., Gupta, R., and Moghe, A.A. (2018, January 28–29). Stock Price Prediction on Daily Stock Data using Deep Neural Networks. Proceedings of the 2018 International Conference on Advanced Computation and Telecommunication (ICACAT), Bhopal, India.10.1109/ICACAT.2018.8933791 ↗
26. A hybrid model based on convolutional neural networks and long short-term memory for ozone concentration prediction10.1007/s11869-018-0585-1 ↗
27. Huang, C.J., and Kuo, P.H. (2018). A deep cnn-lstm model for particulate matter (PM2.5) forecasting in smart cities. Sensors, 18.10.3390/s18072220 ↗
28. Li, S., Xie, G., Ren, J., Guo, L., Yang, Y., and Xu, X. (2020). Urban PM2.5 Concentration Prediction via Attention-Based CNN–LSTM. Appl. Sci., 10.10.3390/app10061953 ↗
29. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.10.3115/v1/D14-1179 ↗
30. Liu, B., Fu, C., Bielefield, A., and Liu, Y.Q. (2017). Forecasting of Chinese primary energy consumption in 2021 with GRU artificial neural network. Energies, 10.10.3390/en10101453 ↗
31. Jaewoong, Y. (2018). Deep Bidirectional and Unidirectional LSTM Neural Networks for Air Pollutant Concentration Prediction. [Master’s Thesis, Gwangju Institute of Science and Technology (GIST)].
32. (2018, October 20). Air Korea Website. Available online: www.airkorea.or.kr/web.
33. (2018, October 20). Korean Government Public Data Repository. Available online: www.data.go.kr.
34. Method comparisons for particulate nitrate, elemental carbon, and PM2.5 mass in seven US cities10.1080/10473289.2000.10464152 ↗
35. Indoor/outdoor relationships for organic and elemental carbon in PM2.5 at residential homes in Guangzhou, China10.4209/aaqr.2012.02.0026 ↗
36. (2018, October 20). Air Korea Lab GIST, South Korea. Available online: https://airlab.gist.ac.kr/.
37. Effects of ambient particulate matter on peak expiratory flow rates and respiratory symptoms of asthmatics during Asian dust periods in Korea10.1111/j.1440-1843.2005.00728.x ↗
38. Dropout: A simple way to prevent neural networks from overfitting
39. Prechelt, L. (1998). Early Stopping|but when?. Lecture Notes in Computer Science, Springer.10.1007/3-540-49430-8_3 ↗
40. (2019, April 23). Rmsprop: Divide the Gradient by a Running Average of Its Recent Magnitude (Online Lecture Slides 26–30). Available online: https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf.