A combined CNN and LSTM model to predict PM2.5 ‎concentration in Vietnam

Authors

  • Vo Phuong-Binh * Faculty of Maths and Computer Science, Dalat University. No. 1, Phu Dong Thien Vuong St., Dalat City, ‎Lam Dong, Vietnam.

https://doi.org/10.22105/thi.v1i1.24

Abstract

    In this paper, we propose a combined deep learning model of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) to predict PM2.5 concentration in Dalat, a famous tourism city in Vietnam. CNN is utilized to extract spatial features of environmental images. The remaining component, LSTM, is designed for the training of spatial and temporal features to predict PM2.5 over a specific period. In our model, training data consists of environmental images and PM2.5 concentrations collected from lifelog on different roads in Dalat City, Vietnam. Experimental results show that the proposed combined CNN and LSTM model using both spatial and temporal features achieves superior PM2.5 concentration prediction accuracy compared to the traditional LSTM approach.

Keywords:

PM2.5 prediction, Deep learning, Convolutional neural networks, Long short-term memory

References

  1. [1] Vo, P. B., Phan, T. D., Dao, M. S., & Zettsu, K. (2019). Association model between visual feature and AQI rank using lifelog data. 2019 IEEE international conference on big data (Big Data), 4197–4200. IEEE. https://doi.org/10.1109/BigData47090.2019.9005636
  2. [2] Doherty, A. R., & Smeaton, A. F. (2010). Automatically augmenting lifelog events using pervasively generated content from millions of people. Sensors (Basel), 10(3), 1423–1446. https://doi.org/10.3390/s100301423
  3. [3] AirNow. (2024). Air quality index (AQI): Basics about the AQI. https://www.airnow.gov/aqi/aqi-basics
  4. [4] Fang, X., Li, Z., Yuan, B., & Chen, Y. (2024). Image-based PM2.5 estimation from imbalanced data distribution using prior-enhanced neural networks. IEEE sensors journal, 24(5), 4677–4693. https://doi.org/10.1109/JSEN.2023.3343080
  5. [5] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems 25(2). https://doi.org/10.1145/3065386
  6. [6] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep residual learning for image recognition. https://arxiv.org/abs/1512.03385
  7. [7] Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3), 211-252. https://doi.org/10.1007/s11263-015-0816-y
  8. [8] Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2017). Places: A 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence, 40(6), 1452-1464. https://doi.org/10.1109/TPAMI.2017.2723009
  9. [9] Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., & Zhang, L. (2018). Bottom-up and top-down attention for image captioning and visual question answering. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6077-6086). https://openaccess.thecvf.com/content_cvpr_2018/html/Anderson_Bottom-Up_and_Top-Down_CVPR_2018_paper.html
  10. [10] Khedhiri, S. (2023). A deep learning LSTM approach to predict COVD-19 deaths in North Africa. Asia pacific journal of public health, 35(1), 53-55. https://doi.org/10.1177/10105395221141590

Downloads

Published

2024-10-02

Issue

Vol. 1 No. 1 (2024): Trends in Health Informatics

Section

Articles

How to Cite

Phuong-Binh, V. (2024). A combined CNN and LSTM model to predict PM2.5 ‎concentration in Vietnam. Trends in Health Informatics, 1(1), 63-68. https://doi.org/10.22105/thi.v1i1.24