DOI QR코드

DOI QR Code

머신러닝을 활용한 내부 발생 요인 기반의 미세먼지 예측에 관한 연구

A Study on Fine Dust Prediction Based on Internal Factors Using Machine Learning

  • 투고 : 2023.10.28
  • 심사 : 2023.12.30
  • 발행 : 2023.12.31

초록

This study aims to enhance the accuracy of fine dust predictions by analyzing various factors within the local environment, in addition to atmospheric conditions. In the atmospheric environment, meteorological and air pollution data were utilized, and additional factors contributing to fine dust generation within the region, such as traffic volume and electricity transaction data, were sequentially incorporated for analysis. XGBoost, Random Forest, and ANN (Artificial Neural Network) were employed for the analysis. As variables were added, all algorithms demonstrated improved performance. Particularly noteworthy was the Artificial Neural Network, which, when using atmospheric conditions as a variable, resulted in an MAE of 6.25. Upon the addition of traffic volume, the MAE decreased to 5.49, and further inclusion of power transaction data led to a notable improvement, resulting in an MAE of 4.61. This research provides valuable insights for proactive measures against air pollution by predicting future fine dust levels.

키워드

참고문헌

  1. BBC NEWS Korea. (2018, March 26). Retrieved December 10, 2023, from https://www.bbc.com/korean/news-43524873
  2. Han, J. M. & Jo, G. H. & Kim, J. G. (2017), Verify a Causal Relationship between Fine Dust and Air Condition-Weather Data in Selected Area by Contamination Factors, Korean Big Data Society, 2(1), pp. 17-26.
  3. Jang, Y. W. & Lee, K. W. & LEE, T. H. & GHIM, Y. S. & Kim, J. H. & Kim, B. G. (2018), The Study of Air Quality in Sao Paulo, Brazil, Hankuk University of Foreign Studies Center for Latin American Studies, 37(2), pp. 137-158.
  4. Kim, H. G. (2018), Estimating Changes of Causative Factors' Influences: Focusing on Diesel, Korean Society of Data Science, 20(2), pp. 747-757.
  5. Kim, H. L. & Moon, T. H. (2021), Machine learning-based Fine Dust Prediction Model using Meteorological data and Fine Dust data, Journal of Korean Geographic Information Society, 24(1), pp. 99-111.
  6. Kim, H. M. & Lee, S. W. & Kim, I. G. & Lee, D. G. & Yoo, S. H. (2020), Measuring the Economic Value of Improving Observation Systems Use and Prediction Model Accuracy_Conjoint Analysis, Korean Journal of Innovation, 15(1), pp. 301-320.
  7. Kim, S. Y. (2023), A study on PM10 forecasting model using machine learning, Korea Data Information Science Society, 34(5), pp. 763-773. https://doi.org/10.7465/jkdi.2023.34.5.763
  8. Lee, S. B. (2022), An Introduction to Machine Learning Focusing on Predictive Models Using Supervised Learning, Ewha Womans University Institute of Education Science, 53(3) pp. 1-43.
  9. Lee, T. H. & Jeon, M. J. (2018), Prediction of Seoul House Price Index Using Deep Learning Algorithms with Multivariate Time Series Data, Journal of Housing and Urban Research, 8(2), pp. 33-56.
  10. Park, S. A. & Shin, H. J. (2017), Analysis of the Factors Influencing PM2.5 in Korea: Focusing on Seasonal Factors, Korea Institute of Environmental Policy and Evaluation, 25(1), pp. 227-248.
  11. Park, Y. S. & Park, J. H. & Kang, S. Y. & Lee, S. H. & Son, J. S. & Yoo, C. & Lee, S. B. & Kim, J. S. (2020), Analysis of High PM10, PM2.5 Concentration in Kangwon, Proceedings of the Korean Society for Atmospheric Environment Annual Conference, pp. 146-146.
  12. Specht, D. F. (1991), A General Regression Neural Network, IEEE Trans. on Neural Networks, 2(6), pp. 568-576. https://doi.org/10.1109/72.97934
  13. Sung, S. H. & Kim, S. J. & Ryu, M. H. (2020), A Comparative Study on the Performance of Machine Learning Models for the Prediction of Fine Dust: Focusing on Domestic and Overseas Factors, Korean Society for Innovation, 15(4), pp. 339-357.