Journal of Cadastre & Land InformatiX (지적과 국토정보)

LX Spatial Information Research Institute (한국국토정보공사 공간정보연구원)
권호 표지
DOI QR코드

DOI QR Code

Particulate Matter Rating Map based on Machine Learning with Adaboost Algorithm

기계학습 Adaboost에 기초한 미세먼지 등급 지도

  • 정종철 (남서울대학교 드론공간정보공학과)
  • Received : 2021.09.24
  • Accepted : 2021.11.25
  • Published : 2021.12.10
Download PDF
⟨ Previous Next ⟩

Abstract

Fine dust is a substance that greatly affects human health, and various studies have been conducted in this regard. Due to the human influence of particulate matter, various studies are being conducted to predict particulate matter grade using past data measured in the monitoring network of Seoul city. In this paper, predictive model have focused on particulate matter concentration in May, 2019, Seoul. The air pollutant variables were used to training such as SO2, CO, NO2, O3. The predictive model based on Adaboost, and training model was dividing PM10 and PM2.5. As a result of the prediction performance comparison through confusion matrix, the Adaboost model was more conformable for predicting the particulate matter concentration grade. Although air pollutant variables have a higher correlation with PM2.5, training model need to train a lot of data and to use additional variables such as traffic volume to predict more effective PM10 and PM2.5 distribution grade.

미세먼지는 사람의 건강에 많은 영향을 미치는 물질로서 이와 관련하여 다양한 연구가 이루어지고 있다. 미세먼지의 인체 영향으로 인해 서울시 모니터링 네트워크에서 측정된 과거 데이터를 활용하여 미세먼지를 예측하려는 다양한 연구가 진행되고 있다. 본 연구는 2019년 5월 서울시의 미세먼지를 중점으로 진행하였으며, 학습에 사용한 변수는 SO2, CO, NO2, O3와 같은 대기오염물질 데이터를 활용하였다. 예측모델은 Adaboost에 기반하여 구축하였고, 훈련모델은 PM10과 PM2.5로 구분하였다. 에러 메트릭스를 통한 예측모델의 정확도 평가 결과로 Adaboost가 시도되었다. 대기오염물질은 초미세먼지와 더 높은 상관성을 보이는 것으로 나타났지만, 보다 효과적인 분포등급을 제시하기 위해서는 많은 양의 데이터를 학습하고, PM10과 PM2.5의 공간분포 등급을 효과적으로 예측하기 위해서 교통량 등의 추가적인 변수를 활용할 필요성이 있다고 판단된다.

Keywords

Acknowledgement

이 논문은 2021년도 남서울대학교 학술연구비 지원에 의해 연구되었음.

References

  1. Ministry of Environment. 2020. Environmental Statistics Yearbook.
  2. Kang MS et al. 2016. Analysis of the correlation between PM10 concentration characteristics and emissions in major metropolitan cities on the Korean Peninsula, Korean Society of Environmental Sciences. 25(8):1065-1076.
  3. Kim YK. 2019. Prediction of Citizens' emotions on home mortgage rates using machine learning algorithms. Journal of cadastre & land InfomatiX. 49(1): 65-84.
  4. Kim WS. 2014. Seoul Metropolitan Government's ultra-fine dust (PM2.5) management plan, Seoul Institute. 2014-182.
  5. Sung SY . 2019. The status of temporal and spatial distribution of fine dust concentrations and the potential influencing factors are reviewed. National Research Institute of Human Settlements. WP 19-04.
  6. Yoo JH. 2011. The redundancy analysis of the air pollution monitoring station in Seoul. Graduate School thesis of Seokyung University.
  7. Lee GH. 2020. Design and analysis of a model for predicting the risk level of fine dust using a complex neural network structure. Graduate degree thesis of Hanyang University.
  8. Lee SB.2019. Research trends on the effects of fine dust on the human body. BRIC View 2019-T26.
  9. Jung JC. 2014. Seoul PM10 Spatial Distribution Analysis and Time Series Changes, Journal of the Korean Geographic Information Society. 17(1):61-69. https://doi.org/10.11108/kagis.2014.17.1.061
  10. Jung JC. 2017. Spatial information application case for appropriate location assessment of PM10 observation network in Seoul city. Journal of cadastre & land InfomatiX. 47(2): 175-184.
  11. Jung JC. 2019. Selection of new particulate matter monitoring stations using Kernel analysis - Elementary schools, Seoul, Korea. Journal of cadastre & land InfomatiX. 47(2): 175-184.
  12. Jo KW. 2019. Evaluation of the suitability of machine learning algorithms for predicting fine dust. Paper of the Korean Society of Information and Communication. 23(1):20-26.
  13. Choi IJ et al.2016.Evaluation of Air Pollution Measurement Network in the Seoul metropolitan area using multivariate analysis method. Korean Society of Environmental Sciences. 25(5):673-681.
  14. Rochelle Schneider dos Santos et al. 2020. A satellite-based spatio-temporal machine learning model to reconstruct daily PM2.5 concentrations across Great Britain, medRxiv 2020.07.19.20157396.
  15. Jan Kleine Deters et al. 2017. Modeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parameters, Journal of Electrical and Computer Engineering, Volume 2017, Article ID 5106045.
  16. Hamed Karimian et al. 2019, Evaluation of Different Machine Learning Approaches to Forecasting PM2.5 Mass Concentrations. Aerosol and Air Quality Research, 19: 1400-1410. https://doi.org/10.4209/aaqr.2018.12.0450
  17. Guang Yang et al. 2020, A Hybrid Deep Learning Model to Forecast Particulate Matter Concentration Levels in Seoul, South Korea, Atomsphere, 11, 348; doi:10.3390/atmos11040348.
  18. Lary D.J. et al. 2015, Using Machine Learning to Estimate Global PM2.5 for Environmental Health Studies. Environmental Health Insights 2015.9(S1):41-52.