기계학습 기반의 우리나라 익일 PM10 농도 예측지도 산출
Machine Learning-based Prediction Maps for the Tomorrow’s PM10 Concentration in Korea
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Because of the population growth and industrialization in recent decades, the air quality over the world has been worsened with the increase of PM10 concentration. Korea is located near the eastern part of China which has many industrial complexes, so the consideration of China’s air quality is necessary for the PM10 prediction in Korea. This paper examines a machine learning-based modeling of the prediction of tomorrow’s PM10 concentration in the form of a gridded map using the AirKorea observations, Chinese cities’ air quality index, and NWP (numerical weather prediction) model data. A blind test using 23,048 cases in 2019 produced a correlation coefficient of 0.973 and an MAE (mean absolute error) of 4.097㎍/㎥, which is high accuracy due to the appropriate selection of input variables and the optimization of the machine learning model. Also, the prediction model showed stable predictability irrespective of the season and the level of PM10. It is expected that the proposed model can be applied to an operative system if a fine-tuning process using a larger database is accomplished.
Abstract
Because of the population growth and industrialization in recent decades, the air quality over the world has been worsened with the increase of PM10 concentration. Korea is located near the eastern part of China which has many industrial complexes, so the consideration of China’s air quality is necessary for the PM10 prediction in Korea. This paper examines a machine learning-based modeling of the prediction of tomorrow’s PM10 concentration in the form of a gridded map using the AirKorea observations, Chinese cities’ air quality index, and NWP (numerical weather prediction) model data. A blind test using 23,048 cases in 2019 produced a correlation coefficient of 0.973 and an MAE (mean absolute error) of 4.097㎍/㎥, which is high accuracy due to the appropriate selection of input variables and the optimization of the machine learning model. Also, the prediction model showed stable predictability irrespective of the season and the level of PM10. It is expected that the proposed model can be applied to an operative system if a fine-tuning process using a larger database is accomplished.
참고문헌 (29)
- Gholamreza Asadollahfardi, "Predicting PM2.5 Concentrations Using Artificial Neural Networks and Markov Chain, a Case Study Karaj City", Asian Journal of Atmospheric Environment, 10(2), pp.67~79 (2016), 한국대기환경학회[DOI]
- Belgiu, M., "Random forest in remote sensing : a review of applications and future directions", ISPRS Journal of Photogrammetry and Remote Sensing, 114, pp.24~31 (2016)
- Berrocal, V. J., "A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2. 5 concentration", Atmospheric Environment, 222, pp.117130~ (2020)
- 차진욱, "SPSS를 이용한 대기질과 기상인자와의 미세먼지 상관관계 분석", 한국정보통신학회논문지, 22(5), pp.722~727 (2018), 한국정보통신학회[DOI]
- 조경학, "심층 신경망을 이용한 대기질 예측", 한국대기환경학회지, 35(2), pp.214~225 (2019), 한국대기환경학회[DOI]
- 조경우, "미세먼지 예측을 위한 기계 학습 알고리즘의 적합성 평가", 한국정보통신학회논문지, 23(1), pp.20~26 (2019), 한국정보통신학회[DOI]
- 조경우, "PM10 예보 정확도 향상을 위한 Deep Neural Network 기반 농도별 분리 예측 모델", 한국정보통신학회논문지, 24(1), pp.8~14 (2020), 한국정보통신학회[DOI]
- 최종규, "미세먼지의 질병에 미치는 유해성", 생명과학회지, 30(2), pp.191~201 (2020), 한국생명과학회[DOI]
- Choubin, B., "Spatial hazard assessment of the PM10using machine learning models, in Barcelona, Spain", Science of the Total Environment, 701, pp.134474~ (2020)
- Cressie, N., "Fitting variogram models by weighted least squares", Journal of the International Association for Mathematical Geology, 17(5), pp.563~586 (1985)
- Feng, R., "Recurrent neural network and random forest for analysis and accurate forecast of atmospheric pollutants : a case study in Hangzhou, China", Journal of Cleaner Production, 231, pp.1005~1015 (2019)
- Gupta, P., "Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: 2. a neural network approach", Journal of Geophysical Research, 114, pp.D20205~ (2009)
- Jacob, D. J., "Effect of climate change on air quality", Atmospheric Environment, 43(1), pp.51~63 (2009)
- 정옥진, "WRF-Chem 모델을 이용한 2010년 한반도의 황사 예측에 관한 연구", 한국지구과학회지, 36(1), pp.90~108 (2015), 한국지구과학회
- Yemin Jeong, "Prediction of Daily PM10 Concentration for Air Korea Stations Using Artificial Intelligence with LDAPS Weather Data, MODIS AOD, and Chinese Air Quality Data", 대한원격탐사학회지, 36(4), pp.573~586 (2020), 대한원격탐사학회[DOI]
- Kim, S. B., "Dust model intercomparison between ADAM and CFORS", Dust for Asian dust case in 2007(March 28-April 3), 2011, pp.7A, 25~28
- Kim, Y. P., "Air pollution in Seoul caused by aerosols", Journal of Korean Society for Atmospheric Environment, 22(5), pp.535~553 (2006)
- 권준현, "분위수 부스팅을 이용한 미세먼지 농도 예측", 응용통계연구, 28(1), pp.83~92 (2015), 한국통계학회
- 이득우, "시계열 데이터와 랜덤 포레스트를 활용한 시간당 초미세먼지 농도 예측", 정보처리학회 논문지, 9(4), pp.129~136 (2020), 한국정보처리학회[DOI]
- Li, X., "Predicting ground-level PM2. 5 concentrations in the Beijing-Tianjin-Hebei region : a hybrid remote sensing and machine learning approach", Environmental Pollution, 249, pp.735~749 (2019)
- 문윤섭, "황사 발생 기간 동안 WRF-Chem 모델을 이용한 미세먼지 예측과 관련 기상장에 대한 민감도 분석", 한국지구과학회지, 35(1), pp.1~18 (2014), 한국지구과학회
- Nguyen, D. A., "Combination of data‑driven models and interpolation technique to develop of PM10 map for Hanoi, Vietnam", Scientific Reports, 10, pp.19268~ (2020)
- 박진수, "서울지역 미세먼지의 화학적 구성 특성에 관한 연구", 한국도시환경학회지, 10(3), pp.293~303 (2010), 한국도시환경학회
- 박순애, "한국의 초미세먼지(PM2.5)의 영향요인 분석 : 풍향을 고려한 계절성 원인을 중심으로", 환경정책, 25(1), pp.227~248 (2017), 한국환경정책학회[DOI]
- Saide, P. E., "Forecasting urban PM10and PM2. 5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF-Chem CO tracer model", Atmospheric Environment, 45(16), pp.2769~2780 (2011)
- 손건태, "CMAQ 예측치를 이용한 서울지역 PM10 농도 예측모형", Journal of The Korean Data Analysis Society, 18(6), pp.3001~3009 (2016), 한국자료분석학회
- Stafoggia, M., "Estimation of daily PM10and PM2. 5 concentrations in Italy, 2013-2015, using a spatiotemporal land-use random-forest model", Environment International, 124, pp.170~179 (2019)
- Woo, K. S., "Sensitivity analysis of ordinary Kriging interpolation according to different variogram models", The Proceeding of the Korean Institute of Illuminating and Electrical Installation Engineers, 33(3), pp.32~36 (2008)
- Yang, Y. H., "Changes in air pollutant concentrations due to climate change and the health effect of exposure to particulate matter", Health and Welfare Policy Forum, 269, pp.20~31 (2019)