기계학습 기반의 우리나라 익일 PM10 농도 예측지도 산출 KCI

Title
기계학습 기반의 우리나라 익일 PM10 농도 예측지도 산출
Alternative Title
Machine Learning-based Prediction Maps for the Tomorrow’s PM10 Concentration in Korea
Author(s)
정예민; 조수빈; 윤유정; 김서연; 김대선; 이양원
KIOST Author(s)
Kim, Dae Sun(김대선)
Alternative Author(s)
김대선
Publication Year
2020-12
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 east of China having 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 4.907㎍/㎥, 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 used as an operative system if a fine-tuning process using a larger database is accomplished.
ISSN
1975-6151
URI
https://sciwatch.kiost.ac.kr/handle/2020.kiost/39531
Bibliographic Citation
기후연구, v.15, no.4, pp.269 - 285, 2020
Publisher
기후연구소
Keywords
PM10; Machine learning; Prediction map; 미세먼지; 기계학습; 예측지도
Type
Article
Language
Korean
Files in This Item:
There are no files associated with this item.

qrcode

Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse