메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
정하윤 (강원대학교) 곽경환 (강원대학교)
저널정보
강원대학교 환경연구소 Journal of the Environment Journal of the Environment Vol.15 No.1
발행연도
2022.12
수록면
41 - 48 (8page)

이용수

DBpia Top 10%동일한 주제분류 기준으로
최근 2년간 이용수 순으로 정렬했을 때
해당 논문이 위치하는 상위 비율을 의미합니다.
표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Machine learning, which has been recently used to predict the concentration of fine particulate matter (PM<SUB>2.5</SUB>), can learn a large amount of data and perform classification or regression analysis. Among well-known machine learning algorithms, random forest and XGBoost have less prediction errors and do not have over-fitting problem. It is possible to check which variables have a great influence on the learning process by calculating the importance index. Because it is difficult to understand the classification and prediction process due to the characteristics of machine learning technology, it is necessary to select an appropriate set of input variables suitable for characteristics of the target variable (e.g., PM<SUB>2.5</SUB>). The PM<SUB>2.5</SUB> concentration prediction model developed based on random forest and XGBoost reported in previous domestic and international studies showed similar or better prediction performance compared with other prediction techniques. There were important input variables related to the occurrence factors of PM<SUB>2.5</SUB><SUB></SUB> or high concentration cases such as AOD (aerosol optical depth), PM<SUB>10</SUB>, relative humidity, and maximum wind speed. In particular, in domestic studies which include the influence of upwind countries, the input variables related to the upwind countries have a great influence on the model performance. The best model for predicting PM<SUB>2.5</SUB> concentration depends on the type, period, and dataset of the input variable, so an algorithm suitable for the data should be used through testing experiments. To select an appropriate input variables, we need to check and compare the prediction accuracy of various sets of input variables, as documented by previous studies.

목차

Abstract
1. 서론
2. 랜덤 포레스트와 XGBooSt
3. 해외 연구 사례
4. 국내 연구 사례
5. 결론 및 유의사항
참고문헌

참고문헌 (0)

참고문헌 신청

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2023-539-000368049