Stacking ensemble을 활용한 서울의 봄철 지면 온도 예측
Prediction of Spring Land Surface Temperature in Seoul using Stacking Ensemble
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Land surface temperature is a crucial variable for monitoring physical, biological, and chemical processes within the climate system. Specifically, spring land surface temperature plays a significant role in bridging the atmospheric circulation between winter and summer. It influences not only summer land surface temperature but also precipitation patterns and drought conditions. The aim of this study is to forecast spring land surface temperature by employing multiple machine learning models. The data used in this study was collected from the Automated Synoptic Observing System (ASOS) in Seoul, covering the period from 2018 to 2022, at hourly intervals. The input variables include temperature, wind speed, humidity, dew point temperature, sunshine duration, and solar radiation. In this study, we utilized both individual and ensemble models, and we further proposed a stacking ensemble method using a multilayer perceptron as the meta learner. The results indicated that most machine learning models exhibited under-dispersion. Notably, the stacking model demonstrated superior predictive performance in both time series cross-validation and the testing set. These findings suggested that the stacking model produces stable and accurate predictions by amalgamating the predicted values of base learners.
Abstract
Land surface temperature is a crucial variable for monitoring physical, biological, and chemical processes within the climate system. Specifically, spring land surface temperature plays a significant role in bridging the atmospheric circulation between winter and summer. It influences not only summer land surface temperature but also precipitation patterns and drought conditions. The aim of this study is to forecast spring land surface temperature by employing multiple machine learning models. The data used in this study was collected from the Automated Synoptic Observing System (ASOS) in Seoul, covering the period from 2018 to 2022, at hourly intervals. The input variables include temperature, wind speed, humidity, dew point temperature, sunshine duration, and solar radiation. In this study, we utilized both individual and ensemble models, and we further proposed a stacking ensemble method using a multilayer perceptron as the meta learner. The results indicated that most machine learning models exhibited under-dispersion. Notably, the stacking model demonstrated superior predictive performance in both time series cross-validation and the testing set. These findings suggested that the stacking model produces stable and accurate predictions by amalgamating the predicted values of base learners.
참고문헌 (22)
- 안나현, "시계열 교차검증을 적용한 2,3-BDO 분리공정 온도예측 모델의 초매개변수 최적화", Korean Chemical Engineering Research(HWAHAK KONGHAK), 59(4), pp.532~541 (2021), 한국화학공학회
- Breiman, L., "Stacked regressions", Machine Learning, 24, pp.49~64 (1996)
- 최지은, "웨이블릿 분해 기반의 대한민국 지면온도 예측", 한국데이터정보과학회지, 34(2), pp.279~289 (2023), 한국데이터정보과학회
- Dong, J., "Modelling soil temperature by tree-based machine learning methods in different climatic regions of China", Applied Sciences, 12(10), pp.5088~ (2022)
- 황유선, "앙상블 기계 학습을 이용한 기온 예측", 기후연구, 14(2), pp.129~143 (2019), 기후연구소[DOI]
- Imran, H. M., "Land surface temperature and human thermal comfort responses to land use dynamics in Chittagong city of Bangladesh", Geomatics, Natural Hazards and Risk, 13(1), pp.2283~2312 (2022)
- 구민호, "국내 지면 온도의 시공간적 변화 분석", 자원환경지질, 39(3), pp.255~268 (2006), 대한자원환경지질학회
- Ksibi, A., "Airstacknet: a stacking ensemble-based approach for air quality prediction", Computers, Materials & Continua, 74(1) (2023)[DOI]
- Liu, J., "Early diabetes prediction based on stacking ensemble learning model", 2021 33rd Chinese Control and Decision Conference (CCDC), pp.2687~2692 (2021)
- Liu, P., "Impacts of land surface and sea surface temperatures on the onset date of the South China Sea summer monsoon", Advances in Atmospheric Sciences, 26, pp.493~502 (2009)
- Maddu, R., "Prediction of land surface temperature of major coastal cities of India using bidirectional LSTM neural networks", Journal of Water and Climate Change, 12(8), pp.3801~3819 (2021)
- Marzban, C., "On the effect of correlation on rank histograms: reliablity of temperature and wind speed forecasts from fine scale ensemble reforecasts", Monthly Weather Review, 139, pp.295~310 (2011)
- Onwuka, B., "Effects of soil temperature on some soil properties and plant growth", Advances in Plants & Agriculture Research, 8(1), pp.34~37 (2018)
- Rocha, N. S. D., "The influence of land surface temperature in evapotranspiration estimated by the S-SEBI model", Atmosphere, 11(10), pp.1059~ (2020)
- Sharma, P., "Predicting soil temperature using air temperature and soil, crop, and meteorological parameters for three specialty crops in southern New Mexico", Applied Engineering in Agriculture, 26(1), pp.47~58 (2010)
- Song, Y., "The dominant modes of spring land surface temperature over Western Eurasia and their possible linkages with large‐scale atmospheric teleconnection patterns", Journal of Geophysical Research: Atmospheres, 127(4) (2022)
- Suh, M. S., "Land Surface Temperature (LST)Algorithm Technical Analysis (LST-v5.0), NMSC", SCI, LST, Issue 1, rev.0, pp.National Meteorological Satellite Center, 2012[DOI]
- Tang, W., "TRIMS LST: a daily 1-km all-weather land surface temperature dataset for the Chinese landmass and surrounding areas (2000-2021)", Earth System Science Data Discussions, pp.1~34 (2023)
- Ves, A. V., "A stacking multi-learning ensemble model for predicting near real Time energy consumption demand of residential buildings", 2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP), pp.183~189 (2019)
- Wolpert, D. H., "Stacked generalization", Neural Networks, 5(2), pp.241~259 (1992)
- Wu, R., "Contrasting Eurasian spring and summer climate anomalies associated with western and eastern Eurasian spring snow cover changes", Journal of Geophysical Research: Atmospheres, 119(12), pp.7410~7424 (2014)
- Xue, Y., "Spring land temperature anomalies in northwestern US and the summer drought over Southern Plains and adjacent areas", Environmental Research Letters, 11(4), pp.044018~ (2016)