GK-2A와 ASOS 지상 관측 자료를 이용한 태양광 에너지 산출 딥러닝 학습 데이터 (Solar Energy Datasets of Deep Learning Models Incorporating with GK-2A and ASOS Ground Measurements)

서지정보

· 발행기관 : (사)지오에이아이데이터학회
· 수록지 정보 : GEO DATA / 6권 / 4호 / 471 ~ 477페이지
· 저자명 : 하종성, 정승택, 민세윤, 이예진, 김수환, 한도희, 염종민

초록

This study presents the construction and evaluation of a dataset for estimating solarenergy using the GK-2A satellite and deep learning. The GK-2A is currently utilizedin real-time for weather observations over the Korean Peninsula. The GK-2A satellitefeatures 16 channels, producing radiative channel images at spatial resolutionsranging from 500 m to 2 km, with temporal intervals as short as 2 minutes dependingon the area. These satellite data are used in various fields, including meteorology,oceanography, vegetation monitoring, and renewable energy. In this study, we usedspectral channel data from the GK-2A expended local area satellite from January 2021to December 2022. For training and evaluating the accuracy of the deep learning model,we utilized data from 98 automated synoptic observing system ground observationsites operated by the Korea Meteorological Administration. A back-propagationneural network model, which showed meaningful results in estimating solar energy,was applied. Various hyperparameters were optimized, and data preprocessing andseparation were conducted to optimize the model. The study also compared theperformance of the deep learning model with physical models. The BPNN deep learningmodel achieved a statistical accuracy of root mean squared error (RMSE) 77.32 Wm-2,mean bias error (MBE) -0.48 Wm-2, and R² 0.91, indicating high accuracy. In contrast, thephysical model showed an RMSE of 132.01 Wm-2, MBE -76.51 Wm-2, and an R² of 0.74,displaying relatively lower accuracy compared to the deep learning model. Additionally,the spatio-temporal map of solar energy generated by the deep learning modelsuccessfully captured the attenuation of radiation due to clouds and the variation insolar energy based on the position of the sun. The solar energy data produced in thisstudy are expected to be useful as input data for various fields such as meteorology,agriculture, environmental monitoring, and marine sciences.

영어초록

This study presents the construction and evaluation of a dataset for estimating solarenergy using the GK-2A satellite and deep learning. The GK-2A is currently utilizedin real-time for weather observations over the Korean Peninsula. The GK-2A satellitefeatures 16 channels, producing radiative channel images at spatial resolutionsranging from 500 m to 2 km, with temporal intervals as short as 2 minutes dependingon the area. These satellite data are used in various fields, including meteorology,oceanography, vegetation monitoring, and renewable energy. In this study, we usedspectral channel data from the GK-2A expended local area satellite from January 2021to December 2022. For training and evaluating the accuracy of the deep learning model,we utilized data from 98 automated synoptic observing system ground observationsites operated by the Korea Meteorological Administration. A back-propagationneural network model, which showed meaningful results in estimating solar energy,was applied. Various hyperparameters were optimized, and data preprocessing andseparation were conducted to optimize the model. The study also compared theperformance of the deep learning model with physical models. The BPNN deep learningmodel achieved a statistical accuracy of root mean squared error (RMSE) 77.32 Wm-2,mean bias error (MBE) -0.48 Wm-2, and R² 0.91, indicating high accuracy. In contrast, thephysical model showed an RMSE of 132.01 Wm-2, MBE -76.51 Wm-2, and an R² of 0.74,displaying relatively lower accuracy compared to the deep learning model. Additionally,the spatio-temporal map of solar energy generated by the deep learning modelsuccessfully captured the attenuation of radiation due to clouds and the variation insolar energy based on the position of the sun. The solar energy data produced in thisstudy are expected to be useful as input data for various fields such as meteorology,agriculture, environmental monitoring, and marine sciences.

참고자료

· 없음