Estimation of Solar Irradiance at Weather Stations in Korea Using Regionally Trained Artificial Neural Network Models

Koo, YoungHyun; Kim, Sung-Min; Oh, Myeongchan; Park, Hyeong‐Dong

doi:10.32390/ksmer.2019.56.2.155

Cited by 3 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A fine-scale solar energy map is highly useful not only for selecting solar power plant sites but also for real-time managements of power grids composed of multiple types of power plants. In-situ insolation measurements provide accurate values, but are not practical in building high-resolution solar energy maps over large areas because of the high costs for the installation and maintenance of instruments (Koo et al 2019;Jee et al 2017). Moreover, in-situ measurements cannot be used for solar energy forecasting.…”

Section: Introductionmentioning

confidence: 99%

Improvement of Korea Meteorological Administration Solar Energy Resources Map Using Fine-Scale Terrain Data

Yun

Kim

Choi

et al. 2023

Asia-Pac J Atmos Sci

View full text Add to dashboard Cite

Real-time solar energy resources mapping is crucial for the development and management of solar power facilities. This study analyzes the effects of the digital elevation model (DEM) resolution on the accuracy of the surface insolation (insolation hereafter) calculated by the Korea Meteorological Administration solar energy mapping system, KMAP-Solar, using two DEMs of different resolutions, 1.5 km and 100 m. It is found that KMAP-Solar yields smaller land-mean insolation with the fine-scale DEM than the coarse-scale DEM. The fine-scale DEM reduces biases by as much as 32 Wm− 2 for all observation sites, especially those in complex terrain and that the insolation error reduction is correlated with the difference in sky view factor (SVF) between the coarse- and fine-scale DEM. Both the coarse- and fine-scale DEMs generate the insolation-elevation and insolation-SVF relationship which is characterized by positive (negative) correlation between the insolation and the terrain altitude (SVF). However, the coarse-scale DEM substantially underestimates these relationships compared to the fine-scale DEM, mainly because the coarse-scale DEM underrepresents large terrain slopes and/or small SVFs, most seriously in high-altitude regions. The fine-scale DEM generates a more realistic insolation distribution than the coarse-scale DEM by incorporating a wider range of key terrain parameters involved in determining insolation. Improvements of insolation calculations in KMAP-Solar using a fine-scale DEM, especially in the areas of complex terrain, is of a practical value for Korea because the operational solar resources map from KMAP-Solar supports solar energy research, solar power plant installations, and real-time prediction and management of solar power within the power grid.

show abstract

Section: Introductionmentioning

confidence: 99%

Improvement of Korea Meteorological Administration Solar Energy Resources Map Using Fine-Scale Terrain Data

Yun

Kim

Choi

et al. 2023

Asia-Pac J Atmos Sci

View full text Add to dashboard Cite

show abstract

“…Basic statistics of factors used to develop machine learning techniques 레이어는 입력층과 은닉층, 출력층으로 구성된다. 또한, 여러 층의 구조를 가진 인공신경망을 MLP(multi-layer perceptron)이라 고 하며, 해당 기법은 복잡한 물리적인 이론식을 계산 하기 어려운 문제에 응용할 경우 전통적인 통계 방법 보다 효율적이고 정확하게 해결할 수 있는 장점이 있다(Koo et al, 2019). Orange Data Mining에서의 ANN 기법은 sklearn의 MLP 알고리즘을 기반으로 한다.• kNN: 알고리즘의 구현이 단순하고 성능이 뛰어나 데 이터 마이닝 분야와 머신러닝 분야에 널리 사용되는 알고리즘이다(Zhang et al, 2017).…”

unclassified

Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques

Han¹,

Choi

Suh³

2022

J. Korean Soc. Miner. Energy Resour. Eng.

View full text Add to dashboard Cite

In this study, the prediction of mining-induced subsidence is analyzed and compared using various machine learning models. Factors affecting the occurrence of subsidence are identified from eight and 1,730 sets of subsidence data. Five machine learning models are selected, i.e., Adaboost, artificial neural networks, the k-nearest neighbor, random forest, and the support vector machine, which are frequently used in studies related to geohazard prediction. In addition, the stacking technique is applied to five algorithms based on 10 combinations, and the predictive performance of each ensemble method is evaluated and compared. To evaluate the classification performance of the machine learning technique applied in this study, recall is used as an evaluation index, which describes the ratio of the predicted ground subsidence instead of the area under curve used previously. Based on the values of recall, the random forest demonstrates the best performance (with a recall of 0.955). The recall is expected to be a more reliable evaluation index for predicting subsidence occurrences compared with other indices.

show abstract

Research Trends in New and Renewable Energy Technology Focusing on Papers Published in Korean/English Journals of the Korean Society of Mineral and Energy Resources Engineers

Choi¹,

Park

2022

J. Korean Soc. Miner. Energy Resour. Eng.

View full text Add to dashboard Cite

In this study, 75 papers published in the Korean/English journals of the Korean Society of Mineral and Energy Resources Engineers were reviewed to analyze research trends in new and renewable energy technology (NRET) in the field of resource engineering. The number of NRET-related papers has been continuously increasing, and since 2006, research topics have diversified to include geothermal energy as well as various NRETs. Classification of papers according to the type of NRET showed that the share of papers on geothermal energy was the highest at 41%, followed by papers on the convergence of heterogeneous NRETs (20%) and solar energy (19%). The share of papers on economy/policy was high in the fields of hydrogen energy, convergence of heterogeneous technologies, and other renewable energy including ocean, bio, and waste energies.

show abstract

Estimation of Solar Irradiance at Weather Stations in Korea Using Regionally Trained Artificial Neural Network Models

Cited by 3 publications

References 37 publications

Improvement of Korea Meteorological Administration Solar Energy Resources Map Using Fine-Scale Terrain Data

Improvement of Korea Meteorological Administration Solar Energy Resources Map Using Fine-Scale Terrain Data

Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques

Research Trends in New and Renewable Energy Technology Focusing on Papers Published in Korean/English Journals of the Korean Society of Mineral and Energy Resources Engineers

Contact Info

Product

Resources

About