인공신경망을 활용한 위성사진 기반 기대풍속 예측 방법론에 관한 연구
Research on Satellite Image-based Wind Speed Prediction Methodology using Neural Network
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
이 연구는 위성사진을 활용하여 건설지점의 기대풍속을 예측하기 위한 인공신경망 방법론을 제안한다. 제안된 방법은 기존의 엔지니어의 판단을 대체하여, Auto-Encoder를 사용해 지형적 특성을 정량화하고, 이를 바탕으로 대상지점과 유사한 지역의 관측소 풍속 데이터를 선형 조합해 기대 풍속을 예측한다. 또한, 머신러닝과 인공신경망을 활용한 종단간 풍속 예측 모델을 제안하고, 성능을 비교 분석하였다. 그 결과 관측소의 풍속 데이터의 선형 조합보다는 종단간 모델을 구성하는 방법이 더 높은 정확도를 보였으며, 특히 Graph Neural Network (GNN)이 Multi-Layer Perceptron (MLP)에 비해 상당히 우수한 예측 성능을 나타내었다.
Abstract
In this study, a methodology using neural network to predict the expected wind speed at construction sites based on satellite images was proposed. The proposed method replaces engineers' judgments by using an Auto-Encoder to quantify topographical features and linearly combining the wind speed data of weather stations in region similar to the target site to predict expected wind speeds. Additionally, the performance of end-to-end wind speed prediction models using machine learning and artificial neural networks were proposed and compared. As a result, it was found that the end-to-end models showed higher accuracy than the linear combination of wind speed data from selected weather stations. Specifically, the Graph Neural Network (GNN) showed better prediction performance compared to the Multi-Layer Perceptron (MLP).
참고문헌 (36)
- 강현구, "KBC 2016 풍하중의 산정법 이해 및 고층건물에서의 적용", 한국풍공학회지, 23(2), pp.83~89 (2019), 한국풍공학회
- 김경민, "지역빈도해석을 이용한 남해안 지역의 극치풍속 추정", 한국풍공학회지, 26(2), pp.61~67 (2022), 한국풍공학회
- 김진호, "기상청 주변의 지형 및 지표면 조도를 고려한 기본풍속 산정 방안 연구", 한국풍공학회지, 21(4), pp.187~196 (2017), 한국풍공학회
- 우수현, "우리나라 강풍의 발생성인별 계속시간 추정", 한국풍공학회지, 21(3), pp.127~134 (2017), 한국풍공학회
- Bernardini, E., "Performance-Based Design of High-Rise Buildingsfor Occupant Comfort", Journal of Structural Engineering, 141(10), pp.4014244~ (2015)
- Bahmani, P., "Displacement-Based Design of Buildings with Torsion: Theory and Verification", Journal of Structural Engineering, 140(6), pp.4014020~ (2014)
- Kwon, D. -K., "Performance Evaluation of Database-Enabled Design Frameworks for the Preliminary Design of Tall Buildings", Journal of Structural Engineering, 141(10), pp.4014242~ (2015)
- Lou, W., "Multiobjective Equivalent Static Wind Loads on Complex Tall Buildings Using Non-Gaussian Peak Factors", Journal of Structural Engineering, 141(11), pp.4015033~ (2015)
- Alinejad, H., "Engineering Review of ASCE 7-16Wind-Load Provisions and Wind Effect on Tall Concrete-Frame Buildings", Journal of Structural Engineering, 146(6), pp.4020089~ (2020)
- Ouyang, Z., "A Performance-Based Wind Engineering Framework for Envelope Systems of Engineered Buildings Subject to Directional Wind and Rain Hazards", Journal of Structural Engineering, 146(5), pp.4020049~ (2020)
- Cui, W., "Performance-Based Wind Engineering of Tall Buildings Examining Life-Cycle Downtime and Multisource Wind Damage", Journal of Structural Engineering, 146(1), pp.4019179~ (2020)
- Jeong, S. Y., "Performance-Based Wind Design of High-Rise Buildings Using Generated Time-History Wind Loads", Journal of Structural Engineering, 147(9), pp.4021134~ (2021)
- 강현구, "국내외 풍직각방향 및 비틀림 풍하중 기준 비교 연구", 한국풍공학회지, 23(3), pp.151~159 (2019), 한국풍공학회
- Tamura, Y., "Mathematical Models for Understanding Phenomena : Vortex-Induced Vibrations", Japan Architectural Review, 3(3), pp.398~422 (2020)
- Cho, N. -S., "A Study on the Estimation of Basic Wind Speed Map for Design of Building Structures", Journal of the Architectural Institute of Korea, 10(11), pp.247~257 (1994)
- Ha, Y. -C., "Basic Wind Speed Map of Korea for Wind Resistant Design", Journal of the Architectural Institute of Korea, 14(8), pp.75~83 (1998)
- 정선하, "건축구조기준(KBC-2009) 기본풍속도의 개선", 대한건축학회논문집 구조계, 30(5), pp.37~47 (2014), 대한건축학회
- American Society of Civil Engineers(ASCE), "Minimum Design Loads and Associated Criteria for Buildings and Other Structures (ASCE 7-22)", ASCE, ~ (2022)
- International Organization for Standardization (ISO), "Wind actions on structures (ISO 4354:2012)", ISO, ~ (2012)
- Architectural Institute of Japan(AIJ), "Recommendations for Loads on Buildings (AIJ 2015)", AIJ, ~ (2015)
- Ministry of Land, Infrastructure and Transport, "Korean Design Standard (KDS 41 12 00:2022)", ~ (2022)
- Sachindra, D. A., "Statistical Downscaling of Precipitation Using Machine Learning Techniques", Atmospheric Research, 212, pp.240~258 (2018)
- Li, L., "Geographically Weighted Machine Learning and Downscaling for High-Resolution Spatiotemporal Estimations of Wind Speed", Remote Sensing (Basel), 11(11) (2019)
- Oh, M., "Machine Learning-Based Statistical Downscaling of Wind Resource Maps Using Multi-Resolution Topographical Data", Wind Energy, 25(6), pp.1121~1141 (2022)
- 김민규, "전산유체해석을 통한 고층 건물의 풍압계수 산정", 한국풍공학회지, 24(3), pp.127~133 (2020), 한국풍공학회[DOI]
- 김석철, "도로협곡내 보행공간에서 식생에 의한 교통 대기오염 저감효과에 대한 CFD 시뮬레이션 연구", 한국풍공학회지, 25(4), pp.171~178 (2021), 한국풍공학회
- 엄정아, "CFD를 이용한 보행자 풍환경 평가 기법의 적합성 분석", 한국풍공학회지, 26(2), pp.53~60 (2022), 한국풍공학회
- 엄정아, "CFD를 활용한 보행자 풍환경 평가기법 개발", 한국풍공학회지, 26(4), pp.137~149 (2022), 한국풍공학회
- 이제현, "재해석 자료를 이용한 전세계 풍속의 회귀분석", 한국풍공학회지, 25(4), pp.165~170 (2021), 한국풍공학회
- Koo, J., "Wind-Speed Prediction and Analysis Based on Geological and Distance Variables Using an Artificial Neural Network: A Case Study in South Korea", Energy, 93, pp.1296~1302 (2015)
- Zhu, Q., "Wind Speed Prediction with Spatio–Temporal Correlation : A Deep Learning Approach", Energies, 11(4), pp.705~ (2018)
- Chen, T., "A Simple Framework for Contrastive Learning of Visual Representations", arXiv.2002.05709, ~ (2020)
- Counihan, J., "Adiabatic Atmospheric Boundary Layers: A Review and Analysis of Data from the Period 1880–1972", Atmospheric Environment, 9(10), pp.871~905 (1975)
- Loh, W.Y., "Classification and Regression Trees", Wiley Interdisciplinary Reviews. Data Mining and Knowledge Discovery, 1(1), pp.14~23 (2011)
- Scarselli, F., "The Graph Neural Network Model", IEEE Transactions on Neural Networks, 20(1), pp.61~80 (2009)
- Kipf, T. N., "Semi-Supervised Classification with Graph Convolutional Networks", arXiv : 1609. 02907, ~ (2017)
