http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이황기(Hwangki Lee),최혁진(Hyukjin Choi),백종대(Jongdae Back),김종규(Jongkyu Kim) 한국해양환경·에너지학회 2021 한국해양환경공학회 학술대회논문집 Vol.2021 No.5
최근 기후변화에 기인한 해수면 상승으로 인해 고파랑 내습시 인적, 물적 피해가 지속적으로 증가하고 있으며, 이에 대한 대응방안으로 정밀도 높은 파랑예보시스템이 요구되어진다. 본 연구에서는 정밀도 높은 파랑예측시스템을 구축하기 위하여 파랑예측의 입력자료인 예보 바람장을 기관별로 수집하고 SWAN 모델을 이용한 파랑 추산실험을 수행하여 기관별 파랑추산 정확도를 검토하였다. 또한, 파랑추산결과의 정확도 향상을 위하여 인공신경망(Artificial Neural Network)과 랜덤포레스트(Random Forest) 기법을 이용하여 추산된 파랑을 보정하였다. 파랑 추산자료의 재현성을 검증 및 인공신경망(Artificial Neural Network)과 랜덤포레스트(Random Forest)기법의 학습 자료는 해양수산부에서 구축한 전국 파랑관측자료 제공시스템(WINK, Wave Information Network of Korea)에서 제공하는 기상청 부이의 실측 자료를 이용하였으며, 구축된 자동화 시스템은 오픈소스 코드인 파이썬(python 3.7.0)을 이용하여 1일 8회 3시간 간격으로 예측결과를 결과를 홈페이지에 자동 업로드 하도록 구축하였다. In this research, in order to minimize the damage that can be caused by high-wave invasion, a high-precision, high-resolution, real-time short-term wave prediction and verification automation system was built. The wind field data of KMA, JMA, and NOAA were used as input conditions, and the significant wave height, peak period, and representative wave direction were estimated using SWAN (Simulating Waves Nearshore, version 41.31) numerical modeling. Artificial Neural Network(ANN) and Random Forest(RF) techniques were applied to improve the accuracy of computational results.
골재채취해역의 복원을 위한 굴패각 투하공법별 확산에 관한 연구
이국현(Kookhyun Lee),윤진형(Jinhyeong Yun),이황기(Hwangki Lee) 전남대학교 수산과학연구소 2022 수산과학연구소논문집 Vol.31 No.1
The total amount of oyster shells produced annually in South Korea is estimated to be about 280,000 tons. Of them, 180,000 tons are being recycled as materials for oyster or Porphyra seed collection, shell fertilizers, and treated by contracted waste management companies. The rest, 100,000 tons, are illegally disposed of at farm sites or near the business facilities, causing severe environmental problems such as pollution of coastal fishing grounds, destruction of the landscape, and disturbance in the management of public waters. Multiple dumping methods of oyster shells comprise restoration measures that utilize unprocessed oyster shells to restore the sand mining zone within the South Sea of the Korean peninsula’s exclusive economic zone (EEZ). On that note, this study aims to conduct primary research to calculate the range of diffusion effects of each dumping method of oyster shells. Accordingly, the researchers collected unprocessed oyster shells from five oyster shucking fields near the South coast three in Tongyeong, one in Geoje, and one in Goseong, and measured the settling velocity by the respective size of the oyster shells in a hydraulic experiment. In addition, the diffusion distance of each dumping method was calculated by using a Computational Fluid Dynamics (CFD).
김승우(Seung-Woo Kim),이황기(Hwangki Lee),최혁진(Hyukjin Choi) 한국연안방재학회 2023 한국연안방재학회지 Vol.10 No.1
In this study, an artificial neural network (ANN) model for the typhoon wave overtopping was developed using the database by a numerical wave flume simulation. The developed ANN model is effective for saving calculation time largely. The accuracy of the model is also approached to over 95% of the numerical simulation. This accuracy was evaluated by the correlation coefficient and the root mean square error with the target data of the numerical simulation and output of the ANN model. This model quickly produces the mean wave overtopping rate, maximum wave run-up height, maximum wave overtopping depth and velocity at the middle point in the coastal road without high-fidelity numerical model and high-computing resources. It means that the typhoon warning system including the ANN models is powerful and useful rather than only the monitoring warning system currently in use.