首页|Researchers from University of Quebec Discuss Findings in Machine Learning (A Ph ysics-informed Machine Learning Model for Timedependent Wave Runup Prediction)
Researchers from University of Quebec Discuss Findings in Machine Learning (A Ph ysics-informed Machine Learning Model for Timedependent Wave Runup Prediction)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning. According to news reporting out of Montreal, Canada, by NewsRx editor s, research stated, "Wave runup is a critical factor that affects coastal floodi ng, shoreline changes, and the damage to coastal structures. Climate change is a lso expected to amplify the impact of wave runup on coastal areas." Financial support for this research came from Natural Sciences and Engineering R esearch Council of Canada (NSERC). Our news journalists obtained a quote from the research from the University of Q uebec, "Therefore, fast and accurate wave runup estimation is essential for effe ctive coastal engineering design and management. However, predicting the time-de pendent wave runup is challenging due to the intrinsic nonlinearities and nonsta tionarity of the process, even with the use of the most advanced machine learnin g techniques. In this study, a physics-informed machine learning-based approach is proposed to efficiently and accurately simulate time-series wave runup. The m ethodology combines the computational efficiency of the Surfbeat (XBSB) mode wit h the accuracy of the nonhydrostatic (XBNH) mode of the XBeach model. Specifical ly, a conditional generative adversarial network (cGAN) is used to map the image representation of wave runup from XBSB to the corresponding image from XBNH. Th ese images are generated by first converting wave runup signals into timefrequen cy scalograms and then transforming them into image representations. The cGAN mo del achieves improved performance in image-to-image mapping tasks by incorporati ng physicsbased knowledge from XBSB. After training the model, the high-fidelit y XBNH-based scalograms can be predicted, which are then used to reconstruct the time-series wave runup using the inverse wavelet transform."
MontrealCanadaNorth and Central Amer icaCyborgsEmerging TechnologiesMachine LearningUniversity of Quebec
NETL
NSTL
