Abstract
Ocean waves are widely estimated using physics-based computational models, which predict how energy is transferred from the wind, dissipated, and transferred spatially across the ocean. Machine learning methods offer an opportunity to predict these data with significantly reduced data input and computational power. This paper describes a novel surrogate model developed using the random forest method, which replicates the spatial nearshore wave data estimated by a Simulating WAves Nearshore (SWAN) numerical model. By incorporating in-situ buoy observations, outputs were found to match observations at a test location more closely than the corresponding SWAN model. Furthermore, the required computational time reduced by a factor of 100. This methodology can provide accurate spatial wave data in situations where computational power and transmission are limited, such as autonomous marine vehicles or during coastal and offshore operations in remote areas. This represents a significant supplementary service to existing physics-based wave models.
Highlights
Met-Ocean data play a significant role in the design and operation of offshore and coastal infrastructure
The work presented in this paper addressed three principle objectives: 1) Generate a surrogate model that applied machine learning method on the physics-based outputs to learn the spatial relationship be tween input buoy data at a few locations within the domain to the full spatially distributed wave conditions across the domain
The surrogate model worked on the assumption that the spatial distri bution of wave conditions created by the physical modelling process was well defined and provides an additional service to immediately estimate wave conditions across the model domain from limited input values
Summary
Met-Ocean data play a significant role in the design and operation of offshore and coastal infrastructure. A series of 3rd generation wave models such as WAM (WAve Modelling) (Günther et al, 1992; Komen et al, 1996), WAVEWATCH-III (Tolman, 2009; Tolman et al, 2002), and Simulating Waves Nearshore (SWAN) (Booij et al, 1999; Ris et al, 1999) have become universal numerical methods These models determine wave conditions based on the energy-balance equations, considering energy input from surface winds with processes dissipating wave energy. SWAN was designed as a tool for coastal modelling, focusing more on wave propagation in shallow water (Booij et al, 1999) It was designed for application in coastal re gions around the world and has been widely used to quantify wave conditions for offshore renewable energy sites It was designed for application in coastal re gions around the world and has been widely used to quantify wave conditions for offshore renewable energy sites (e.g. Ashton et al, 2014; Liang et al, 2014; Wu et al, 2020)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
