![]() ![]() The dataset consists of example inputs and outputs, as seen in the figure below. We packaged the computer model in a docker container and ran it using singularity without noticeable performance overhead. The Dell Technologies HPC cluster in Frankfurt provided the computation power and batch system to run all the jobs. We ran a series of 20,000 model runs to create a representative training dataset. high wave height and low sea level, high wave height with highest sea level) to ensure our emulator is exposed to a broad range of inputs. We prioritize sampling extreme combinations (e.g. It involves selecting sea level and wave spectra (a combination of waves with different heights and wavelengths from various directions) as input parameters for the global wave models. A sampling strategy is a method of creating a dataset. The SWAN computer model was used to run a wave simulation for each sample. We generated a dataset of wave simulations by using a sampling approach for the parameters and data from bathymetries. The EMODNET and GEBCO bathymetries have European and global coverage. We also have information on the bathymetry near the coasts. Wave Watch III) typically provide coarse waves at the boundary of the coastal sea. As input, we use the wave energy of global ocean wave models. The second step is to select relevant input information.If wind directions change, this can cause specific stretches of coast to suffer from more and other regions to have less coastal erosion. Future coastal erosion estimates need this information. Here we focus on creating estimates for the total wave energy that reaches the beach over decades. The first task is to define the application. ![]() The figure below shows the main tasks and the actions involved per task. How did you set up this wave emulator?Ĭreating an emulator consists of several steps. Other terms include a surrogate model (as opposed to the "real model" that you prefer) or a data-driven model. The geoscientific field refers to this machine-learning approach as an emulator. Using a machine learning model that learns the physical rules is an alternative to the physical-based model. Your old model runs and measurements allow you to learn how waves will likely propagate. If you can collect a large enough dataset of model runs and or observations, you may not need to run a simulation. Many applications ignore coastal waves, use simplified approaches using empirical formulas, or only focus on small regions.Īn emulator takes an alternative implementation. That works for a few days ahead if you want to do this for a few days ahead, but it becomes a very compute-intensive job for decades-long simulations. It can take several hours to predict the sea state in a large region. One complex part about coastal waves is that they are hard to compute. We can use these models to predict waves several days ahead or for the next decades for climate scenarios. ![]() The traditional approach to coastal wave prediction uses computer models to simulate the physics of this process. As waves begin to feel the seafloor, they will turn towards the beach and can break as they reach shallow water. These waves then roll towards the coast, where they "feel" the seafloor. Large waves can form if the wind pushes water over a long stretch. The wind generates waves by shearing over the water's surface. Coastal waves are the waves you see when you go out to the sea. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |