Forecasting Buoy Observations Using Physics-Informed Neural Networks
- 14 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 49 (3) , 821-840
Abstract
Methodologies inspired by physics-informed neural networks (PINNs) were used to forecast observations recorded by stationary ocean buoys. We combined buoy observations with numerical models to train surrogate deep learning networks that performed better than with either data alone. Numerical model outputs were collected from two sources for training and regularization: the hybrid circulation ocean model and the fifth European Centre for Medium-Range Weather Forecasts (ECMWF) reanalysis experiment. A hyperparameter determines the ratio of observational and modeled data to be used in the training procedure, so we conducted a grid search to find the most performant ratio. Overall, the technique improved the general forecast performance compared with nonregularized models. Under specific circumstances, the regularization mechanism enabled the PINN models to be more accurate than the numerical models. This demonstrates the utility of combining various climate models and sensor observations to improve surrogate modeling.Keywords
All Related Versions
Funding Information
- Science, Mathematics and Research for Transformation
- U.S. Department of War
- U.S. Navy (N00173-20-2-C007)
- Naval Research Laboratory (N00173-20-2-C007)
This publication has 34 references indexed in Scilit:
- A machine‐learning and data assimilation forecasting framework for surface wavesQuarterly Journal of the Royal Meteorological Society, 2024
- A regional wind wave prediction surrogate model based on CNN deep learning networkApplied Ocean Research, 2022
- Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s NextJournal of Scientific Computing, 2022
- Variability of the deep South China Sea circulation derived from HYCOM reanalysis dataActa Oceanologica Sinica, 2022
- Structural dynamics simulation using a novel physics-guided machine learning methodEngineering Applications of Artificial Intelligence, 2020
- Coupled data assimilation and parameter estimation in coupled ocean–atmosphere models: a reviewClimate Dynamics, 2020
- The ERA5 global reanalysisQuarterly Journal of the Royal Meteorological Society, 2020
- A machine learning framework to forecast wave conditionsCoastal Engineering, 2018
- A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon‐Ocean Feedback in Typhoon Forecast ModelsGeophysical Research Letters, 2018
- A time-dependent surrogate model for storm surge prediction based on an artificial neural network using high-fidelity synthetic hurricane modelingNatural Hazards, 2014