Towards Optimally Weighted Physics-Informed Neural Networks in Ocean Modelling
This work addresses ocean modeling for climate change analysis, but it appears incremental as it explores trade-offs in existing PINN methods without claiming major breakthroughs.
The paper tackled the problem of modeling ocean currents and temperature flows using physics-informed neural networks (PINNs) to solve partial differential equations, finding that small datasets benefit more from incorporating physics information in the loss function.
The carbon pump of the world's ocean plays a vital role in the biosphere and climate of the earth, urging improved understanding of the functions and influences of the ocean for climate change analyses. State-of-the-art techniques are required to develop models that can capture the complexity of ocean currents and temperature flows. This work explores the benefits of using physics-informed neural networks (PINNs) for solving partial differential equations related to ocean modeling; such as the Burgers, wave, and advection-diffusion equations. We explore the trade-offs of using data vs. physical models in PINNs for solving partial differential equations. PINNs account for the deviation from physical laws in order to improve learning and generalization. We observed how the relative weight between the data and physical model in the loss function influence training results, where small data sets benefit more from the added physics information.