Deep neural operators can predict the real-time response of floating offshore structures under irregular waves

Cao, Qianying; Goswami, Somdatta; Tripura, Tapas; Chakraborty, Souvik; Karniadakis, George Em

doi:10.1016/j.compstruc.2023.107228

Cited by 8 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture of DeepONet features a DNN, which encodes the input functions at fixed sensor points (branch net), and another DNN, which encodes the information related to the spatio-temporal coordinates of the output function (trunk net). Since its first appearance, standard DeepONet has been employed to tackle challenging problems involving complex high-dimensional dynamical systems 13 – 17 . In addition, extensions of DeepONet have been recently proposed in the context of multi-fidelity learning 18 – 20 , integration of multiple-input continuous operators 21 , 22 , hybrid transferable numerical solvers 23 , transfer learning 24 , and physics-informed learning to satisfy the underlying PDE 25 , 26 .…”

Section: Introductionmentioning

confidence: 99%

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Kontolati,

Goswami,

Em Karniadakis

et al. 2024

Nat Commun

Self Cite

View full text Add to dashboard Cite

Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

show abstract