[HTML][HTML] Deepokan: Deep operator network based on kolmogorov arnold networks for mechanics problems

DW Abueidda, P Pantidis, ME Mobasher - Computer Methods in Applied …, 2025 - Elsevier
The modern digital engineering design often requires costly repeated simulations for
different scenarios. The prediction capability of neural networks (NNs) makes them suitable …

Synergistic learning with multi-task deeponet for efficient pde problem solving

V Kumar, S Goswami, K Kontolati, MD Shields… - Neural Networks, 2025 - Elsevier
Multi-task learning (MTL) is an inductive transfer mechanism designed to leverage useful
information from multiple tasks to improve generalization performance compared to single …

Basis-to-basis operator learning using function encoders

T Ingebrand, AJ Thorpe, S Goswami, K Kumar… - Computer Methods in …, 2025 - Elsevier
Abstract We present Basis-to-Basis (B2B) operator learning, a novel approach for learning
operators on Hilbert spaces of functions based on the foundational ideas of function …

A Spectral-based Physics-informed Finite Operator Learning for Prediction of Mechanical Behavior of Microstructures

A Harandi, H Danesh, K Linka, S Reese… - arxiv preprint arxiv …, 2024 - arxiv.org
A novel physics-informed operator learning technique based on spectral methods is
introduced to model the complex behavior of heterogeneous materials. The Lippmann …

Neural fields for rapid aircraft aerodynamics simulations

G Catalani, S Agarwal, X Bertrand, F Tost… - Scientific Reports, 2024 - nature.com
This paper presents a methodology to learn surrogate models of steady state fluid dynamics
simulations on meshed domains, based on Implicit Neural Representations (INRs). The …

[HTML][HTML] Tutorials: Physics-informed machine learning methods of computing 1D phase-field models

W Li, R Fang, J Jiao, GN Vassilakis, J Zhu - APL Machine Learning, 2024 - pubs.aip.org
Phase-field models are widely used to describe phase transitions and interface evolution in
various scientific disciplines. In this Tutorial, we present two neural network methods for …