Publications

Standard PIHNNs

• Title: Physics-Informed Holomorphic Neural Networks (PIHNNs): Solving 2D linear elasticity problems

• Authors: Matteo Calafà, Emil Hovad, Allan P. Engsig-Karup, Tito Andriollo

• Published in: Computer Methods in Applied Mechanics and Engineering

• Year of publication: 2024

• DOI: 10.1016/j.cma.2024.117406

Enriched PIHNNs

• Title: Solving plane crack problems via enriched holomorphic neural networks

• Authors: Matteo Calafà, Henrik Myhre Jensen, Tito Andriollo

• Published in: Engineering Fracture Mechanics

• Year of publication: 2025

• DOI: 10.1016/j.engfracmech.2025.111133

PIHKANs and L-PIHNNs

• Title: A holomorphic Kolmogorov-Arnold network framework for solving elliptic problems on arbitrary 2D domains

• Authors: Matteo Calafà, Tito Andriollo, Allan P. Engsig-Karup, Cheol-Ho Jeong

• Published in: Machine Learning for Computational Science and Engineering

• Year of publication: 2026

• DOI: 10.1007/s44379-026-00094-8

This research was supported by the Aarhus University Research Foundation, Denmark.

Note

If you use PIHNNs for your research, don’t forget to cite our works in this page.