Week 47 10 papers Coverage: 2026-11-06 → 2026-11-13

Week 47 · Physics AI Paper Digest

This week collects 10 preprints across physics-informed, pinn, pinns, all circling the same question: how physics-constrained learning stays reliable once the problem reaches realistic solver scale. Each entry below carries a short summary and the reason it is worth reading.

Highlights

  • 1. Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs (physics-informed, pinn)
  • 2. CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs (neural operator, operator learning)
  • 3. Convergence analysis of physics-informed neural networks for subdiffusion (physics-informed, pinn)
  • 4. Parameterized Physics-Informed Neural Networks for Efficient Simulation of Embedded Microfluidic Chip Cooling (physics-informed, pinn)
  • This week: 10 papers, focusing on physics-informed, pinn, pinns; recommendation reasons are auto-generated from the abstracts, with details per entry

In this issue

1

Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs

Authors Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck et al. 9 pages plus Appendix, 11 figures, 1 table. Rejected at ICLR
Why read it

Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, providing a wide ecosystem of novel methods. However, one frequent limit

arXiv · 2611.18409 ↗ physics-informedpinnpinnspde
2

CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs

Authors Trong Khiem Tran, Minh Long Bui, Phi Le Nguyen et al. Accepted NeurIPS 2026
Why read it

This paper introduces COUPLED FLOW, a new neural operator learning framework for multi-physics PDE systems that captures the co-evolution of multiple physical processes by modeling their cross-process

arXiv · 2611.10945 ↗ neural operatoroperator learningpdemulti-physics
3

Convergence analysis of physics-informed neural networks for subdiffusion

Authors Bangti Jin, Qiqi Rao, Zhi Zhou
Why read it

Physics-informed neural networks have emerged as mesh-free solvers for partial differential equations, yet their rigorous convergence theory for time-fractional problems remains limited. We present a

arXiv · 2611.17759 ↗ physics-informedpinnpinnspartial differential equation
4

Parameterized Physics-Informed Neural Networks for Efficient Simulation of Embedded Microfluidic Chip Cooling

Authors Weiheng Li, Zhiyao Jiang, Bai Song
Why read it

Embedded microfluidic cooling is a promising technology for dissipating the intense heat generated by high-performance electronic chips. However, the design and optimization of such coolers impose pro

arXiv · 2611.10666 ↗ physics-informedpinnpinnssurrogate model
5

Rethinking How to Leverage Cheap Physics for Data-Efficient Neural Operators

Authors Shuo Zhang, Senwei Liang
Why read it

Neural operators learn mappings from PDE inputs, such as initial conditions and coefficient fields, to the corresponding solutions. Once trained, they can rapidly predict solutions for new inputs. How

arXiv · 2611.10217 ↗ physics-informedneural operatorpde
6

A systematic comparison of physics-informed neural networks and mechanistic models for epidemic modeling and forecasting

Authors Martina Rama, Yuhan Li, Bruno Lepri et al.
Why read it

Physics-Informed Neural Networks (PINNs) have recently been applied to epidemic modeling and forecasting with promising results. These methods integrate mechanistic knowledge with data-driven learning

arXiv · 2611.18389 ↗ physics-informedpinnpinns
7

Well-Balanced WE-PINNs for the Shallow Water Equations over Smooth and Discontinuous Bathymetries

Authors Ismail Oubarka, Imad Kissami, Mohamed Boubekeur et al.
Why read it

Physics-informed neural networks (PINNs) solve partial differential equations without a mesh, but they do not in general preserve the steady states that well-balanced schemes reproduce exactly. We pre

arXiv · 2611.17289 ↗ physics-informedpinnpinnspartial differential equation
8

Physics-informed neural networks in the small-data regime: A controlled comparison with classical PDE surrogates

Authors Kirill Katsuba, Oleg Rudenko, Egor Bugaev et al.
Why read it

Neural surrogates for engineering models are often trained on large collections of simulated solutions. We investigate whether physics-informed neural networks (PINNs) can achieve accurate predictions

arXiv · 2611.12424 ↗ physics-informedpinnpinns
9

On the Global Convergence of Stochastic Adam for Physics-Informed Neural Networks

Authors Yihang Gao
Why read it

The Adam optimizer is widely used to train neural networks with highly nonlinear and nonconvex objective functions. Remarkably, Adam often drives the empirical training loss nearly to zero. This pheno

arXiv · 2611.11905 ↗ physics-informedpinnpinns
10

ALETHEIA: A Multi-Frequency Eddy Current Pulsed Thermography Dataset for Neural Operator Learning in Nondestructive Testing

Authors Changbin Sun, Jie Xiao, Xiaotian Chen et al. 62 pages, 19 figures
Why read it

Learning neural solvers for spatiotemporal partial differential equations (PDEs) under real-world constraints remains a key challenge in scientific machine learning, especially for inverse tasks with

arXiv · 2611.11252 ↗ neural operatorscientific machine learningpdepartial differential equation

Overview

This week collects 10 preprints across physics-informed, pinn, pinns, all circling the same question: how physics-constrained learning stays reliable once the problem reaches realistic solver scale. Each entry below carries a short summary and the reason it is worth reading.

1. Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs

Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, providing a wide ecosystem of novel methods. However, one frequent limit

2. CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs

This paper introduces COUPLED FLOW, a new neural operator learning framework for multi-physics PDE systems that captures the co-evolution of multiple physical processes by modeling their cross-process

3. Convergence analysis of physics-informed neural networks for subdiffusion

Physics-informed neural networks have emerged as mesh-free solvers for partial differential equations, yet their rigorous convergence theory for time-fractional problems remains limited. We present a

4. Parameterized Physics-Informed Neural Networks for Efficient Simulation of Embedded Microfluidic Chip Cooling

Embedded microfluidic cooling is a promising technology for dissipating the intense heat generated by high-performance electronic chips. However, the design and optimization of such coolers impose pro

5. Rethinking How to Leverage Cheap Physics for Data-Efficient Neural Operators

Neural operators learn mappings from PDE inputs, such as initial conditions and coefficient fields, to the corresponding solutions. Once trained, they can rapidly predict solutions for new inputs. How

6. A systematic comparison of physics-informed neural networks and mechanistic models for epidemic modeling and forecasting

Physics-Informed Neural Networks (PINNs) have recently been applied to epidemic modeling and forecasting with promising results. These methods integrate mechanistic knowledge with data-driven learning

7. Well-Balanced WE-PINNs for the Shallow Water Equations over Smooth and Discontinuous Bathymetries

Physics-informed neural networks (PINNs) solve partial differential equations without a mesh, but they do not in general preserve the steady states that well-balanced schemes reproduce exactly. We pre

8. Physics-informed neural networks in the small-data regime: A controlled comparison with classical PDE surrogates

Neural surrogates for engineering models are often trained on large collections of simulated solutions. We investigate whether physics-informed neural networks (PINNs) can achieve accurate predictions

9. On the Global Convergence of Stochastic Adam for Physics-Informed Neural Networks

The Adam optimizer is widely used to train neural networks with highly nonlinear and nonconvex objective functions. Remarkably, Adam often drives the empirical training loss nearly to zero. This pheno

10. ALETHEIA: A Multi-Frequency Eddy Current Pulsed Thermography Dataset for Neural Operator Learning in Nondestructive Testing

Learning neural solvers for spatiotemporal partial differential equations (PDEs) under real-world constraints remains a key challenge in scientific machine learning, especially for inverse tasks with