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
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
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
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
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
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
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
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
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
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
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
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