Tag
The paper proposes a physics-informed deep learning approach for lithium-ion battery state-of-health estimation using incomplete discharge curves, achieving high accuracy and enabling real-time degradation trend prognosis.
This paper proposes FALM-PINN, an alternating Levenberg-Marquardt training framework for physics-informed neural networks that uses Fourier-enhanced features to address spectral bias and representation-coefficient coupling, achieving up to two orders of magnitude lower errors on high-frequency and nonlinear PDEs.
This paper proposes SCORE, a self-concordance-inspired quasi-Newton method for training physics-informed neural networks (PINNs). It uses a decrement-coupled shifted secant geometry to improve final accuracy on nonlinear PDE benchmarks without requiring Hessian computations.
This paper introduces GeoID-PINN, a physics-informed neural network for regional epidemic inference that incorporates geographic coupling via a spatial source-composition matrix. It demonstrates that accurate trajectory forecasts do not guarantee correct recovery of regional dependence structures, using simulations and COVID-19 data from Louisiana counties.
The paper introduces a hybrid quantum-classical framework enhancing Quantum Physics-Informed Neural Networks (QPINNs) with adaptive collocation point sampling and loss-aware attention for solving differential equations, achieving significant accuracy improvements in fluid dynamics and reaction-diffusion benchmarks.
This paper introduces feature interaction modules based on factorization machines into physics-informed neural networks and neural operators (FM-PINN, FM-Operator, FM-DeepONet) to better capture spatio-temporal variable couplings for solving parameterized PDEs, showing accuracy gains particularly on shock-dominated equations.
EvoPINN is an agentic framework that reformulates PINN development as an execution-grounded algorithm discovery problem, using an LLM agent to propose programmatic modifications. It autonomously discovers PDE-specialized learning algorithms, including a novel architecture called SLRC-PINN, which outperforms baselines across diverse PDE regimes.
This paper traces step-by-step how PyTorch's automatic differentiation engine computes gradients for Physics-Informed Neural Network training, including the two levels of differentiation needed for physics residuals and parameter gradients, using a simple MLP and ODE example.
This paper presents a hybrid analytical-PINN model for simulating geothermal heat exchangers in heterogeneous subsurface, removing singularities and enabling efficient neural network training via an analytical correction approach.
This paper evaluates five model families for macroeconomic forecasting, finding that less-constrained models like ARIMA and Neural ODE outperform structurally-prioritized models like PINNs, highlighting that structural priors can act as misregularizers when mismatched.
This paper presents a physics-informed neural network (PINN) framework for modeling transient elastodynamic wave propagation in bimaterial systems, using a steel-aluminum specimen from a Split Hopkinson Pressure Bar. The PINN accurately predicts wave transmission and reflection, validated against high-fidelity finite-element simulations, and serves as a continuous surrogate model for elastodynamic analysis.
This work-in-progress paper proposes embedding a differentiable physics model into the PPO actor loss function to penalize anticipated safety violations in reinforcement learning, evaluated on a simulated 1-DoF helicopter system. The physics-informed soft regularizations reduce constraint violations while maintaining reliable target tracking.
This paper introduces DigiTurbine, a synthetic reliability-aware Physics-Informed Neural Network (PINN) benchmark for offshore wind turbine monopile support-structure monitoring, combining forward and inverse PINN with Bayesian prior-informed identification and FORM-based reliability screening.
This paper identifies a capacity-induced failure mode in physics-informed neural networks (PINNs) where overparameterized networks develop functional modularity that hinders convergence, and proposes Modular-Sparsity Synchronization (ModSync), a framework that penalizes task-exclusive connections to maintain cross-objective interaction and achieve state-of-the-art accuracy.
Korzhinskii-Net is a 2-D radial physics-informed neural network that couples Darcy flow, heat transport, and reaction kinetics for sub-surface mineral prospectivity modelling, outperforming classical baselines on five Russian ore provinces.
This paper diagnoses the loss landscape of gradient-based inversion for the Gray-Scott reaction-diffusion system, showing that direct backpropagation fails due to flat plateaus and sharp cliffs, while PINN components like residual loss smooth the landscape. The findings provide design implications for PINN-type methods.
This paper identifies a consistent three-regime structure in scientific machine learning models, showing that optimization effectiveness is regime-specific and can challenge conventional loss-landscape interpretations. It proposes a regime-aware diagnostic framework validated across PINNs, neural operators, and neural ODEs.
The paper introduces beignet, a PINN architecture that replaces random Fourier features with a trainable multi-resolution Fourier feature pyramid, achieving higher accuracy and computational efficiency on PDE benchmarks.
This paper introduces a novel uncertainty-aware PINN framework for flood inference from SAR data, addressing 'physics shock' by dynamically relaxing physical constraints in noisy regions. Evaluated on Sen1Floods11, the method achieves a 25% improvement in IoU and provides calibrated uncertainty bounds for operational disaster response.
This paper presents a physics-informed convolutional encoder–decoder network to predict pore-scale velocity fields from porous media geometry, and demonstrates that using network predictions to initialize Lattice-Boltzmann simulations accelerates convergence in over 90% of cases.