Mass Conservation on Rails -- Rethinking Physics-Informed Learning of Ice Flow Vector Fields

• URL: http://arxiv.org/abs/2510.06286v1
• Date: Tue, 07 Oct 2025 00:41:01 GMT
• Title: Mass Conservation on Rails -- Rethinking Physics-Informed Learning of Ice Flow Vector Fields
• Authors: Kim Bente, Roman Marchant, Fabio Ramos,
• Abstract summary: We propose neural networks (NNs) that enforce local mass conservation exactly via a vector calculus trick.<n>Our comparison of NNs, PINNs, and unconstrained NNs on ice flux over Byrd Glacier suggests that "mass conservation on rails" yields more reliable estimates.
• Score: 2.994635007851795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To reliably project future sea level rise, ice sheet models require inputs that respect physics. Embedding physical principles like mass conservation into models that interpolate Antarctic ice flow vector fields from sparse & noisy measurements not only promotes physical adherence but can also improve accuracy and robustness. While physics-informed neural networks (PINNs) impose physics as soft penalties, offering flexibility but no physical guarantees, we instead propose divergence-free neural networks (dfNNs), which enforce local mass conservation exactly via a vector calculus trick. Our comparison of dfNNs, PINNs, and unconstrained NNs on ice flux interpolation over Byrd Glacier suggests that "mass conservation on rails" yields more reliable estimates, and that directional guidance, a learning strategy leveraging continent-wide satellite velocity data, boosts performance across models.

Related papers

• PhysE-Inv: A Physics-Encoded Inverse Modeling approach for Arctic Snow Depth Prediction [0.16206783799607727]
  We introduce PhysE-Inv, a novel framework that integrates a sophisticated sequential architecture, an LSTM-Decoder with Multi-head Attention and physics-guided contrastive learning, with physics-guided inference.<n> PhysE-Inv significantly improves prediction performance, reducing error by 20% while demonstrating superior physical consistency and resilience to data sparsity compared to empirical methods.<n>This approach pioneers a path for noise-tolerant, interpretable inverse modeling, with wide applicability in geospatial and cryospheric domains.
  arXiv  Detail & Related papers  (2026-01-23T00:43:51Z)
• Physics-Informed Spiking Neural Networks via Conservative Flux Quantization [6.328961717118723]
  Physics-Informed Neural Networks (PINNs) combine data-driven learning with physics-based constraints to ensure the model's predictions are with underlying physical principles.<n> PINNs are energy-intensive and struggle to strictly enforce physical conservation laws.<n>This paper introduces a novel Physics-Informed Spiking Neural Network (PISNN) framework.
  arXiv  Detail & Related papers  (2025-11-26T13:35:50Z)
• Prediction of Sea Ice Velocity and Concentration in the Arctic Ocean using Physics-informed Neural Network [0.0]
  We develop physics-informed neural network (PINN) strategies to integrate physical knowledge of sea ice into the machine learning model.<n>Our PINN model outperforms the fully data-driven model in the daily predictions of sea ice velocity (SIV) and sea ice concentration (SIC)<n>The PINN approach particularly improves SIC predictions in melting and early freezing seasons and near fast-moving ice regions.
  arXiv  Detail & Related papers  (2025-10-20T17:10:01Z)
• Physics-Informed Neural Networks for Vessel Trajectory Prediction: Learning Time-Discretized Kinematic Dynamics via Finite Differences [1.740114131842074]
  Accurate vessel trajectory prediction is crucial for navigational safety, route optimization, traffic management, search and rescue operations, and autonomous navigation.<n>Traditional data-driven models lack real-world physical constraints, leading to forecasts that disobey vessel motion dynamics.<n>We propose a Physics-Informed Neural Network (PINN) approach for trajectory prediction that integrates a streamlined kinematic model for vessel motion into the neural network training process.
  arXiv  Detail & Related papers  (2025-05-22T15:09:25Z)
• Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks [1.1879716317856948]
  Divergence-free symmetric tensors (DFSTs) are fundamental in continuum mechanics.<n>We introduce a novel neural architecture that inherently satisfies the DFST condition to machine precision.<n>This work is the first to use DFSTs as an inductive bias in neural PDE surrogates.
  arXiv  Detail & Related papers  (2025-03-02T06:24:16Z)
• On the importance of learning non-local dynamics for stable data-driven climate modeling: A 1D gravity wave-QBO testbed [0.0]
  Machine learning (ML) techniques have shown promise in learning subgrid-scale parameterizations for climate models. However, a major problem with data-driven parameterizations is model instability. Here, we combine ML theory and climate physics to address a source of instability in NN-based parameterization.
  arXiv  Detail & Related papers  (2024-07-07T01:15:52Z)
• Physics-Informed Neural Networks with Hard Linear Equality Constraints [9.101849365688905]
  This work proposes a novel physics-informed neural network, KKT-hPINN, which rigorously guarantees hard linear equality constraints. Experiments on Aspen models of a stirred-tank reactor unit, an extractive distillation subsystem, and a chemical plant demonstrate that this model can further enhance the prediction accuracy.
  arXiv  Detail & Related papers  (2024-02-11T17:40:26Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
  This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling. We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
  arXiv  Detail & Related papers  (2023-02-11T21:07:30Z)
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks [56.35403810762512]
  Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. We study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method.
  arXiv  Detail & Related papers  (2023-02-01T04:22:59Z)
• Simultaneous boundary shape estimation and velocity field de-noising in Magnetic Resonance Velocimetry using Physics-informed Neural Networks [70.7321040534471]
  Magnetic resonance velocimetry (MRV) is a non-invasive technique widely used in medicine and engineering to measure the velocity field of a fluid. Previous studies have required the shape of the boundary (for example, a blood vessel) to be known a priori. We present a physics-informed neural network that instead uses the noisy MRV data alone to infer the most likely boundary shape and de-noised velocity field.
  arXiv  Detail & Related papers  (2021-07-16T12:56:09Z)
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations [86.41674945012369]
  We develop a scalable and expressive Graph Neural Networks model, ForceNet, to approximate atomic forces. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs.
  arXiv  Detail & Related papers  (2021-03-02T03:09:06Z)
• Learning Unknown Physics of non-Newtonian Fluids [56.9557910899739]
  We extend the physics-informed neural network (PINN) method to learn viscosity models of two non-Newtonian systems. The PINN-inferred viscosity models agree with the empirical models for shear rates with large absolute values but deviate for shear rates near zero. We use the PINN method to solve the momentum conservation equation for non-Newtonian fluid flow using only the boundary conditions.
  arXiv  Detail & Related papers  (2020-08-26T20:41:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.