Physics Closure Matters for Machine Olfaction: A Maxwell-Stefan Graph Solver for Identifiable Dynamic Gas Unmixing

• URL: http://arxiv.org/abs/2607.18544v2
• Date: Sat, 25 Jul 2026 21:08:24 GMT
• Title: Physics Closure Matters for Machine Olfaction: A Maxwell-Stefan Graph Solver for Identifiable Dynamic Gas Unmixing
• Abstract summary: We formulate gas unmixing as a multi-physics-constrained inverse problem governed by Maxwell--Stefan multicomponent transport PDEs.<n>We propose UnMixNet, a physics-closed graph neural solver that embeds this multi-physics forward process into end-to-end gas unmixing.<n>UnMixNet discretizes Maxwell--Stefan cross-diffusion on spatial graphs and formulates the multicomponent flux on each edge.
• Score: 6.156377010595533
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Machine olfaction for gas unmixing is an underconstrained inverse problem in which gas compositions must be inferred from low-dimensional, delayed, and entangled sensor responses produced by interacting chemical transport, surface adsorption, and sensor transduction. One of the key obstacles is physics closure misspecification, where a neural network is designed to fit sensor traces rather than infer a physically closed olfactory process. In this work, we formulate gas unmixing as a multi-physics-constrained inverse problem governed by Maxwell--Stefan multicomponent transport PDEs, competitive adsorption ODEs, and nonlinear sensor transduction ODEs. Directly solving such a high-dimensional coupled system is computationally expensive and often numerically unstable. To this end, we propose UnMixNet, a physics-closed graph neural solver that embeds this multi-physics forward process into end-to-end gas unmixing. UnMixNet discretizes Maxwell--Stefan cross-diffusion on spatial graphs and formulates the multicomponent flux on each edge. This design enables local, differentiable, and flux-conservative inference for multicomponent cross-diffusion. Evaluations on SmellNet show improved single-odor recognition, seen-mixture unmixing, and unseen-mixture generalization. In addition, an external validation on UCI Dynamic Gas Mixtures shows that the inferred concentration process agrees with ground truth concentration set points under dynamic transitions. Process-consistency diagnostics further show that the proposed model learns transferable dynamic physical fingerprints that better satisfies transport, conservation, adsorption, and readout closure.

Related papers

• Fluid-DiT: Graph-Free Diffusion Transformers for Fluid Flow Simulations Learning [50.053186229257555]
  We propose a Graph-Free Diffusion Transformer that replaces graph message passing with attention-based denoising.<n>By leveraging the transformer's global receptive field, Fluid-DiT naturally captures both local flow structures and long-range correlations.<n>It consistently outperforms graph-based diffusion baselines in both sample quality and distributional accuracy.
  arXiv  Detail & Related papers  (2026-08-07T12:28:45Z)
• Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations [58.079925240809644]
  We propose an end-to-end graph neural surrogate tailored to CO$$ibility plume migration forecasting in geological storage.<n>The method is evaluated on the SPE11A benchmark, a well-known industry test case designed to assess CO$$ storage scenarios.<n>The proposed model produces competitive forecasts of gas saturation and liquid-phase density, with cumulative errors that remain moderate over extended forecasting horizons.
  arXiv  Detail & Related papers  (2026-06-15T18:19:17Z)
• WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer [107.36949516442782]
  We present a learning-based particle simulator built on a single transformer architecture to model cloth, elastic solds, Newtonian and non-Newtonian fluids, granular materials, and molecular dynamics.
  arXiv  Detail & Related papers  (2026-05-14T18:18:12Z)
• Physics-Guided Concentration Inference from Resistance Transients in a Mixed-Phase SnO-SnO$_2$ Carbon Monoxide Sensor with p-n Switching [0.0]
  This work presents a physics-guided machine-learning framework for carbon monoxide concentration inference from experimentally measured resistance transients.<n> Cycle-level transient responses are represented through physically interpretable descriptors.<n>We show that p-type sensing is particularly favorable for classification, whereas n-type sensing is more favorable for high-fidelity regression.
  arXiv  Detail & Related papers  (2026-05-13T10:37:32Z)
• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition [49.955269674859004]
  This paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to align model capacity with signal complexity.<n>Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement.<n>A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency.
  arXiv  Detail & Related papers  (2026-01-19T07:57:52Z)
• A machine-learned expression for the excess Gibbs energy [15.799043135621565]
  The excess Gibbs energy plays a central role in chemical engineering and chemistry, providing a basis for modeling the thermodynamic properties of liquid mixtures.<n>In this work, we address this challenge by integrating physical laws as hard constraints within a flexible neural network.<n>The resulting model, HANNA, was trained end-to-end on an extensive experimental dataset for binary mixtures from the Dortmund Data Bank.
  arXiv  Detail & Related papers  (2025-09-08T09:47:03Z)
• NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements [7.704598780320887]
  This study introduces NeuroSEM, a hybrid framework integrating PINNs with the high-fidelity Spectral Element Method (SEM) solver, Nektar++. NeuroSEM leverages the strengths of both PINNs and SEM, providing robust solutions for multiphysics problems. We demonstrate the efficiency and accuracy of NeuroSEM for thermal convection in cavity flow and flow past a cylinder.
  arXiv  Detail & Related papers  (2024-07-30T22:01:14Z)
• Machine learning of hidden variables in multiscale fluid simulation [77.34726150561087]
  Solving fluid dynamics equations often requires the use of closure relations that account for missing microphysics. In our study, a partial differential equation simulator that is end-to-end differentiable is used to train judiciously placed neural networks. We show that this method enables an equation based approach to reproduce non-linear, large Knudsen number plasma physics.
  arXiv  Detail & Related papers  (2023-06-19T06:02:53Z)
• Data-driven framework for input/output lookup tables reduction -- with application to hypersonic flows in chemical non-equilibrium [0.0]
  We present a novel machine learning technique to extract a reduced thermochemical model for reacting hypersonic flows simulation. The method is validated and benchmarked on a simulation of a hypersonic flat-plate boundary layer with finite-rate chemistry. Substituting Mutation++ with the light-weight, machine-learned alternative improves the performance of the solver by 50% while maintaining overall accuracy.
  arXiv  Detail & Related papers  (2022-10-09T14:03:26Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)
• Generalized Discrete Truncated Wigner Approximation for Nonadiabtic Quantum-Classical Dynamics [0.0]
  We introduce a linearized semiclassical method, the generalized discrete truncated Wigner approximation (GDTWA) GDTWA samples the electron degrees of freedom in a discrete phase space, and forbids an unphysical growth of electronic state populations. Our results suggest that the method can be very adequate to treat challenging nonadiabatic dynamics problems in chemistry and related fields.
  arXiv  Detail & Related papers  (2021-04-14T21:53:35Z)

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.