Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study addresses the challenge of gas unmixing in machine olfaction by formulating it as a multi-physics-constrained inverse problem, utilizing Maxwell–Stefan multicomponent transport equations and competitive adsorption dynamics. The authors introduce UnMixNet, a physics-closed graph neural network that integrates these complex physical processes into an end-to-end gas unmixing framework, achieving local and differentiable inference. Evaluations demonstrate that UnMixNet significantly enhances single-odor recognition and generalization capabilities in dynamic gas mixtures, outperforming traditional methods and aligning closely with ground truth data.
UnMixNet not only solves gas unmixing more accurately but also embeds physical laws into the inference process, leading to superior performance in dynamic environments.
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.