Machine learning to identify variables in thermodynamically small systems

Ford, David M.; Dendukuri, Aditya; Kalyoncu, Gülce; Luu, Khoa; Patitz, Matthew J.

doi:10.1016/j.compchemeng.2020.106989

Cited by 2 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…272,273 Diffusion Maps can identify thermodynamic variables through the eigendecomposition of the particles affinity matrix. 274 Macroscopic transport phenomena, at the boundary of chemistry and physics, 275 involve gradual information spread within the component network, 276 while the synchronization of CRN 277 or particle concentration field 278 harmonizes dynamics. Coupled diffusion-reaction phenomena may drive self-organizing spatiotemporal patterns 279 found in combustion, biology, or catalysis, 280 such as "chemical turbulence".…”

Section: Continuum-scale Chemical Mixturesmentioning

confidence: 99%

“…Gibbs introduced the term “phase”, used in section , to represent a continuum of spatially homogeneous thermodynamic states governed by a specific fundamental equation . Small systems may behave differently from macroscopic ones due to system subdivision and quantum interactions, leading occasionally to the violation of extensivity and the Gibbs–Duhem relation. , Diffusion Maps can identify thermodynamic variables through the eigendecomposition of the particles affinity matrix . Macroscopic transport phenomena, at the boundary of chemistry and physics, involve gradual information spread within the component network, while the synchronization of CRN or particle concentration field harmonizes dynamics.…”

Section: Continuum-scale Chemical Mixturesmentioning

confidence: 99%

See 1 more Smart Citation

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Nicolle,

Deng,

Ihme

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the ’recomposition’ of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure–Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.

show abstract