An Explainable AI Model for Binary LJ Fluids

2025-02-24

AI Summary

This work addresses the challenge of generalizing radial distribution function (RDF) predictions for binary Lennard-Jones fluids across unseen temperatures and compositions. Methodologically, we propose an interpretable deep learning framework trained on molecular dynamics simulation data: RDFs are discretized to reduce output dimensionality, and physically informed features—such as particle size ratio—are explicitly incorporated into a supervised neural network architecture. Crucially, we quantitatively uncover the higher-order nonlinear influence of size ratio on local structural ordering—a finding previously unreported. The model achieves high accuracy (mean relative error <3.2%) even outside the training temperature range, successfully predicting RDFs for unobserved compositions and across broad temperature intervals. Moreover, it identifies failure boundaries associated with physical mechanism transitions (e.g., structural crossovers). Compared to conventional empirical fitting, our approach delivers superior generalizability, accuracy, and physical interpretability—enabling mechanistic attribution of predictions to underlying thermodynamic and structural principles.

Technology Category

• Machine Learning: Structured Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Description Logics

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Lennard-Jones (LJ) fluids serve as an important theoretical framework for understanding molecular interactions. Binary LJ fluids, where two distinct species of particles interact based on the LJ potential, exhibit rich phase behavior and provide valuable insights of complex fluid mixtures. Here we report the construction and utility of an artificial intelligence (AI) model for binary LJ fluids, focusing on their effectiveness in predicting radial distribution functions (RDFs) across a range of conditions. The RDFs of a binary mixture with varying compositions and temperatures are collected from molecular dynamics (MD) simulations to establish and validate the AI model. In this AI pipeline, RDFs are discretized in order to reduce the output dimension of the model. This, in turn, improves the efficacy, and reduce the complexity of an AI RDF model. The model is shown to predict RDFs for many unknown mixtures very accurately, especially outside the training temperature range. Our analysis suggests that the particle size ratio has a higher order impact on the microstructure of a binary mixture. We also highlight the areas where the fidelity of the AI model is low when encountering new regimes with different underlying physics.

Problem

• Predicts radial distribution functions for binary LJ fluids
• Analyzes impact of particle size ratio on mixture microstructure
• Identifies limitations in AI model fidelity in new regimes

Innovation

• Uses AI to predict radial distribution functions.
• Discretizes RDFs to reduce model complexity.
• Validates model with molecular dynamics simulations.