Searcharxiv⌕ Search

arXiv subjects

Jeffrey G. Ethier

Publications and source records attributed to Jeffrey G. Ethier.

5 recordsLinked to original sources

Leveraging Large Language Models to Predict Atomic Oxygen Erosion of Polymers in Low Earth Orbit

Low Earth orbit (LEO), home to most active satellites, is projected to undergo a debris-fragmentation cascade known as Kessler Syndrome. In light of this eventuality, it is imperative to maximize the operational lifetime of LEO satellites. Instrumental to this goal is the development of next-generation polymeric materials with improved resistance to atomic oxygen (AO) erosion. Because genuine LEO exposure experiments are prohibitively expensive and LEO conditions are difficult to reproduce in the laboratory, data-driven approaches offer a promising alternative for accelerating materials discovery. Here, we develop a fine-tuned large language model (LLM) based on OpenAI's GPT-4o to predict the AO erosion yield ($E_y$) of polymers using a curated dataset of 201 measurements compiled from multiple NASA LEO exposure missions. The model achieves an order of magnitude error (OME) of 0.154 and a log-scaled coefficient of determination (log-$R^2$) of 0.719, outperforming conventional machine learning approaches while eliminating the need for extensive feature engineering. Notably, incorporating macroscopic descriptors such as film thickness and layering did not improve predictive performance, suggesting that AO erosion is governed primarily by chemical and environmental variables rather than bulk structural characteristics. This finding underscores the importance of chemically informed polymer design in developing materials with improved AO resistance, while demonstrating the ability of modern LLMs to effectively extract chemically meaningful relationships even when data is limited. Beyond its predictive accuracy, the proposed framework provides a scalable platform for rapidly screening candidate polymers, reducing reliance on costly spaceflight experiments.

physics.geo-ph↗

Multi-scale Modeling of the Electro-viscoelasticity of Charged Polymers in Combined Flow and Electric Fields

The behavior of polymers in combined flow and electric fields underlies many manufacturing processes but remains poorly understood. We model charged polymers across scales, extending the Rouse model for a bead-spring chain to include a charge density distributed along the polymer chain, and derive the viscoelastic stress under homogeneous shear and electric fields. The viscosity increase depends on field-flow orientation, scaling quadratically with select components of the electric field strength, modulated by the effective charge sequence relaxation time and dielectric constant. Inspired by this, a new continuum model--the upper-convected electro-Maxwell (UCEM) model--is proposed. It resembles an upper-convected Maxwell model with polarization stresses expressed through an electric field dyadic subject to upper-convected time derivatives. The UCEM model captures the electro-rheological coupling for unentangled, salt-free melts at low shear rates and remains predictive into the moderately nonlinear regime ($Wi \approx 2-4$) provided its parameters are treated as state-dependent material functions. We analyze the constitutive response for various flows under applied electric fields, discussing model limitations and demonstrating compliance with the second law of thermodynamics. Coarse-grained molecular dynamics (MD) simulations of Kremer-Grest chains confirm distinct relaxation timescales for chain dynamics versus charge redistribution, consistent with UCEM predictions. Critically, the upper-convected time derivative of the electric field dyadic is required in the stress evolution to account for stretching and rotation of charge pairs in flow. This reproduces the viscosity scaling observed in both the Rouse and MD results, whereas standard continuum formulations without these terms fail to capture this scaling.

cond-mat.soft↗

Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers

Modern optimization in experimental chemistry employs algorithmic search through black-box parameter spaces. Here we demonstrate that pre-trained knowledge in large language models (LLMs) fundamentally changes this paradigm. Using six fully enumerated categorical reaction datasets (768-5,684 experiments), we benchmark LLM-guided optimization (LLM-GO) against Bayesian optimization (BO) and random sampling. Frontier LLMs consistently match or exceed BO performance across five single-objective datasets, with advantages growing as parameter complexity increases and high-performing conditions become scarce (<5% of space). BO retains superiority only for explicit multi-objective trade-offs. To understand these contrasting behaviors, we introduce a topology-agnostic information theory framework quantifying sampling diversity throughout optimization campaigns. This analysis reveals that LLMs maintain systematically higher exploration Shannon entropy than BO across all datasets while achieving superior performance, with advantages most pronounced in solution-scarce parameter spaces where high-entropy exploration typically fails-suggesting that pre-trained domain knowledge enables more effective navigation of chemical parameter space rather than replacing structured exploration strategies. To enable transparent benchmarking and community validation, we release Iron Mind (https://gomes.andrew.cmu.edu/iron-mind), a no-code platform for side-by-side evaluation of human, algorithmic, and LLM optimization campaigns with public leaderboards and complete trajectories. Our findings establish that LLM-GO excels precisely where traditional methods struggle: complex categorical spaces requiring domain understanding rather than mathematical optimization.

cs.LG↗

Pessimistic asynchronous sampling in high-cost Bayesian optimization

Asynchronous Bayesian optimization is a recently implemented technique that allows for parallel operation of experimental systems and disjointed workflows. Contrasting with serial Bayesian optimization which individually selects experiments one at a time after conducting a measurement for each experiment, asynchronous policies sequentially assign multiple experiments before measurements can be taken and evaluate new measurements continuously as they are made available. This technique allows for faster data generation and therefore faster optimization of an experimental space. This work extends the capabilities of asynchronous optimization methods beyond prior studies by evaluating four additional policies that incorporate pessimistic predictions in the training data set. Combined with a conventional policy that uses model predictions, the five total policies were evaluated in a simulated environment and benchmarked with serial sampling. Under some conditions and parameter space dimensionalities, the pessimistic prediction asynchronous policy reached optimum experimental conditions in significantly fewer experiments than equivalent serial policies and proved to be less susceptible to convergence onto local optima at higher dimensions. Without accounting for the faster sampling rate, the pessimistic asynchronous algorithm presented in this work could result in more efficient algorithm driven optimization of high-cost experimental spaces. Accounting for sampling rate, the presented asynchronous algorithm could allow for faster optimization in experimental spaces where multiple experiments can be run before results are collected.

cs.LG↗

Modeling Multi-Step Scientific Processes with Graph Transformer Networks

This work presents the use of graph learning for the prediction of multi-step experimental outcomes for applications across experimental research, including material science, chemistry, and biology. The viability of geometric learning for regression tasks was benchmarked against a collection of linear models through a combination of simulated and real-world data training studies. First, a selection of five arbitrarily designed multi-step surrogate functions were developed to reflect various features commonly found within experimental processes. A graph transformer network outperformed all tested linear models in scenarios that featured hidden interactions between process steps and sequence dependent features, while retaining equivalent performance in sequence agnostic scenarios. Then, a similar comparison was applied to real-world literature data on algorithm guided colloidal atomic layer deposition. Using the complete reaction sequence as training data, the graph neural network outperformed all linear models in predicting the three spectral properties for most training set sizes. Further implementation of graph neural networks and geometric representation of scientific processes for the prediction of experiment outcomes could lead to algorithm driven navigation of higher dimension parameter spaces and efficient exploration of more dynamic systems.

cs.LG↗