Data-driven design of polymer-based biomaterials: high-throughput simulation, experimentation, and machine learning

RA Patel, MA Webb - ACS Applied Bio Materials, 2023 - ACS Publications
Polymers, with the capacity to tunably alter properties and response based on manipulation
of their chemical characteristics, are attractive components in biomaterials. Nevertheless …

Hybrid magnetorheological elastomers enable versatile soft actuators

MA Moreno-Mateos, M Hossain, P Steinmann… - npj Computational …, 2022 - nature.com
Recent advances in magnetorheological elastomers (MREs) have posed the question on
whether the combination of both soft-and hard-magnetic particles may open new routes to …

Bayesian optimization of catalysts with in-context learning

MC Ramos, SS Michtavy, MD Porosoff… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs) are able to do accurate classification with zero or only a few
examples (in-context learning). We show a prompting system that enables regression with …

Machine learning optimization of lignin properties in green biorefineries

J Lofgren, D Tarasov, T Koitto, P Rinke… - ACS Sustainable …, 2022 - ACS Publications
Novel biorefineries could transform lignin, an abundant biopolymer, from side-stream waste
to high-value-added byproducts at their site of production and with minimal experiments …

Bayesian Optimization of photonic curing process for flexible perovskite photovoltaic devices

W Xu, Z Liu, RT Piper, JWP Hsu - Solar Energy Materials and Solar Cells, 2023 - Elsevier
Photonic curing is a thin-film processing technique that can enable high-throughput
perovskite solar cell (PSC) manufacturing. However, photonic curing has many variables …

Bayesian design optimization of biomimetic soft actuators

B Kaczmarski, DE Moulton, A Goriely, E Kuhl - Computer Methods in …, 2023 - Elsevier
The design of versatile soft actuators remains a challenging task, as it is a complex trade-off
between robotic adaptability and structural complexity. Recently, researchers have used …

Bayesian coarsening: rapid tuning of polymer model parameters

H Weeratunge, D Robe, A Menzel, AW Phillips… - Rheologica Acta, 2023 - Springer
A protocol based on Bayesian optimization is demonstrated for determining model
parameters in a coarse-grained polymer simulation. This process takes as input the …

Mapping pareto fronts for efficient multi-objective materials discovery

A Low, YF Lim, K Hippalgaonkar… - Authorea …, 2022 - advance.sagepub.com
With advancements in automation and high-throughput techniques, complex materials
discovery with multiple conflicting objectives can now be tackled in experimental labs. Given …

[HTML][HTML] A machine learning approach to automate ductile damage parameter selection using finite element simulations

AN O'Connor, PG Mongan, NP O'Dowd - European Journal of Mechanics-A …, 2024 - Elsevier
Ductile damage models require constitutive model parameter values that are difficult to
derive experimentally or analytically. The calibration procedure for ductile damage model …

Uncertainty-aware mixed-variable machine learning for materials design

H Zhang, W Chen, A Iyer, DW Apley, W Chen - Scientific reports, 2022 - nature.com
Data-driven design shows the promise of accelerating materials discovery but is challenging
due to the prohibitive cost of searching the vast design space of chemistry, structure, and …