Machine learning for materials science: Barriers to broader adoption

Boyce, Brad Lee; Dingreville, Remi Philippe Michel; Desai, Saaketh; Walker, Elise; Shilt, Troy; Bassett, Kimberly L.; Wixom, Ryan R.; Stebner, Aaron P.; Arróyave, Raymundo; Hattrick‐Simpers, Jason; Warren, James A.

doi:10.1016/j.matt.2023.03.028

Cited by 7 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Boyce et al posed the question: Is machine learning for every problem? 64 While the utility of using ML has been shown for predicting current in a galvanic couple, the use of FEM and ML models may not be applicable or useful in all corrosion scenarios. Despite this, it is possible that FEM modeling can be used to supplement experimental data sets that have small sizes.…”

Section: Discussion: Application Of Machine Learning To Corrosionmentioning

confidence: 99%

Accelerating FEM-Based Corrosion Predictions Using Machine Learning

Montes de Oca Zapiain,

Maestas,

Roop

et al. 2024

J. Electrochem. Soc.

View full text Add to dashboard Cite

Atmospheric corrosion of metallic parts is a widespread materials degradation phenomena that is challenging to predict given its dependence on many factors (e.g. environmental, physiochemical, and part geometry). For materials with long expected service lives, accurately predicting the degree to which corrosion will degrade part performance is especially difficult due to the stochastic nature of corrosion damage spread across years or decades of service. The finite element method (FEM) is a computational technique capable of providing accurate estimates of corrosion rate by numerically solving complex differential equations characterizing this phenomena. Nevertheless, given the iterative nature of FEM and the computational expense required to solve these complex equations, FEM is ill-equipped for an efficient exploration of the design space to identify factors that accelerate or deter corrosion, despite its accuracy. In this work, a machine-learning-based surrogate model capable of providing accurate predictions of corrosion with significant computational savings is introduced. Specifically, this work leverages AdaBoosted Decision trees to provide an accurate estimate of corrosion current per width given different values of temperature, water layer thickness, molarity of the solution, and the length of the cathode for a galvanic couple of aluminum and stainless steel.

show abstract

Section: Discussion: Application Of Machine Learning To Corrosionmentioning

confidence: 99%

Accelerating FEM-Based Corrosion Predictions Using Machine Learning

Montes de Oca Zapiain,

Maestas,

Roop

et al. 2024

J. Electrochem. Soc.

View full text Add to dashboard Cite

show abstract

“…What types of restrictions arise due to a proposed modeling approach. For example, all three of the approaches studied in this paper require data which have been sampled on a regular grid 7 . Similarly, the LMKS framework currently does not directly account for the dependence of the influence coefficients on the PDE coefficients.…”

Section: Discussionmentioning

confidence: 99%

“…Machine learning is transforming computational materials science by offering tools to accelerate forward simulations [1,2], unveil hidden patterns [3,4], and ultimately support computational pipelines for all sorts of materials and mechanical analyses [5][6][7]. Amongst the most popular computational materials science techniques, the phase-field method, a powerful approach for modeling microstructure evolution [8], is witnessing rapid growth driven by numerous developments integrating machine-learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…For example, the accuracy and robustness of machine-learned phase-field models depend heavily on the quality and specifics of the training dataset. However, because engineering training data is expensive and difficult to acquire [7,25], the training dataset also defines much of a proposed framework's overhead cost. In other words, bigger is not necessarily better.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Benchmarking machine learning strategies for phase-field problems

Dingreville,

Roberston,

Attari

et al. 2024

Modelling Simul. Mater. Sci. Eng.

View full text Add to dashboard Cite

We present a comprehensive benchmarking framework for evaluating machine-learning approaches applied to phase-field problems. This framework focuses on four key analysis areas crucial for assessing the performance of such approaches in a systematic and structured way. Firstly, interpolation tasks are examined to identify trends in prediction accuracy and accumulation of error over simulation time. Secondly, extrapolation tasks are also evaluated according to the same metrics. Thirdly, the relationship between model performance and data requirements is investigated to understand the impact on predictions and robustness of these approaches. Finally, systematic errors are analyzed to identify specific events or inadvertent rare events triggering high errors. Quantitative metrics evaluating the local and global description of the microstructure evolution, along with other scalar metrics representative of phase-field problems, are used across these four analysis areas. This benchmarking framework provides a path to evaluate the effectiveness and limitations of machine-learning strategies applied to phase-field problems, ultimately facilitating their practical application.

show abstract

“…However, some ML approaches are specifically geared toward dealing with data-poor optimization campaigns, which are often prevalent in experimental materials science, let alone electrocatalysis. 24 One active learning approach is Bayesian optimization (BO), an adaptive sampling strategy relying on an iterative optimization process to find the global optimum in a predefined parameter space. 25 The BO algorithm consists of the following steps: (i) initialization, in which some observations are collected, building the starting point for the optimization process.…”

Section: Introductionmentioning

confidence: 99%