The Materials Simulation Toolkit for Machine learning (MAST-ML): An automated open source toolkit to accelerate data-driven materials research

Jacobs, Ryan; Mayeshiba, Tam; Afflerbach, Ben; Miles, Luke Harold; Williams, M. Diane; Turner, Martin; Finkel, Raphael A.; Morgan, Dane

doi:10.1016/j.commatsci.2020.109544

Cited by 44 publications

(32 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data contain 408 activation energies for 15 different hosts and are described in detail in Reference 35 (see the sidebar titled Online Availability of Data in This Review for data availability on Figshare). All the models were evaluated using the routines available in the scikit-learn package (155), and the model fits and analysis were automated using the Materials Simulation Toolkit for Machine Learning (MAST-ML) (https://github.com/uw-cmg/MAST-ML) (156).…”

Section: Example Of Assessing Model Errors and Domain Of Applicability Using Gaussian Process Regression And Random Forest Decision Tree mentioning

confidence: 99%

“…All of the models were evaluated using the routines available in the scikit-learn package, 156 and the model fits and analysis were automated using the Materials Simulation Toolkit for Machine Learning (MAST-ML). 157,158 To help assess the model domain of applicability, we explore a chemistry test where we consider Pd-X systems, where Pd is the host element and X is a dilute impurity taken from three sets (set 1 = 3d and 4d transition metals, set 2 = Col VIA elements except O, set 3 = elements from the first 2 rows on the periodic table). In this test we train the model with no Pd host data and then predict the errors for the 3 sets.…”

Section: Model Domain Of Applicability and Assessing Uncertainties In...mentioning

confidence: 99%

See 1 more Smart Citation

Opportunities and Challenges for Machine Learning in Materials Science

Morgan

Jacobs²

2020

Annu. Rev. Mater. Res.

Self Cite

220

127

View full text Add to dashboard Cite

Advances in machine learning have impacted myriad areas of materials science, such as the discovery of novel materials and the improvement of molecular simulations, with likely many more important developments to come. Given the rapid changes in this field, it is challenging to understand both the breadth of opportunities and the best practices for their use. In this review, we address aspects of both problems by providing an overview of the areas in which machine learning has recently had significant impact in materials science, and then we provide a more detailed discussion on determining the accuracy and domain of applicability of some common types of machine learning models. Finally, we discuss some opportunities and challenges for the materials community to fully utilize the capabilities of machine learning.

show abstract

Section: Example Of Assessing Model Errors and Domain Of Applicability Using Gaussian Process Regression And Random Forest Decision Tree mentioning

confidence: 99%

Section: Model Domain Of Applicability and Assessing Uncertainties In...mentioning

confidence: 99%

Opportunities and Challenges for Machine Learning in Materials Science

Morgan

Jacobs²

2020

Annu. Rev. Mater. Res.

Self Cite

220

127

View full text Add to dashboard Cite

show abstract

“…The model analysis and exploration were primarily performed with the MAterials Simulation Toolkit for Machine Learning (MAST-ML, version 3.x, University of Wisconsin-Madison Computational Materials Group, Madison, WI, USA.) [ 20 ], an open-source Python package with scikit-learn [ 19 ] library to automate machine learning workflows and model assessments. The hyperparameters ( α , γ ) of the GKRR model were optimized using a genetic algorithm (GA) with the five-fold cross validation (CV) root-mean-square error (RMSE) as the scoring metric.…”

Section: Methodsmentioning

confidence: 99%

Exploring Dielectric Constant and Dissipation Factor of LTCC Using Machine Learning

Liu

Huang

et al. 2021

Materials

View full text Add to dashboard Cite

Low-temperature co-fired ceramics (LTCCs) have been attracting attention due to rapid advances in wireless telecommunications. Low-dielectric-constant (Dk) and low-dissipation-factor (Df) LTCCs enable a low propagation delay and high signal quality. However, the wide ranges of glass, ceramic filler compositions, and processing features in fabricating LTCC make property modulating difficult via experimental trial-and-error approaches. In this study, we explored Dk and Df values of LTCCs using a machine learning method with a Gaussian kernel ridge regression model. A principal component analysis and k-means methods were initially performed to visually analyze data clustering and to reduce the dimension complexity. Model assessments, by using a five-fold cross-validation, residual analysis, and randomized test, suggest that the proposed Dk and Df models had some predictive ability, that the model selection was appropriate, and that the fittings were not just numerical due to a rather small data set. A cross-plot analysis and property contour plot were performed for the purpose of exploring potential LTCCs for real applications with Dk and Df values less than 10 and 2 × 10−3, respectively, at an operating frequency of 1 GHz. The proposed machine learning models can potentially be utilized to accelerate the design of technology-related LTCC systems.

show abstract

“…The machine learning models were built and validated with the MAterials Simulation Toolkit for Machine Learning MAST-ML utility [79], which uses numerical procedures as implemented in scikit-learn [80].…”

Section: Vibmentioning

confidence: 99%

Modified band alignment method to obtain hybrid functional accuracy from standard DFT: Application to defects in highly mismatched III-V:Bi alloys

Polak

Kudrawiec

Jacobs

et al. 2021

Phys. Rev. Materials

Self Cite

View full text Add to dashboard Cite

This paper provides an accurate theoretical defect energy database for pure and Bi-containing 111-V (111-V:Bi) materials and investigates efficient methods for high-throughput defect calculations based on corrections of results obtained with local and semi-local functionals. Point defects as well as nearest-neighbor and second-nearest-neighbor pair defects were investigated in charge states ranging from -5 to 5. Ga-V:Bi systems (GaP:Bi, GaAs:Bi, and GaSb:Bi) were thoroughly investigated with significantly slower, higher fidelity hybrid Heyd-Scuseria-Ernzerhof (HSE) and significantly faster, lower fidelity local density approximation (LDA) calculations. In both approaches spurious electrostatic interactions were corrected with the Freysoldt correction. The results were verified against available experimental results and used to assess the accuracy of a previous band alignment correction. Here, a modified band alignment method is proposed in order to better predict the HSE values from the LDA ones. The proposed method allows prediction of defect energies with values that approximate those from the HSE functional at the computational cost of LDA (about 20x faster for the systems studied here). Tests of selected point defects in In-V :Bi materials resulted in corrected LDA values having a mean absolute error (MAE) = 0.175 eV for defect levels vs. HSE. The method was further verified on an external database of defects and impurities in CdX (X=S, Se, Te) systems, yielding a MAE = 0.194 eV. These tests demonstrate the correction to be sufficient for qualitative and semi-quantitative predictions, and may suggest transferability to many semiconductor systems without significant loss in accuracy. Properties of the remaining In-V :Bi defects and all Al-V :Bi defects were predicted with the use of the modified band alignment method.

show abstract

The Materials Simulation Toolkit for Machine learning (MAST-ML): An automated open source toolkit to accelerate data-driven materials research

Cited by 44 publications

References 53 publications

Opportunities and Challenges for Machine Learning in Materials Science

Opportunities and Challenges for Machine Learning in Materials Science

Exploring Dielectric Constant and Dissipation Factor of LTCC Using Machine Learning

Modified band alignment method to obtain hybrid functional accuracy from standard DFT: Application to defects in highly mismatched III-V:Bi alloys

Contact Info

Product

Resources

About