Benchmarking machine learning strategies for phase-field problems

Dingreville, Rémi; Roberston, Andreas E.; Attari, Vahid; Greenwood, Michael; Ofori-Opoku, Nana; Ramesh, Mythreyi; Voorhees, Peter W.; Zhang, Qian

doi:10.1088/1361-651X/ad5f4a

Benchmarking machine learning strategies for phase-field problems

Journal Article · Mon Jul 15 00:00:00 EDT 2024 · Modelling and Simulation in Materials Science and Engineering

DOI:https://doi.org/10.1088/1361-651X/ad5f4a· OSTI ID:2403381

; Roberston, Andreas E.; ; ; ; ; ; Zhang, Qian

Abstract

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.

View Journal Article

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: NA0003525

OSTI ID:: 2403381

Alternate ID(s):: OSTI ID: 2391016
OSTI ID: 2404603

Journal Information:: Modelling and Simulation in Materials Science and Engineering, Journal Name: Modelling and Simulation in Materials Science and Engineering Journal Issue: 6 Vol. 32; ISSN 0965-0393

Publisher:: IOP PublishingCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (51)

Combining machine learning and domain decomposition methods for the solution of partial differential equations—A review Heinlein, Alexander; Klawonn, Axel; Lanser, Martin GAMM-Mitteilungen, Vol. 44, Issue 1 https://doi.org/10.1002/gamm.202100001	journal	March 2021
Graphical test for discrete uniformity and its applications in goodness-of-fit evaluation and multiple sample comparison Säilynoja, Teemu; Bürkner, Paul-Christian; Vehtari, Aki Statistics and Computing, Vol. 32, Issue 2 https://doi.org/10.1007/s11222-022-10090-6	journal	March 2022
Materials Knowledge Systems in Python—a Data Science Framework for Accelerated Development of Hierarchical Materials Brough, David B.; Wheeler, Daniel; Kalidindi, Surya R. Integrating Materials and Manufacturing Innovation, Vol. 6, Issue 1 https://doi.org/10.1007/s40192-017-0089-0	journal	March 2017
MICRO2D: A Large, Statistically Diverse, Heterogeneous Microstructure Dataset Robertson, Andreas E.; Generale, Adam P.; Kelly, Conlain Integrating Materials and Manufacturing Innovation, Vol. 13, Issue 1 https://doi.org/10.1007/s40192-023-00340-4	journal	February 2024
On spinodal decomposition Cahn, John W. Acta Metallurgica, Vol. 9, Issue 9 https://doi.org/10.1016/0001-6160(61)90182-1	journal	September 1961
Applications of semi-implicit Fourier-spectral method to phase field equations Chen, L. Q.; Shen, Jie Computer Physics Communications, Vol. 108, Issue 2-3 https://doi.org/10.1016/S0010-4655(97)00115-X	journal	February 1998
Extraction of reduced-order process-structure linkages from phase-field simulations Yabansu, Yuksel C.; Steinmetz, Philipp; Hötzer, Johannes Acta Materialia, Vol. 124 https://doi.org/10.1016/j.actamat.2016.10.071	journal	February 2017
An active learning high-throughput microstructure calibration framework for solving inverse structure–process problems in materials informatics Tran, Anh; Mitchell, John A.; Swiler, Laura P. Acta Materialia, Vol. 194 https://doi.org/10.1016/j.actamat.2020.04.054	journal	August 2020
Local–Global Decompositions for Conditional Microstructure Generation Robertson, Andreas E.; Kelly, Conlain; Buzzy, Michael Acta Materialia, Vol. 253 https://doi.org/10.1016/j.actamat.2023.118966	journal	July 2023
Towards inverse microstructure-centered materials design using generative phase-field modeling and deep variational autoencoders Attari, Vahid; Khatamsaz, Danial; Allaire, Douglas Acta Materialia, Vol. 259 https://doi.org/10.1016/j.actamat.2023.119204	journal	October 2023
Trade-offs in the latent representation of microstructure evolution Desai, Saaketh; Shrivastava, Ankit; D’Elia, Marta Acta Materialia, Vol. 263 https://doi.org/10.1016/j.actamat.2023.119514	journal	January 2024
Accelerating phase-field simulation of three-dimensional microstructure evolution in laser powder bed fusion with composable machine learning predictions Choi, Jin Young; Xue, Tianju; Liao, Shuheng Additive Manufacturing, Vol. 79 https://doi.org/10.1016/j.addma.2023.103938	journal	January 2024
A data-driven surrogate model to rapidly predict microstructure morphology during physical vapor deposition Herman, Elizabeth; Stewart, James A.; Dingreville, Rémi Applied Mathematical Modelling, Vol. 88 https://doi.org/10.1016/j.apm.2020.06.046	journal	December 2020
Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions Teichert, G. H.; Natarajan, A. R.; Van der Ven, A. Computer Methods in Applied Mechanics and Engineering, Vol. 353 https://doi.org/10.1016/j.cma.2019.05.019	journal	August 2019
Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures Zhang, Xiaoxuan; Garikipati, Krishna Computer Methods in Applied Mechanics and Engineering, Vol. 372 https://doi.org/10.1016/j.cma.2020.113362	journal	December 2020
Accelerating phase-field predictions via recurrent neural networks learning the microstructure evolution in latent space Hu, C.; Martin, S.; Dingreville, R. Computer Methods in Applied Mechanics and Engineering, Vol. 397 https://doi.org/10.1016/j.cma.2022.115128	journal	July 2022
Probabilistic deep learning for real-time large deformation simulations Deshpande, Saurabh; Lengiewicz, Jakub; Bordas, Stéphane P. A. Computer Methods in Applied Mechanics and Engineering, Vol. 398 https://doi.org/10.1016/j.cma.2022.115307	journal	August 2022
Phase-Field DeepONet: Physics-informed deep operator neural network for fast simulations of pattern formation governed by gradient flows of free-energy functionals Li, Wei; Bazant, Martin Z.; Zhu, Juner Computer Methods in Applied Mechanics and Engineering, Vol. 416 https://doi.org/10.1016/j.cma.2023.116299	journal	November 2023
Image driven machine learning methods for microstructure recognition Chowdhury, Aritra; Kautz, Elizabeth; Yener, Bülent Computational Materials Science, Vol. 123 https://doi.org/10.1016/j.commatsci.2016.05.034	journal	October 2016
Benchmark problems for numerical implementations of phase field models Jokisaari, A. M.; Voorhees, P. W.; Guyer, J. E. Computational Materials Science, Vol. 126 https://doi.org/10.1016/j.commatsci.2016.09.022	journal	January 2017
Recurrent localization networks applied to the Lippmann-Schwinger equation Kelly, Conlain; Kalidindi, Surya R. Computational Materials Science, Vol. 192 https://doi.org/10.1016/j.commatsci.2021.110356	journal	May 2021
Machine-learning-based surrogate modeling of microstructure evolution using phase-field Peivaste, Iman; Siboni, Nima H.; Alahyarizadeh, Ghasem Computational Materials Science, Vol. 214 https://doi.org/10.1016/j.commatsci.2022.111750	journal	November 2022
Spatiotemporal prediction of microstructure evolution with predictive recurrent neural network Kazemzadeh Farizhandi, Amir Abbas; Mamivand, Mahmood Computational Materials Science, Vol. 223 https://doi.org/10.1016/j.commatsci.2023.112110	journal	April 2023
A time multiscale based data-driven approach in cyclic elasto-plasticity Rodriguez, Sebastian; Pasquale, Angelo; Nguyen, Khanh Computers & Structures, Vol. 295 https://doi.org/10.1016/j.compstruc.2024.107277	journal	May 2024
Microstructure-based knowledge systems for capturing process-structure evolution linkages Brough, David B.; Wheeler, Daniel; Warren, James A. Current Opinion in Solid State and Materials Science, Vol. 21, Issue 3 https://doi.org/10.1016/j.cossms.2016.05.002	journal	June 2017
Learning from class-imbalanced data: Review of methods and applications Haixiang, Guo; Yijing, Li; Shang, Jennifer Expert Systems with Applications, Vol. 73 https://doi.org/10.1016/j.eswa.2016.12.035	journal	May 2017
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials Thompson, A. P.; Swiler, L. P.; Trott, C. R. Journal of Computational Physics, Vol. 285 https://doi.org/10.1016/j.jcp.2014.12.018	journal	March 2015
Mechanistic artificial intelligence (mechanistic-AI) for modeling, design, and control of advanced manufacturing processes: Current state and perspectives Mozaffar, Mojtaba; Liao, Shuheng; Xie, Xiaoyu Journal of Materials Processing Technology, Vol. 302 https://doi.org/10.1016/j.jmatprotec.2021.117485	journal	April 2022
Learning time-dependent deposition protocols to design thin films via genetic algorithms Desai, Saaketh; Dingreville, Rémi Materials & Design, Vol. 219 https://doi.org/10.1016/j.matdes.2022.110815	journal	July 2022
Machine learning for materials science: Barriers to broader adoption Boyce, Brad; Dingreville, Remi; Desai, Saaketh Matter, Vol. 6, Issue 5 https://doi.org/10.1016/j.matt.2023.03.028	journal	May 2023
Deep learning prediction of stress fields in additively manufactured metals with intricate defect networks Croom, Brendan P.; Berkson, Michael; Mueller, Robert K. Mechanics of Materials, Vol. 165 https://doi.org/10.1016/j.mechmat.2021.104191	journal	February 2022
PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation Klöckner, Andreas; Pinto, Nicolas; Lee, Yunsup Parallel Computing, Vol. 38, Issue 3 https://doi.org/10.1016/j.parco.2011.09.001	journal	March 2012
Self-supervised learning and prediction of microstructure evolution with convolutional recurrent neural networks Yang, Kaiqi; Cao, Yifan; Zhang, Youtian Patterns, Vol. 2, Issue 5 https://doi.org/10.1016/j.patter.2021.100243	journal	May 2021
Voxelized Atomic Structure Potentials: Predicting Atomic Forces with the Accuracy of Quantum Mechanics Using Convolutional Neural Networks Barry, Matthew C.; Wise, Kristopher E.; Kalidindi, Surya R. The Journal of Physical Chemistry Letters, Vol. 11, Issue 21 https://doi.org/10.1021/acs.jpclett.0c02271	journal	September 2020
Machine Learning Surrogate Model for Acceleration of Ferroelectric Phase-Field Modeling Alhada-Lahbabi, Kévin; Deleruyelle, Damien; Gautier, Brice ACS Applied Electronic Materials, Vol. 5, Issue 7 https://doi.org/10.1021/acsaelm.3c00601	journal	July 2023
Machine learning in materials informatics: recent applications and prospects Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam npj Computational Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s41524-017-0056-5	journal	December 2017
Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods Montes de Oca Zapiain, David; Stewart, James A.; Dingreville, Rémi npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-020-00471-8	journal	January 2021
Recent advances and applications of deep learning methods in materials science Choudhary, Kamal; DeCost, Brian; Chen, Chi npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00734-6	journal	April 2022
Learning two-phase microstructure evolution using neural operators and autoencoder architectures Oommen, Vivek; Shukla, Khemraj; Goswami, Somdatta npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00876-7	journal	September 2022
Inferring topological transitions in pattern-forming processes with self-supervised learning Abram, Marcin; Burghardt, Keith; Ver Steeg, Greg npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00889-2	journal	September 2022
Rethinking materials simulations: Blending direct numerical simulations with neural operators Oommen, Vivek; Shukla, Khemraj; Desai, Saaketh npj Computational Materials, Vol. 10, Issue 1 https://doi.org/10.1038/s41524-024-01319-1	journal	July 2024
Array programming with NumPy Harris, Charles R.; Millman, K. Jarrod; van der Walt, Stéfan J. Nature, Vol. 585, Issue 7825 https://doi.org/10.1038/s41586-020-2649-2	journal	September 2020
Phase Separation by Spinodal Decomposition in Isotropic Systems Cahn, John W. The Journal of Chemical Physics, Vol. 42, Issue 1 https://doi.org/10.1063/1.1695731	journal	January 1965
Learning data-driven discretizations for partial differential equations Bar-Sinai, Yohai; Hoyer, Stephan; Hickey, Jason Proceedings of the National Academy of Sciences, Vol. 116, Issue 31 https://doi.org/10.1073/pnas.1814058116	journal	July 2019
Machine learning–accelerated computational fluid dynamics Kochkov, Dmitrii; Smith, Jamie A.; Alieva, Ayya Proceedings of the National Academy of Sciences, Vol. 118, Issue 21 https://doi.org/10.1073/pnas.2101784118	journal	May 2021
A finite element-convolutional neural network model (FE-CNN) for stress field analysis around arbitrary inclusions Rezasefat, Mohammad; Hogan, James D. Machine Learning: Science and Technology, Vol. 4, Issue 4 https://doi.org/10.1088/2632-2153/ad134a	journal	December 2023
Testing the manifold hypothesis Fefferman, Charles; Mitter, Sanjoy; Narayanan, Hariharan Journal of the American Mathematical Society, Vol. 29, Issue 4 https://doi.org/10.1090/jams/852	journal	February 2016
Accelerating microstructure modeling via machine learning: A method combining Autoencoder and ConvLSTM Ahmad, Owais; Kumar, Naveen; Mukherjee, Rajdip Physical Review Materials, Vol. 7, Issue 8 https://doi.org/10.1103/PhysRevMaterials.7.083802	journal	August 2023
LSTM: A Search Space Odyssey Greff, Klaus; Srivastava, Rupesh K.; Koutnik, Jan IEEE Transactions on Neural Networks and Learning Systems, Vol. 28, Issue 10 https://doi.org/10.1109/TNNLS.2016.2582924	journal	October 2017
Phase-Field Models for Microstructure Evolution Chen, Long-Qing Annual Review of Materials Research, Vol. 32, Issue 1 https://doi.org/10.1146/annurev.matsci.32.112001.132041	journal	August 2002
The five V’s, seven virtues and ten rules of big data engagement for official statistics Tam, Siu-Ming; Van Halderen, Gemma Statistical Journal of the IAOS, Vol. 36, Issue 2 https://doi.org/10.3233/SJI-190595	journal	June 2020

Similar Records

EC-Bench: A Benchmark for Enzyme Commission Number Prediction

Journal Article · Wed Jan 07 19:00:00 EST 2026 · Bioinformatics Advances · OSTI ID:3012452

Benchmarking machine learning strategies for phase-field problems

Citation Formats

References (51)

Similar Records

Related Subjects