1
|
Qian X, Yoon BJ, Arróyave R, Qian X, Dougherty ER. Knowledge-driven learning, optimization, and experimental design under uncertainty for materials discovery. Patterns (N Y) 2023; 4:100863. [PMID: 38035192 PMCID: PMC10682757 DOI: 10.1016/j.patter.2023.100863] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/02/2023]
Abstract
Significant acceleration of the future discovery of novel functional materials requires a fundamental shift from the current materials discovery practice, which is heavily dependent on trial-and-error campaigns and high-throughput screening, to one that builds on knowledge-driven advanced informatics techniques enabled by the latest advances in signal processing and machine learning. In this review, we discuss the major research issues that need to be addressed to expedite this transformation along with the salient challenges involved. We especially focus on Bayesian signal processing and machine learning schemes that are uncertainty aware and physics informed for knowledge-driven learning, robust optimization, and efficient objective-driven experimental design.
Collapse
Affiliation(s)
- Xiaoning Qian
- Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USA
- Computational Science Initiative, Brookhaven National Laboratory, Upton, NY 11973, USA
| | - Byung-Jun Yoon
- Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USA
- Computational Science Initiative, Brookhaven National Laboratory, Upton, NY 11973, USA
| | - Raymundo Arróyave
- Department of Materials Science & Engineering, Texas A&M University, College Station, TX 77843, USA
| | - Xiaofeng Qian
- Department of Materials Science & Engineering, Texas A&M University, College Station, TX 77843, USA
| | - Edward R. Dougherty
- Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USA
| |
Collapse
|
2
|
Roy AM, Bose R, Sundararaghavan V, Arróyave R. Deep learning-accelerated computational framework based on Physics Informed Neural Network for the solution of linear elasticity. Neural Netw 2023; 162:472-489. [PMID: 36966712 DOI: 10.1016/j.neunet.2023.03.014] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2022] [Revised: 02/07/2023] [Accepted: 03/08/2023] [Indexed: 03/16/2023]
Abstract
The paper presents an efficient and robust data-driven deep learning (DL) computational framework developed for linear continuum elasticity problems. The methodology is based on the fundamentals of the Physics Informed Neural Networks (PINNs). For an accurate representation of the field variables, a multi-objective loss function is proposed. It consists of terms corresponding to the residual of the governing partial differential equations (PDE), constitutive relations derived from the governing physics, various boundary conditions, and data-driven physical knowledge fitting terms across randomly selected collocation points in the problem domain. To this end, multiple densely connected independent artificial neural networks (ANNs), each approximating a field variable, are trained to obtain accurate solutions. Several benchmark problems including the Airy solution to elasticity and the Kirchhoff-Love plate problem are solved. Performance in terms of accuracy and robustness illustrates the superiority of the current framework showing excellent agreement with analytical solutions. The present work combines the benefits of the classical methods depending on the physical information available in analytical relations with the superior capabilities of the DL techniques in the data-driven construction of lightweight, yet accurate and robust neural networks. The models developed herein can significantly boost computational speed using minimal network parameters with easy adaptability in different computational platforms.
Collapse
Affiliation(s)
- Arunabha M Roy
- Department of Materials Science and Engineering, Texas A&M University, 3003 TAMU, College Station, TX 77843, USA.
| | - Rikhi Bose
- Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA
| | - Veera Sundararaghavan
- Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI 48109, USA
| | - Raymundo Arróyave
- Department of Materials Science and Engineering, Texas A&M University, 3003 TAMU, College Station, TX 77843, USA; Department of Mechanical Engineering, Texas A&M University, 3003 TAMU, College Station, TX 77843, USA
| |
Collapse
|
3
|
Sauceda D, Singh P, Ouyang G, Palasyuk O, Kramer MJ, Arróyave R. High throughput exploration of the oxidation landscape in high entropy alloys. Mater Horiz 2022; 9:2644-2663. [PMID: 36000520 DOI: 10.1039/d2mh00729k] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
High entropy alloys (HEAs) have gained interest for structural applications in extreme environments. With a potentially vast chemical and phase space, there are significant opportunities to discover superior performing alloys. Crucial for most high-temperature applications is understanding and mitigating the oxidation behavior of these chemically complex alloys. Most experimental and computational HEA studies have focused on a limited set of compositions and only a fraction of these compositions have been characterized for oxidation. We present a high-throughput framework that utilizes density-functional theory (DFT) in concert with a combined machine-learning model and grand-canonical linear programming for assessing phase stability, phase-fraction, chemical activity and high-temperature survivability of arbitrary HEAs. This framework considers temperature dependent contributions to the Gibbs energy of the competing phases arising from short-range order and vibrational entropy. We demonstrate the effectiveness of the framework by assessing the thermodynamic stability, oxidation behavior, chemical activity, and phase decomposition of body-centered cubic Mo-W-Ta-Ti-Zr refractory HEAs. A total of 51 compositions were analyzed and ranked in order of their survivability based on the Pareto-front analysis. Oxidation was performed at 1373 K on four samples in air showing the difference in oxidation behavior determined experimentally through scale thickness and their mass changes. The insights on oxidation behavior presented in this work will enable the fast assessment of technologically useful HEAs needed for future structural application in extreme conditions.
Collapse
Affiliation(s)
- D Sauceda
- Department of Materials Science & Engineering, Texas A&M University, College Station, Texas, 77843, USA.
| | - P Singh
- Department of Materials Science & Engineering, Texas A&M University, College Station, Texas, 77843, USA.
- Ames Laboratory, United States Department of Energy, Iowa State University, Ames, Iowa 50011, USA.
| | - G Ouyang
- Ames Laboratory, United States Department of Energy, Iowa State University, Ames, Iowa 50011, USA.
| | - O Palasyuk
- Ames Laboratory, United States Department of Energy, Iowa State University, Ames, Iowa 50011, USA.
| | - M J Kramer
- Ames Laboratory, United States Department of Energy, Iowa State University, Ames, Iowa 50011, USA.
| | - R Arróyave
- Department of Materials Science & Engineering, Texas A&M University, College Station, Texas, 77843, USA.
- J. Mike Walker '66 Department of Mechanical Engineering, Texas A&M University, College Station, Texas, 77843, USA.
- Wm Michael Barnes '64 Department of Industrial and Systems Engineering, Texas A&M University, College Station, College Station, Texas, 77843, USA
| |
Collapse
|
4
|
Braham EJ, Davidson RD, Al-Hashimi M, Arróyave R, Banerjee S. Navigating the design space of inorganic materials synthesis using statistical methods and machine learning. Dalton Trans 2020; 49:11480-11488. [PMID: 32743629 DOI: 10.1039/d0dt02028a] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Data-driven approaches have brought about a revolution in manufacturing; however, challenges persist in their applications to synthetic strategies. Their application to the deterministic navigation of reaction trajectories to stabilize crystalline solids with precise composition, atomic connectivity, microstructural dimensionality, and surface structure remains a frontier in inorganic materials research. The design of synthetic methodologies for the preparation of inorganic materials is often inefficient in terms of exploration of potentially vast design spaces spanning multiple process variables, reaction sequences, as well as structural parameters and reactivities of precursors and structure-directing agents. Reported synthetic methods are further limited in terms of the insight they provide into underlying chemical and physical principles. The recent surge in interest in accelerating the discovery of new materials can be considered as an opportunity to re-evaluate our approach to materials synthesis, and for considering new frameworks for exploration that are systematic and strategic in approach. Herein, we outline with the help of several illustrative examples, the challenges, opportunities, and limitations of data-driven synthesis design. The account collates discussion of design-of-experiments sampling methods, machine learning modeling, and active learning to develop experimental workflows that accelerate the experimental navigation of synthetic landscapes.
Collapse
Affiliation(s)
- Erick J Braham
- Department of Chemistry, Texas A&M University, College Station, TX 77843, USA. and Department of Material Science and Engineering, Texas A&M University, College Station, TX 77843, USA.
| | - Rachel D Davidson
- Department of Chemistry, Texas A&M University, College Station, TX 77843, USA. and Department of Material Science and Engineering, Texas A&M University, College Station, TX 77843, USA.
| | - Mohammed Al-Hashimi
- Department of Chemistry, Texas A&M University at Qatar, P.O. Box 23874, Doha, Qatar
| | - Raymundo Arróyave
- Department of Material Science and Engineering, Texas A&M University, College Station, TX 77843, USA.
| | - Sarbajit Banerjee
- Department of Chemistry, Texas A&M University, College Station, TX 77843, USA. and Department of Material Science and Engineering, Texas A&M University, College Station, TX 77843, USA.
| |
Collapse
|
5
|
Junkaew A, Arróyave R. Enhancement of the selectivity of MXenes (M2C, M = Ti, V, Nb, Mo) via oxygen-functionalization: promising materials for gas-sensing and -separation. Phys Chem Chem Phys 2018; 20:6073-6082. [DOI: 10.1039/c7cp08622a] [Citation(s) in RCA: 62] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
Abstract
Mo2CO2 and V2CO2 reveal very good selectivity toward NO, while Nb2CO2 and Ti2CO2 show very good selectivity toward NH3.
Collapse
Affiliation(s)
- A. Junkaew
- National Nanotechnology Center (NANOTEC)
- National Science and Technology Development Agency (NSTDA)
- Thailand
| | - R. Arróyave
- Department of Materials Science and Engineering
- Texas A&M University
- College Station
- USA
| |
Collapse
|
6
|
Abstract
The quest towards expansion of the M n+1AX n design space has been accelerated with the recent discovery of several solid solution and ordered phases involving at least two M n+1AX n end members. Going beyond the nominal M n+1AX n compounds enables not only fine tuning of existing properties but also entirely new functionality. This search, however, has been mostly done through painstaking experiments as knowledge of the phase stability of the relevant systems is rather scarce. In this work, we report the first attempt to evaluate the finite-temperature pseudo-binary phase diagram of the Ti2AlC-Cr2AlC via first-principles-guided Bayesian CALPHAD framework that accounts for uncertainties not only in ab initio calculations and thermodynamic models but also in synthesis conditions in reported experiments. The phase stability analyses are shown to have good agreement with previous experiments. The work points towards a promising way of investigating phase stability in other MAX Phase systems providing the knowledge necessary to elucidate possible synthesis routes for M n+1AX n systems with unprecedented properties.
Collapse
Affiliation(s)
- Thien C Duong
- Department of Materials Science and Engineering, Texas A&M University, College Station, TX, 77843, United States.
| | - Anjana Talapatra
- Department of Materials Science and Engineering, Texas A&M University, College Station, TX, 77843, United States
| | - Woongrak Son
- Department of Materials Science and Engineering, Texas A&M University, College Station, TX, 77843, United States
| | - Miladin Radovic
- Department of Materials Science and Engineering, Texas A&M University, College Station, TX, 77843, United States.,Department of Mechanical Engineering, Texas A&M University, College Station, TX, 77843, United States
| | - Raymundo Arróyave
- Department of Materials Science and Engineering, Texas A&M University, College Station, TX, 77843, United States.,Department of Mechanical Engineering, Texas A&M University, College Station, TX, 77843, United States
| |
Collapse
|
7
|
Junkaew A, Maitarad P, Arróyave R, Kungwan N, Zhang D, Shi L, Namuangruk S. The complete reaction mechanism of H2S desulfurization on an anatase TiO2 (001) surface: a density functional theory investigation. Catal Sci Technol 2017. [DOI: 10.1039/c6cy02030e] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
An anatase TiO2 (001) surface is active and selective toward water production and results in the modification of the surface by forming S-doped TiO2, which enhances its photocatalytic activity.
Collapse
Affiliation(s)
- Anchalee Junkaew
- National Nanotechnology Center (NANOTEC)
- National Science and Technology Development Agency (NSTDA)
- Pathum Thani 12120
- Thailand
| | - Phornphimon Maitarad
- Research Center of Nanoscience and Technology
- Shanghai University
- Shanghai 200444
- PR China
| | - Raymundo Arróyave
- Department of Materials Science & Engineering
- Texas A&M University
- USA
| | - Nawee Kungwan
- Department of Chemistry
- Faculty of Science
- Chiang Mai University
- Chiang Mai 50200
- Thailand
| | - Dengsong Zhang
- Research Center of Nanoscience and Technology
- Shanghai University
- Shanghai 200444
- PR China
| | - Liyi Shi
- Research Center of Nanoscience and Technology
- Shanghai University
- Shanghai 200444
- PR China
| | - Supawadee Namuangruk
- National Nanotechnology Center (NANOTEC)
- National Science and Technology Development Agency (NSTDA)
- Pathum Thani 12120
- Thailand
| |
Collapse
|
8
|
Bajaj S, Haverty MG, Arróyave R, Goddard WA, Shankar S. Correction: Phase stability in nanoscale material systems: extension from bulk phase diagrams. Nanoscale 2015; 7:20776. [PMID: 26584203 DOI: 10.1039/c5nr90199e] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
Correction for 'Phase stability in nanoscale material systems: extension from bulk phase diagrams' by Saurabh Bajaj et al., Nanoscale, 2015, 7, 9868-9877.
Collapse
Affiliation(s)
- Saurabh Bajaj
- Department of Applied Physics and Materials Science, California Institute of Technology, Pasadena, CA 91125, USA.
| | | | | | | | | |
Collapse
|
9
|
Bajaj S, Haverty MG, Arróyave R, Goddard WA, Shankar S. Phase stability in nanoscale material systems: extension from bulk phase diagrams. Nanoscale 2015; 7:9868-9877. [PMID: 25965301 DOI: 10.1039/c5nr01535a] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
Phase diagrams of multi-component systems are critical for the development and engineering of material alloys for all technological applications. At nano dimensions, surfaces (and interfaces) play a significant role in changing equilibrium thermodynamics and phase stability. In this work, it is shown that these surfaces at small dimensions affect the relative equilibrium thermodynamics of the different phases. The CALPHAD approach for material surfaces (also termed "nano-CALPHAD") is employed to investigate these changes in three binary systems by calculating their phase diagrams at nano dimensions and comparing them with their bulk counterparts. The surface energy contribution, which is the dominant factor in causing these changes, is evaluated using the spherical particle approximation. It is first validated with the Au-Si system for which experimental data on phase stability of spherical nano-sized particles is available, and then extended to calculate phase diagrams of similarly sized particles of Ge-Si and Al-Cu. Additionally, the surface energies of the associated compounds are calculated using DFT, and integrated into the thermodynamic model of the respective binary systems. In this work we found changes in miscibilities, reaction compositions of about 5 at%, and solubility temperatures ranging from 100-200 K for particles of sizes 5 nm, indicating the importance of phase equilibrium analysis at nano dimensions.
Collapse
Affiliation(s)
- Saurabh Bajaj
- Department of Applied Physics and Materials Science, California Institute of Technology, Pasadena, CA 91125, USA.
| | | | | | | | | |
Collapse
|
10
|
Junkaew A, Rungnim C, Kunaseth M, Arróyave R, Promarak V, Kungwan N, Namuangruk S. Metal cluster-deposited graphene as an adsorptive material for m-xylene. NEW J CHEM 2015. [DOI: 10.1039/c5nj01975c] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
m-Xylene weakly adsorbs on graphene and silver cluster doped graphene, but it has excellent interaction with platinum cluster doped graphene.
Collapse
Affiliation(s)
- Anchalee Junkaew
- NANOTEC
- National Science and Technology Development Agency (NSTDA)
- 111 Thailand Science Park
- Phahonyothin
- Khlong Nueng
| | - Chompoonut Rungnim
- NANOTEC
- National Science and Technology Development Agency (NSTDA)
- 111 Thailand Science Park
- Phahonyothin
- Khlong Nueng
| | - Manaschai Kunaseth
- NANOTEC
- National Science and Technology Development Agency (NSTDA)
- 111 Thailand Science Park
- Phahonyothin
- Khlong Nueng
| | - Raymundo Arróyave
- Department of Materials Science and Engineering
- Texas A&M University
- College Station
- USA
| | - Vinich Promarak
- Vidyasirimedhi Institute of Science and Technology
- Wang Chan
- Rayong 21210
- Thailand
| | - Nawee Kungwan
- Department of Chemistry
- Faculty of Science
- Chiang Mai University
- Chiang Mai 50200
- Thailand
| | - Supawadee Namuangruk
- NANOTEC
- National Science and Technology Development Agency (NSTDA)
- 111 Thailand Science Park
- Phahonyothin
- Khlong Nueng
| |
Collapse
|