1
|
Palizhati A, Torrisi SB, Aykol M, Suram SK, Hummelshøj JS, Montoya JH. Agents for sequential learning using multiple-fidelity data. Sci Rep 2022; 12:4694. [PMID: 35304496 PMCID: PMC8933401 DOI: 10.1038/s41598-022-08413-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2021] [Accepted: 02/17/2022] [Indexed: 11/09/2022] Open
Abstract
Sequential learning for materials discovery is a paradigm where a computational agent solicits new data to simultaneously update a model in service of exploration (finding the largest number of materials that meet some criteria) or exploitation (finding materials with an ideal figure of merit). In real-world discovery campaigns, new data acquisition may be costly and an optimal strategy may involve using and acquiring data with different levels of fidelity, such as first-principles calculation to supplement an experiment. In this work, we introduce agents which can operate on multiple data fidelities, and benchmark their performance on an emulated discovery campaign to find materials with desired band gap values. The fidelities of data come from the results of DFT calculations as low fidelity and experimental results as high fidelity. We demonstrate performance gains of agents which incorporate multi-fidelity data in two contexts: either using a large body of low fidelity data as a prior knowledge base or acquiring low fidelity data in-tandem with experimental data. This advance provides a tool that enables materials scientists to test various acquisition and model hyperparameters to maximize the discovery rate of their own multi-fidelity sequential learning campaigns for materials discovery. This may also serve as a reference point for those who are interested in practical strategies that can be used when multiple data sources are available for active or sequential learning campaigns.
Collapse
Affiliation(s)
- Aini Palizhati
- Energy and Materials Division, Toyota Research Institute, Los Altos, USA
- Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, USA
| | - Steven B Torrisi
- Energy and Materials Division, Toyota Research Institute, Los Altos, USA
| | - Muratahan Aykol
- Energy and Materials Division, Toyota Research Institute, Los Altos, USA
| | - Santosh K Suram
- Energy and Materials Division, Toyota Research Institute, Los Altos, USA
| | - Jens S Hummelshøj
- Energy and Materials Division, Toyota Research Institute, Los Altos, USA
| | - Joseph H Montoya
- Energy and Materials Division, Toyota Research Institute, Los Altos, USA.
| |
Collapse
|
2
|
Velasco L, Castillo JS, Kante MV, Olaya JJ, Friederich P, Hahn H. Phase-Property Diagrams for Multicomponent Oxide Systems toward Materials Libraries. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2021; 33:e2102301. [PMID: 34514669 DOI: 10.1002/adma.202102301] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/24/2021] [Revised: 07/29/2021] [Indexed: 05/27/2023]
Abstract
Exploring the vast compositional space offered by multicomponent systems or high entropy materials using the traditional route of materials discovery, one experiment at a time, is prohibitive in terms of cost and required time. Consequently, the development of high-throughput experimental methods, aided by machine learning and theoretical predictions will facilitate the search for multicomponent materials in their compositional variety. In this study, high entropy oxides are fabricated and characterized using automated high-throughput techniques. For intuitive visualization, a graphical phase-property diagram correlating the crystal structure, the chemical composition, and the band gap are introduced. Interpretable machine learning models are trained for automated data analysis and to speed up data comprehension. The establishment of materials libraries of multicomponent systems correlated with their properties (as in the present work), together with machine learning-based data analysis and theoretical approaches are opening pathways toward virtual development of novel materials for both functional and structural applications.
Collapse
Affiliation(s)
- Leonardo Velasco
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344, Eggenstein-Leopoldshafen, Germany
| | - Juan S Castillo
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344, Eggenstein-Leopoldshafen, Germany
- Facultad de Ingeniería, Universidad Nacional de Colombia, Av. Cra. 30 # 45-03, Ed. 407, Ciudad Universitaria, Bogotá, DC, 111321, Colombia
- Joint Research Laboratory Nanomaterials, Technische Universität Darmstadt, Otto-Berndt-Str. 3, 64206, Darmstadt, Germany
| | - Mohana V Kante
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344, Eggenstein-Leopoldshafen, Germany
- Joint Research Laboratory Nanomaterials, Technische Universität Darmstadt, Otto-Berndt-Str. 3, 64206, Darmstadt, Germany
| | - Jhon J Olaya
- Facultad de Ingeniería, Universidad Nacional de Colombia, Av. Cra. 30 # 45-03, Ed. 407, Ciudad Universitaria, Bogotá, DC, 111321, Colombia
| | - Pascal Friederich
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344, Eggenstein-Leopoldshafen, Germany
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131, Karlsruhe, Germany
| | - Horst Hahn
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344, Eggenstein-Leopoldshafen, Germany
- Joint Research Laboratory Nanomaterials, Technische Universität Darmstadt, Otto-Berndt-Str. 3, 64206, Darmstadt, Germany
| |
Collapse
|
3
|
Abstract
Studies have been actively conducted on systems that prevent the breakage of water pipes from freezing in winter. Shape memory alloy (SMA) coil springs have been used as the key components of actuators that can operate automatically by detecting the real-time outside temperature changes, but research on its use as an actuator that can operate at sub-zero temperatures is insufficient. This study proposes the anti-freezing system using Ni-44.08Ti-1.46Co (wt.%) SMA coil springs that operate near sub-zero temperatures to prevent the freezing accident of water pipes. After fabricating the SMA coil springs, the test for performance evaluation of the springs applied static load conditions was conducted on the specific outside temperature. To examine the operation of anti-freezing systems applied the SMA coil spring as an actuator, the water discharge test (WDT) was also conducted along with the computational fluid simulation. The results of water discharge measurement obtained by WDT, simulations, and theoretical equations applied to the fluid resupply system constructed were compared with each other to verify the reliability. Consequently, it was confirmed that water discharge can be automatically controlled in real time according to temperature changes of SMA coil springs in the anti-freezing system.
Collapse
|