A machine learning–based classification approach for phase diagram prediction
Knowledge of phase diagrams is essential for material design as it helps in understanding microstructure evolution during processing. The determination of phase diagrams is thus one of the central tasks in materials science. When exploring new materials for which the phase diagram is unknown, experi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-03-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127522001186 |
| _version_ | 1818759723040636928 |
|---|---|
| author | Guillaume Deffrennes Kei Terayama Taichi Abe Ryo Tamura |
| author_facet | Guillaume Deffrennes Kei Terayama Taichi Abe Ryo Tamura |
| author_sort | Guillaume Deffrennes |
| collection | DOAJ |
| description | Knowledge of phase diagrams is essential for material design as it helps in understanding microstructure evolution during processing. The determination of phase diagrams is thus one of the central tasks in materials science. When exploring new materials for which the phase diagram is unknown, experimentalists often try to determine the key experiments that should be performed by referencing known phase diagrams of similar systems. To enhance this practical strategy, we attempted to estimate unknown phase diagrams based on known phase diagrams using a machine learning–based classification approach. As a proof of concept, we focused on predicting the number of coexisting phases across the 800 K isothermal section of each of the 10 ternaries of the Al-Cu-Mg-Si-Zn system from the other 9 sections. To increase the prediction accuracy, we introduced new descriptors generated from the thermodynamic properties of the elements and CALPHAD extrapolations from lower-order systems. Using the random forest method, the presence of single-, two-, and three-phase domains was predicted with an average accuracy of 84% across all 10 considered sections with a standard deviation of 11%. The proposed approach represents a promising tool for assisting the investigator in developing new materials and determining phase equilibria efficiently. |
| first_indexed | 2024-12-18T06:47:15Z |
| format | Article |
| id | doaj.art-2eab58d4b8b241d5a222b1c51e61ef60 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-12-18T06:47:15Z |
| publishDate | 2022-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-2eab58d4b8b241d5a222b1c51e61ef602022-12-21T21:17:26ZengElsevierMaterials & Design0264-12752022-03-01215110497A machine learning–based classification approach for phase diagram predictionGuillaume Deffrennes0Kei Terayama1Taichi Abe2Ryo Tamura3International Center for Materials Nanoarchitectonics (WPI-MANA), National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan; Corresponding authors at: National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan.Graduate School of Medical Life Science, Yokohama City University, 1-7-29, Suehiro-cho, Tsurumi-ku, Kanagawa 230-0045, JapanResearch Center for Structural Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, Japan; Research and Services Division of Materials Data and Integrated System, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, JapanInternational Center for Materials Nanoarchitectonics (WPI-MANA), National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan; Research and Services Division of Materials Data and Integrated System, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan; RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan; Graduate School of Frontier Sciences, The University of Tokyo, 5-1-5 Kashiwa-no-ha, Kashiwa, Chiba 277-8561, Japan; Corresponding authors at: National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan.Knowledge of phase diagrams is essential for material design as it helps in understanding microstructure evolution during processing. The determination of phase diagrams is thus one of the central tasks in materials science. When exploring new materials for which the phase diagram is unknown, experimentalists often try to determine the key experiments that should be performed by referencing known phase diagrams of similar systems. To enhance this practical strategy, we attempted to estimate unknown phase diagrams based on known phase diagrams using a machine learning–based classification approach. As a proof of concept, we focused on predicting the number of coexisting phases across the 800 K isothermal section of each of the 10 ternaries of the Al-Cu-Mg-Si-Zn system from the other 9 sections. To increase the prediction accuracy, we introduced new descriptors generated from the thermodynamic properties of the elements and CALPHAD extrapolations from lower-order systems. Using the random forest method, the presence of single-, two-, and three-phase domains was predicted with an average accuracy of 84% across all 10 considered sections with a standard deviation of 11%. The proposed approach represents a promising tool for assisting the investigator in developing new materials and determining phase equilibria efficiently.http://www.sciencedirect.com/science/article/pii/S0264127522001186Phase diagramsMachine learningAlloysCALPHAD |
| spellingShingle | Guillaume Deffrennes Kei Terayama Taichi Abe Ryo Tamura A machine learning–based classification approach for phase diagram prediction Materials & Design Phase diagrams Machine learning Alloys CALPHAD |
| title | A machine learning–based classification approach for phase diagram prediction |
| title_full | A machine learning–based classification approach for phase diagram prediction |
| title_fullStr | A machine learning–based classification approach for phase diagram prediction |
| title_full_unstemmed | A machine learning–based classification approach for phase diagram prediction |
| title_short | A machine learning–based classification approach for phase diagram prediction |
| title_sort | machine learning based classification approach for phase diagram prediction |
| topic | Phase diagrams Machine learning Alloys CALPHAD |
| url | http://www.sciencedirect.com/science/article/pii/S0264127522001186 |
| work_keys_str_mv | AT guillaumedeffrennes amachinelearningbasedclassificationapproachforphasediagramprediction AT keiterayama amachinelearningbasedclassificationapproachforphasediagramprediction AT taichiabe amachinelearningbasedclassificationapproachforphasediagramprediction AT ryotamura amachinelearningbasedclassificationapproachforphasediagramprediction AT guillaumedeffrennes machinelearningbasedclassificationapproachforphasediagramprediction AT keiterayama machinelearningbasedclassificationapproachforphasediagramprediction AT taichiabe machinelearningbasedclassificationapproachforphasediagramprediction AT ryotamura machinelearningbasedclassificationapproachforphasediagramprediction |