- Senior Researcher, Data-driven Materials Design Group, Data-driven Materials Research Field, Center for Basic Research on Materials
- Data-driven Materials Design Group, Digital Transformation Initiative Center for Magnetic Materials, Research Center for Magnetic and Spintronic Materials
- Materials Open Platform for Structural Materials-DX, External Collaboration Division
- Address
- 305-0044 1-1 Namiki Tsukuba Ibaraki JAPAN [Access]
Research
PublicationsNIMS affiliated publications since 2004.
Research papers
- Vickey Nandal, Sae Dieb, Dmitry S. Bulgarevich, Toshio Osada, Toshiyuki Koyama, Satoshi Minamoto, Masahiko Demura. Artificial intelligence inspired design of non-isothermal aging for γ–γ′ two-phase, Ni–Al alloys. Scientific Reports. 13 [1] (2023) 12660 10.1038/s41598-023-39589-2 Open Access
- Sae Dieb, Yoshiaki Toda, Keitaro Sodeyama, Masahiko Demura. Machine learning-assisted determination of material chemical compositions: a study case on Ni-base superalloy. Science and Technology of Advanced Materials: Methods. 3 [1] (2023) 2278321 10.1080/27660400.2023.2278321 Open Access
- Zhilong Song, Qionghua Zhou, Shuaihua Lu, Sae Dieb, Chongyi Ling, Jinlan Wang. Adaptive Design of Alloys for CO2 Activation and Methanation via Reinforcement Learning Monte Carlo Tree Search Algorithm. The Journal of Physical Chemistry Letters. 14 [14] (2023) 3594-3601 10.1021/acs.jpclett.3c00242
Proceedings
- JU Shenghong, DIEB, Sae, TSUDA, Koji, SHIOMI, Junichiro. Designing Nanostructures for Heat Transport via Materials Informatics.. The 16th International Heat Transfer Conference. (2018) 9999-1-9999-8
- DIEB, Sae, OKA, Hiroyuki, ISHII, Masashi. Linking polymer names abbreviation to their definition in related scientific documents. Third International Workshop on SCIentific DOCument Analysis (SCIDOCA2018). (2018) 9999-1-9999-6
- JU Shenghong, DIEB, Sae, TSUDA, Koji, SHIOMI, Junichiro. Optimizing Interface/Surface Roughness for Thermal Transport. Machine Learning for Molecules and Materials NIPS 2018 Workshop. (2018) 9999-1-9999-7
Presentations
- NANDAL, Vickey, DIEB, Sae, BULGAREVICH, Dmitry, OSADA, Toshio, KOYAMA Toshiyuki, MINAMOTO, Satoshi, DEMURA, Masahiko. Critical Assessment of AI-Founded Non-Isothermal Aging Treatment Schedules for Improving 0.2% Proof Stress in Binary Ni-Al Alloys. MRM2023/IUMRS-ICA2023 Materials Innovation for Sustainable Development Goals. 2023
- Yoshihiro Chida, DIEB Sae, SODEYAMA Keitaro, Hiraku Masui, Arata Umehara, Naoto Todoroki, Toshimasa Wadayama. 白金－ハイエントロピー合金単結晶表面系の酸素還元反応特性：機械学習による合成条件検討. 第64回電池討論会. 2023
- NANDAL, Vickey, DIEB, Sae, BULGAREVICH, Dmitry, OSADA, Toshio, Toshiyuki Koyama, MINAMOTO, Satoshi, DEMURA, Masahiko. Utilizing Artificial Intelligence and Expert Knowledge to Optimize Non-Isothermal Aging Heat Treatment for Enhancing 0.2% Proof Stress in γ – γ' Binary Ni-Al Alloys. 14th ISAJ Symposium (Integrated Science for a Sustainable Society). 2023
Misc
- FOPPIANO, Luca, DIEB, Sae, SUZUKI, Akira, ISHII, Masashi. Proposal for Automatic Extraction Framework of Superconductors Related Information from Scientific Literature. IEICE technical report. (2019) 1-5
- DIEB, Sae, SODEYAMA, Keitaro, TANIFUJI, Mikiko. Visualization of Materials Science topics in Publications of Institutional Repository using Natural Language processing. Research Ideas and Outcomes. 8 (2022) e95679
Center for Basic Research on Materials
Data-driven algorithms for materials innovation
Materials informatics, Machine learning, Natural Language Processing
Overview
Development of machine learning algorithms for materials design and discovery.
Automatic construction of materials databases from related research papers using natural language processing.
Development of profiling serivce for mateials science reserchers.
Prediction of materials properties using regression methods.
Novelty and originality
Development of MDTS (Materials Design by Tree search) Python package for materials space exploration based on Monte Carlo tree search (MCTS) (https://github.com/tsudalab/MDTS).
Development of visualization service for NIMS SAMURAI researchers catalouge to capture research output and connect researchers with similar reserach interest using natural language processing.
Details
Materials design and discovery can be represented as selecting the optimal structure from a space of candidates that optimizes a target property. The selection is an iterative process, where selected candidate in one iteration is evaluted and fedback to the process for a more informed selection in the next iteration. Since the number of candidates can be exponentially proportional to the structure determination variables, the efficiency to obtain the optimal structure is a critical issue. We use Monte Carlo tree search (MCTS) approach in combination with expansion policy neural network to accelerate this process. MCTS has no tuning parameters and works autonomously in various problems. Additionally, it does not require pre- availalbe training data and it is highly scalble making it good fit for large spaces problems such as the chemical and mateirals space.
Summary
Optimization of the chemical compositions and heat treatment scheduling for new Ni-based superalloy for addiditve manufacturing using machine learning. Active-Leaning-Driven Development of Platinum-Free Electrocatalysts for the Hydrogen Oxidation Reaction.
