# Fileset

[[vol.92]MANA Scientists Employ Active Machine Learning to Enhance Thermoelectric Performance of Materials_MANA.pdf](https://mdr.nims.go.jp/filesets/7288a8de-2f45-4e3a-9d42-38d56a82b2be/download)

## Creator

International Center for Materials Nanoarchitectonics (WPI-MANA)

## Rights

In Copyright[In Copyright](http://rightsstatements.org/vocab/InC/1.0/)

## Other metadata

[[Research Highlights Vol. 92]MANA Scientists Employ Active Machine Learning to Enhance Thermoelectric Performance of Materials](https://mdr.nims.go.jp/datasets/621964e4-1f3c-42b5-b446-3f9c6d539f3e)

## Fulltext

MANA Scientists Employ Active Machine Learning to Enhance Thermoelectric Performance of Materials | MANAPrevious Index NextResearch Highlights[Vol. 92]MANA Scientists Employ Active Machine Learning to Enhance ThermoelectricPerformance of Materials20 Jan, 2025Scientists from the Research Center for Materials Nanoarchitectonics (MANA) have integratedmachine learning with traditional materials science to expedite the discovery of kesterite-typethermoelectric materials, paving the way for efficient energy conversion technologies.Kesterite-type materials, like Cu2ZnSnS4, are promising thermoelectric (TE) materials that convert wasteheat into electricity. These non-toxic materials are composed of abundant, easily accessible elementsand exhibit a figure of merit (zT), a quantity that measures thermoelectric efficiency, of greater than 1 attemperatures between 300 and 800K (26 to 526°C). Around 500K, kesterites undergo a transition froman ordered to a disordered one cationic structure, which affects their TE properties significantly.However, identifying optimal manufacturing conditions is time-consuming and requires multipleexperiments.Researchers from MANA used machine learning to accelerate this process. In just four experimentalcycles, they optimized the sintering process, improving the thermoelectric performance ofCu2.125Zn0.875SnS4 by 60%. The study was led by Dr. Cédric Bourgès from the International Center forYoung Scientists, along with Guillaume Lambard from Center for Basic Research on Materials as well asNaoki Sato, Makoto Tachibana, Satoshi Ishii, and Takao Mori from MANA, NIMS, Japan.The researchers employed Active Learning with Bayesian Optimization (ALMLBO), which analyzessintering parameters—such as heating rate, sintering temperature, holding time, cooling rate, andapplied pressure—alongside thermoelectric properties obtained from experiments. This approachResearchQuantum Materials FieldNanomaterials FieldResearch SupportResearch HighlightsHot TopicsHome  > Research  > Research Highlights  > Vol. 92 MANA Scientists Employ Active ･･･About MANA Research People News Room Outreach Employment AlumniSite Map Contact Us Access to MANA Website System Requirements   Text size  Standard Large  Japanese Pagehttps://www.nims.go.jp/mana/research/highlights/vol91.htmlhttps://www.nims.go.jp/mana/research/highlights/index.htmlhttps://www.nims.go.jp/mana/research/index.htmlhttps://www.nims.go.jp/mana/research/quantum_material.htmlhttps://www.nims.go.jp/mana/research/nano_material.htmlhttps://www.nims.go.jp/mana/research/researcher_support.htmlhttps://www.nims.go.jp/mana/research/highlights/index.htmlhttps://www.nims.go.jp/mana/research/hottopics/index.htmlhttps://www.nims.go.jp/mana/jp/index.htmlhttps://www.nims.go.jp/mana/research/index.htmlhttps://www.nims.go.jp/mana/research/highlights/index.htmlhttp://www.jsps.go.jp/english/e-toplevel/http://www.jsps.go.jp/english/e-toplevel/https://www.nims.go.jp/mana/index.htmlhttps://www.nims.go.jp/mana/index.htmlhttps://www.nims.go.jp/mana/about/index.htmlhttps://www.nims.go.jp/mana/research/index.htmlhttps://www.nims.go.jp/mana/member/index.htmlhttps://www.nims.go.jp/mana/news_room/2024.htmlhttps://www.nims.go.jp/mana/pror/index.htmlhttps://www.nims.go.jp/mana/recruit/index.htmlhttps://www.nims.go.jp/mana/alumni/index.htmlhttps://www.nims.go.jp/mana/siteinfo/sitemap.htmlhttps://www.nims.go.jp/mana/siteinfo/inquiry.htmlhttps://www.nims.go.jp/mana/siteinfo/access.htmlhttps://www.nims.go.jp/mana/siteinfo/accessibility.htmlhttps://www.nims.go.jp/mana/jp/research/highlights/vol92.htmlrecommended new experimental conditions, and the process was repeated until the thermoelectricproperties improved, indicated by a stabilized zT.The team began with data from 11 samples prepared using spark plasma sintering, combining copper,zinc, tin, and sulfur powders under partial vacuum. The ALMLBO model predicted sintering conditionsthat achieved a record maximum zT of 0.44 at 725K. “This method showcases how integrating machinelearning with traditional materials science accelerates discovery and optimization in complex materialsystems,” say the authors. This approach has the potential to be extended to other materials, enablingrapid innovations in photovoltaics, batteries, and electronics.ReferenceJournal Acta MaterialiaTitle Process optimization on kesterite-based ceramics for enhancing their thermoelectric performancesassisted by active machine learning approach: A tool for metal-sulfide ceramics developmentAuthors Cédric Bourgès, Guillaume Lambard, Naoki Sato, Makoto Tachibana , Satoshi Ishii, Takao MoriAffiliations International Center for Young Scientists(ICYS), Sengen 1-2-1, Tsukuba, Ibaraki 305-0047, JAPANCenter for Basic Research on Materiarls (CBRM), 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, JAPANResearch Center for Materials Nanoarchitectonics (MANA), 1-1 Namiki Tsukuba, Ibaraki 305-0044 JAPANDOI 10.1016/j.actamat.2024.120342Contact informationResearch Center for Materials Nanoarchitectonics (MANA)National Institute for Materials Science1-1 Namiki, Tsukuba, Ibaraki 305-0044 JapanPhone: +81-29-860-4710E-mail: mana-pr[AT]nims.go.jpTo receive our e-mail newsletter “MANA Research Highlights”, please send an e-mail with "MANA ResearchHighlights request” in the subject line or main text to the following address: mana-pr_at_nims.go.jp *Pleasechange "_at_ " in the email address to @.Research Center for Materials Nanoarchitectonics (MANA)National Institute for Materials Science (NIMS)1-1 Namiki Tsukuba, Ibaraki 305-0044 JAPAN+81-29-860-4709E-mail: mana[AT]nims.go.jpCopyright © National Institute for Materials Science. All rights reserved.Page Tophttps://samurai.nims.go.jp/profiles/lambard_guillaume?locale=enhttps://samurai.nims.go.jp/profiles/sato_naokihttps://samurai.nims.go.jp/profiles/tachibana_makotohttps://samurai.nims.go.jp/profiles/sishiihttps://samurai.nims.go.jp/profiles/mori_takaohttps://www.nims.go.jp/icys/https://www.nims.go.jp/cbrm/en/https://www.nims.go.jp/mana/index.htmlhttps://doi.org/10.1016/j.actamat.2024.120342http://www.nims.go.jp/eng/index.htmlhttp://www.nims.go.jp/eng/index.htmlhttps://www.jsps.go.jp/english/e-toplevel/index.htmlhttps://www.jsps.go.jp/english/e-toplevel/index.htmlhttp://www.nims.go.jp/icys/http://www.nims.go.jp/icys/https://samurai.nims.go.jp/?locale=enhttps://samurai.nims.go.jp/?locale=enhttps://www.tandfonline.com/toc/tsta20/currenthttps://www.tandfonline.com/toc/tsta20/currenthttps://www.facebook.com/wpi.mana/https://www.facebook.com/wpi.mana/https://twitter.com/wpi_manahttps://twitter.com/wpi_manahttps://www.youtube.com/channel/UCVSuGvDIrL-ZAzpaPVipslwhttps://www.youtube.com/channel/UCVSuGvDIrL-ZAzpaPVipslw