Bayesian Optimization of the Experimental Parameters of Material Synthesis: Application to the Magnesioreduction of Rare-Earth-Free (Mn1–xFex)5Si3 Magnetocalorics
Uložené v:
| Názov: | Bayesian Optimization of the Experimental Parameters of Material Synthesis: Application to the Magnesioreduction of Rare-Earth-Free (Mn1–xFex)5Si3 Magnetocalorics |
|---|---|
| Autori: | Sylvain Le Tonquesse, Laura Agnarelli, Swathi Sakthivel |
| Prispievatelia: | Le Tonquesse, Sylvain |
| Zdroj: | Chemistry of Materials. 37:5740-5752 |
| Informácie o vydavateľovi: | American Chemical Society (ACS), 2025. |
| Rok vydania: | 2025 |
| Predmety: | [CHIM.INOR] Chemical Sciences/Inorganic chemistry, [CHIM.MATE] Chemical Sciences/Material chemistry, Intermetallics, Magnesioreduction Synthesis, Bayesian Optimization, [STAT.AP] Statistics [stat]/Applications [stat.AP], Magnetocalorics, [MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC] |
| Popis: | Optimizing complex synthesis processes remains a significant challenge in materials science, particularly when high phase purity must be achieved in complex multi-variable systems with restricted experimental throughput. Here, we demonstrate the application of a fully experimental Bayesian Optimization (BO) framework to efficiently optimize the synthesis conditions of (Mn1-xFex)5Si3 a rare-earth-free magnetocaloric material. Using magnesioreduction as the synthesis route, seven experimental parameters were iteratively refined via active learning to maximize phase purity. Phase-pure samples, including the challenging peritectoid-forming Fe5Si3 , were obtained within five active learning iterations. The approach generalizes to unseen compositions and yields chemically meaningful insights via SHAP analysis of the trained Gaussian Process model, identifying maximum temperature and SiO2 excess as key drivers of phase purity. X-ray diffraction and scanning electron microscopy confirmed high crystallinity, uniform submicron grain 1 size, and accurate compositional control in the optimized samples. Magnetic measurements revealed a near-room-temperature magnetocaloric effect in ferromagnetic Mn1.25Fe3.75Si3, with a peak -∆S$_{mag}$ of 1.06 J kg -1 K -1 at 275 K under a 2 T magnetic field change. This study establishes BO as a powerful and data-efficient framework for accelerating the synthesis of functional materials from small experimental datasets. |
| Druh dokumentu: | Article |
| Popis súboru: | application/pdf |
| Jazyk: | English |
| ISSN: | 1520-5002 0897-4756 |
| DOI: | 10.1021/acs.chemmater.5c00879 |
| Prístupová URL adresa: | https://hal.science/hal-05232344v1 https://doi.org/10.1021/acs.chemmater.5c00879 https://hal.science/hal-05232344v1/document |
| Rights: | STM Policy #29 CC BY |
| Prístupové číslo: | edsair.doi.dedup.....31c07d6cabc77f4fc0a0952c31afb1c9 |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | Optimizing complex synthesis processes remains a significant challenge in materials science, particularly when high phase purity must be achieved in complex multi-variable systems with restricted experimental throughput. Here, we demonstrate the application of a fully experimental Bayesian Optimization (BO) framework to efficiently optimize the synthesis conditions of (Mn1-xFex)5Si3 a rare-earth-free magnetocaloric material. Using magnesioreduction as the synthesis route, seven experimental parameters were iteratively refined via active learning to maximize phase purity. Phase-pure samples, including the challenging peritectoid-forming Fe5Si3 , were obtained within five active learning iterations. The approach generalizes to unseen compositions and yields chemically meaningful insights via SHAP analysis of the trained Gaussian Process model, identifying maximum temperature and SiO2 excess as key drivers of phase purity. X-ray diffraction and scanning electron microscopy confirmed high crystallinity, uniform submicron grain 1 size, and accurate compositional control in the optimized samples. Magnetic measurements revealed a near-room-temperature magnetocaloric effect in ferromagnetic Mn1.25Fe3.75Si3, with a peak -∆S$_{mag}$ of 1.06 J kg -1 K -1 at 275 K under a 2 T magnetic field change. This study establishes BO as a powerful and data-efficient framework for accelerating the synthesis of functional materials from small experimental datasets. |
|---|---|
| ISSN: | 15205002 08974756 |
| DOI: | 10.1021/acs.chemmater.5c00879 |