Filtern
Dokumenttyp
Sprache
- Englisch (3)
- Mehrsprachig (1)
Schlagworte
- Metal phosphates (2)
- Sequential learning (2)
- Automated synthesis (1)
- Calcined clay (1)
- DFG SPP 2005 (1)
- Grignard reaction (1)
- Grignard-Reaktion (1)
- High entropy (1)
- High-entropy (1)
- Limestone powder (1)
Organisationseinheit der BAM
- 6 Materialchemie (3)
- 6.3 Strukturanalytik (3)
- 7 Bauwerkssicherheit (3)
- 7.6 Korrosion und Korrosionsschutz (2)
- 8 Zerstörungsfreie Prüfung (2)
- 8.0 Abteilungsleitung und andere (2)
- 1 Analytische Chemie; Referenzmaterialien (1)
- 1.4 Non-Target-Analytik (1)
- 6.0 Abteilungsleitung und andere (1)
- 7.4 Baustofftechnologie (1)
To accelerate high-entropy metal phosphate (HEMP) discovery, we employed a Random Forest regression model within a SLAMD framework. Trained on limited initial data, the model efficiently explored the vast compositional space to predict a novel five-metal phosphate, which was then successfully synthesized and validated experimentally.
A thorough characterization of base materials is the prereq- uisite for further research. In this paper, the characterization data of the reference materials (CEM I 42.5 R, limestone pow- der, calcined clay and a mixture of these three components) used in the second funding phase of the priority program 2005 of the German Research Foundation (DFG SPP 2005) are presented under the aspects of chemical and min- eralogical composition as well as physical and chemical properties. The data were collected based on tests performed by up to eleven research groups involved in this cooperative program.
A big problem with the chemistry literature is that it is not standardized with respect to precise operational parameters, and real time corrections are hard to make without expert knowledge. This lack of context means difficult reproducibility because many steps are ambiguous, and hence depend on tacit knowledge. Here we present the integration of online NMR into an automated chemical synthesis machine (CSM aka. “Chemputer” which is capable of small-molecule synthesis using a universal programming language) to allow automated analysis and adjustment of reactions on the fly. The system was validated and benchmarked by using Grignard reactions which were chosen due to their importance in synthesis. The system was monitored in real time using online-NMR, and spectra were measured continuously during the reactions. This shows that the synthesis being done in the Chemputer can be dynamically controlled in response to feedback optimizing the reaction conditions according to the user requirements.
Transition metal phosphates (TMPs) are extensively explored for electrochemical and catalytical applications due to their structural versatility and chemical stability. Within this material class, novel high-entropy metal phosphates (HEMPs)─containing multiple transition metals combined into a single-phase structure─are particularly promising, as their compositional complexity can significantly enhance functional properties. However, the discovery of suitable HEMP compositions is hindered by the vast compositional design space and complex or very specific synthesis conditions. Here, we present a data-driven strategy combining automated wet-chemical synthesis with a Sequential Learning App for Materials Discovery (SLAMD) framework (Random Forest regression model) to efficiently explore and optimize HEMP compositions. Using a limited set of initial experiments, we identified multimetal compositions in a single-phase crystalline solid. The model successfully predicted a novel Co0.3Ni0.3Fe0.2Cd0.1Mn0.1 phosphate octahydrate phase, validated experimentally, demonstrating the effectiveness of the machine learning approach. This work highlights the potential of integrating automated synthesis platforms with data-driven algorithms to accelerate the discovery of high-entropy materials, offering an efficient design pathway to advanced functional materials.
