Materials genes of heterogeneous catalysis from clean experiments and artificial intelligence.

ABSTRACT: The performance in heterogeneous catalysis is an example of a complex materials function, governed by an intricate interplay of several processes (e.g., the different surface chemical reactions, and the dynamic restructuring of the catalyst material at reaction conditions). Modeling the full catalytic progression via first-principles statistical mechanics is impractical, if not impossible. Instead, we show here how a tailored artificial-intelligence approach can be applied, even to a small number of materials, to model catalysis and determine the key descriptive parameters ("materials genes") reflecting the processes that trigger, facilitate, or hinder catalyst performance. We start from a consistent experimental set of "clean data," containing nine vanadium-based oxidation catalysts. These materials were synthesized, fully characterized, and tested according to standardized protocols. By applying the symbolic-regression SISSO approach, we identify correlations between the few most relevant materials properties and their reactivity. This approach highlights the underlying physicochemical processes, and accelerates catalyst design. IMPACT STATEMENT: Artificial intelligence (AI) accepts that there are relationships or correlations that cannot be expressed in terms of a closed mathematical form or an easy-to-do numerical simulation. For the function of materials, for example, catalysis, AI may well capture the behavior better than the theory of the past. However, currently the flexibility of AI comes together with a lack of interpretability, and AI can only predict aspects that were included in the training. The approach proposed and demonstrated in this IMPACT article is interpretable. It combines detailed experimental data (called "clean data") and symbolic regression for the identification of the key descriptive parameters (called "materials genes") that are correlated with the materials function. The approach demonstrated here for the catalytic oxidation of propane will accelerate the discovery of improved or novel materials while also enhancing physical understanding. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1557/s43577-021-00165-6.

Transition from 2D to 3D SBA-15 by High-Temperature Fluoride Addition and its Impact on the Surface Reactivity Probed by Isopropanol Conversion.

A systematic variation of the SBA-15 synthesis conditions and their impact on the structural and chemical characteristics are reported. An incremental alteration of the hydrothermal aging temperature and time was used to induce changes of the highly ordered SBA-15 structure. Any effects on the total surface area, mesopores size, micropore contributions, and pore connectivity are amplified by a combined incremental increase of the NH4 F concentration. Based on changes of the unit-cell parameter as a function of the mesopore size, and a feature in the low-angle XRD pattern, useful descriptors for the disorder of the corresponding SBA-15 are identified. An additional analysis of the Brunauer-Emmett-Teller (BET) surface area and pore size distributions enables investigations of the structural integrity of the material. This systematic approach allows the identification of coherencies between the evolution of physical SBA-15 properties. The obtained correlations of the surface and structural characteristics allow the discrimination between highly ordered 2D SBA-15, disordered 3D SBA-15, and highly nonuniform silica fractions with mainly amorphous character. The fluoride-induced disintegration of the silica structure under hydrothermal conditions was also verified by TEM. A direct influence of the structural adaption on the chemical properties of the surface was demonstrated by isopropanol conversion and H/D exchange monitored by FTIR analysis as sensitive probes for acid and redox active surface sites.