Abstract. The rapid increase in the volume of accumulated experimental data, the complexity of correlating phenomena at the molecular and nanoscale levels, and the need for a qualitatively new leap in the development of new chemical technologies lead to the active introduction of Artificial Intelligence (AI) algorithms and digital design techniques in chemical research. Using cutting edge chemical problems as examples, this report discusses current challenges focused on catalysis and new materials and dealing with the development of practical applications of AI algorithms for the creation of highly active catalysts, the analysis of spectral data, and digital optimization of experiments in synthesis and catalysis.

AI brings a transformative approach to designing materials for catalysis, and AI models, underpinned by machine learning algorithms, facilitate the rapid discovery of novel catalysts by predicting material properties and identifying optimal conditions for catalytic reactions. These models are particularly adept at handling the multi-dimensional and nonlinear nature of materials data, enabling the exploration of a vast array of chemical compositions and structures in a highly efficient manner. However, the reliability and accuracy of predictions remain a significant challenge, necessitating the development of robust and interpretable models and the incorporation of high-quality datasets. Addressing these challenges requires interdisciplinary collaboration, integrating expertise in chemistry, materials science, and data science, to advance the development of AI-driven materials design and uncover new possibilities. By overcoming these challenges, AI has the potential to revolutionize material science by accelerating the design of innovative and high-performance catalysts, driving advancements in sustainable energy and environmental protection.