Artificial Intelligence-Assisted Photocatalysis: A Systematic Review of Materials Design, Performance Prediction, and Reactor Optimization with Emphasis on Plasmonic Systems

Plasmonic photocatalysis offers promising alternatives for solar energy conversion, hydrogen production, CO2 reduction, and pollutant degradation. However, its performance depends on multiple variables related to composition, structure, optical and electronic properties, charge transfer, operating conditions, and reactor configuration. This systematic review analyzes the application of artificial intelligence (AI) and machine learning in photocatalysis, with an emphasis on plasmonic materials, during the period 2020–2026. Using a PRISMA-based methodology, supplemented by bibliometric and technical–comparative analyses, we examined material design and selection, the prediction of photocatalytic performance, reactor optimization, and the construction of datasets. The results show that AI models enable the exploration of compositional and synthetic spaces, the prediction of optical and electronic properties, the optimization of heterojunctions and core–shell structures, and the estimation of H2 production, CO2 conversion, and pollutant degradation, in addition to reducing the computational cost of simulations through surrogate models. Integration with DFT calculations, CFD simulations, active learning, and inverse design expands its application to interconnected predictive and experimental systems. However, limitations persist regarding small and heterogeneous datasets, insufficient external validation, interpretability, and low transferability. Advances in the field will require standardized and traceable data, physically meaningful descriptors, and models that bridge the material, reaction, and reactor scales.