Navigating the evolution of two-dimensional carbon nitride research: integrating machine learning into conventional approaches

Abstract

Carbon nitride research has reached a promising point in today's research endeavours with diverse applications including photocatalysis, energy storage, and sensing due to their unique electronic and structural properties. Recent advances in machine learning (ML) have opened new avenues for exploring and optimizing the potential of these materials. This study presents a comprehensive review of the integration of ML techniques in carbon nitride research with an introduction to CN classifications and recent advancements. We discuss the methodologies employed, such as supervised learning, unsupervised learning, and reinforcement learning, in predicting material properties, optimizing synthesis conditions, and enhancing performance metrics. Key findings indicate that ML algorithms can significantly reduce experimental trial-and-error, accelerate discovery processes, and provide deeper insights into the structure–property relationships of carbon nitride. The synergistic effect of combining ML with traditional experimental approaches is highlighted, showcasing studies where ML driven models have successfully predicted novel carbon nitride compositions with enhanced functional properties. Future directions in this field are also proposed, emphasizing the need for high-quality datasets, advanced ML models, and interdisciplinary collaborations to fully realize the potential of carbon nitride materials in next-generation technologies.