AI/ML-Driven Design and Optimisation of Quantum Dots: A Perspective Toward Intelligent Materials Discovery

Abstract

Quantum dots (QDs), nanoscale semiconductors with size-dependent and tunable optoelectronic properties, are central to next-generation technologies spanning displays, photovoltaics, bioimaging, and quantum information systems. However, their synthesis and optimisation remain challenging due to the intricate interplay of reaction parameters and nonlinear physicochemical interactions. The integration of artificial intelligence (AI) and machine learning (ML) is redefining this landscape, enabling predictive design, autonomous synthesis control, and accelerated discovery across the QD domain. This Perspective highlights the conceptual advances and methodological innovations driving AI/ML-assisted QD research, emphasising achievements in data-driven modelling, synthesis optimisation, and materials informatics. Persistent challenges, including data scarcity, model transparency, and limited generalizability, are critically examined, alongside emerging strategies toward physics-informed and autonomous discovery frameworks. We propose that the convergence of intelligent algorithms and human expertise will catalyse a paradigm shift from empirical experimentation toward rational, self-evolving materials design in quantum dot science.