Machine Learning Driven Energy Transfer Prediction in Mn-Doped 2D Halide Perovskites

Abstract

Manganese (Mn2+) metal doping into lead halide perovskite has offered an expanded palette to tailor the optoelectronic properties through engineering the energy transfer between the energy donor (exciton) and energy acceptor (Mn2+). However, it still remains a challenge to precisely modulate the two different emission centers to achieve the desired optoelectronic properties due to the presence of a complex interplay of competing excited-state dynamics, involving exciton recombination, forward and backward energy transfer, and dopant-state recombination. Here, we have developed a machine learning (ML) driven predictive framework to elucidate the complex energy transfer seen in Mn(x)-doped 2D PEA2Pb(Br1–yIy)4 perovskites. With integration of the ML predictive modelwith time-resolved spectroscopy, we identify and prioritize key important features (closely associated with excitonic properties such as bandgap, full width at half-maximum (FWHM), and wavelength), governing the degree of Mn sensitization. The ML-driven approach not only allows for precise prediction of desired optoelectronic properties but also uncovers nonlinear structure–function correlations that are often overlooked by conventional approaches. Our study, thus, provides new insight into the doped system, paving the way for the rational design of next