Physics-informed machine learning for inorganic scintillator discovery

Applications of inorganic scintillators-activated with lanthanide dopants, such as Ce and Eu-are found in diverse fields. As a strict requirement to exhibit scintillation, the 4f ground state (with the electronic configuration of [Xe]4fⁿ 5d⁰) and 5d₁ lowest excited state (with the electronic configuration of [Xe]4f^n-1 5d¹) levels induced by the activator must lie within the host bandgap. Here we introduce a new machine learning (ML) based search strategy for high-throughput chemical space explorations to discover and design novel inorganic scintillators. Building upon well-known physics-based chemical trends for the host dependent electron binding energies within the 4f and 5d₁ energy levels of lanthanide ions and available experimental data, the developed ML model-coupled with knowledge of the vacuum referred valence and conduction band edges computed from first principles-can rapidly and reliably estimate the relative positions of the activator's energy levels relative to the valence and conduction band edges of any given host chemistry. Using perovskite oxides and elpasolite halides as examples, the presented approach has been demonstrated to be able to (i) capture systematic chemical trends across host chemistries and (ii) effectively screen promising compounds in a high-throughput manner. While a number of other application-specific performance requirements need to be considered for a viable scintillator, the scheme developed here can be a practically useful tool to systematically down-select the most promising candidate materials in a first line of screening for a subsequent in-depth investigation.