POMFinder: Identifying polyoxometalate cluster structures from pair distribution function data using explainable machine learning

Characterisation of material structure with Pair Distribution Function (PDF) analysis typically involves refining a structure model against an experimental dataset. However, finding or constructing a suitable atomic model for PDF modelling can be an extremely labour-intensive task, requiring carefully browsing through large numbers of possible models. We present POMFinder, a machine learning (ML) classifier that rapidly screens a database of structures, here polyoxometalate (POM) clusters, to identify candidate structures for PDF data modelling. The approach is demonstrated to identify suitable POMs on experimental data, including in situ data collected with fast acquisition time. This automated approach shows significant potential for identifying suitable structure models for structure refinements to extract quantitative, structural parameters in materials chemistry research. The code is open source and user-friendly, making it accessible to those without prior ML knowledge. We also demonstrate that POMFinder offers a promising modelling framework for combined modelling of multiple scattering techniques compared to conventional refinement methods.