Accurate SEM-EDS quantification, automation, and machine learning enable high-throughput compositional characterization of powders.

Compositional characterization is essential for understanding and optimizing material performance. For powder-based materials underpinning many modern technologies, however, accurately and rapidly resolving the composition of individual constituent phases remains an unsolved challenge, slowing materials research and limiting autonomous laboratory platforms. Scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDS) offers a time- and cost-effective route, but artifacts generated by irregular particle morphologies fundamentally limit its reliability for quantitative compositional analysis. Here, we introduce a scalable particle-based SEM-EDS quantification scheme that overcomes these artifacts requiring only one experimental standard per element, including light elements conventionally difficult to quantify. To deploy this capability at scale, we then integrate this core quantification scheme with automated measurements and unsupervised machine-learning analysis in an end-to-end automated Python-based framework, AutoEMX, to enable identification and extraction of phase-level compositions within multiphase samples. AutoEMX consistently quantifies atomic fractions across diverse chemistries with relative errors below 10% and typically below 5%, resolving primary phases and intermixed impurities that evade conventional particle-averaged analysis. This work removes a long-standing barrier to rapid powder compositional characterization, enabling seamless integration in autonomous laboratories for accelerated discovery.