🤖 AI Summary
X-ray absorption spectroscopy (XAS) analysis has long suffered from high computational costs and heavy reliance on domain expertise, hindering high-throughput and autonomous experimentation. To address this, we propose OmniXAS—a novel framework introducing a triple-transfer-learning paradigm: (i) local structural representation via M3GNet, (ii) cross-element multi-task pretraining followed by element-specific fine-tuning, and (iii) cross-fidelity adaptive transfer. OmniXAS enables rapid, accurate, element-generalized (Ti–Cu, eight 3d transition metals), and fidelity-agnostic K-edge XAS spectral prediction. Compared to single-element models, it improves average prediction accuracy by 69%; it accelerates modeling tenfold over conventional feature engineering; and its throughput exceeds first-principles calculations by three to four orders of magnitude. These advances significantly advance the automation and scalability of XAS analysis.
📝 Abstract
X-ray absorption spectroscopy (XAS) is a powerful characterization technique for probing the local chemical environment of absorbing atoms. However, analyzing XAS data presents significant challenges, often requiring extensive, computationally intensive simulations, as well as significant domain expertise. These limitations hinder the development of fast, robust XAS analysis pipelines that are essential in high-throughput studies and for autonomous experimentation. We address these challenges with OmniXAS, a framework that contains a suite of transfer learning approaches for XAS prediction, each contributing to improved accuracy and efficiency, as demonstrated on K-edge spectra database covering eight 3d transition metals (Ti-Cu). The OmniXAS framework is built upon three distinct strategies. First, we use M3GNet to derive latent representations of the local chemical environment of absorption sites as input for XAS prediction, achieving up to order-of-magnitude improvements over conventional featurization techniques. Second, we employ a hierarchical transfer learning strategy, training a universal multi-task model across elements before fine-tuning for element-specific predictions. Models based on this cascaded approach after element-wise fine-tuning outperform element-specific models by up to 69%. Third, we implement cross-fidelity transfer learning, adapting a universal model to predict spectra generated by simulation of a different fidelity with a higher computational cost. This approach improves prediction accuracy by up to 11% over models trained on the target fidelity alone. Our approach boosts the throughput of XAS modeling by orders of magnitude versus first-principles simulations and is extendable to XAS prediction for a broader range of elements. This transfer learning framework is generalizable to enhance deep-learning models that target other properties in materials research.