Spectra at scale
One careful simulation answers one question. A library of them becomes training data.
From one spectrum to a library
Workflow engines run the theory ladder over thousands of structures and store each spectrum with its absorbing site and provenance. The result is training data, but only for the chemistry and approximations the library actually contains.
The library is the quiet decision in every ML-for-XAS paper: which structures it contains, which rung of the ladder computed them, and which broadening was applied decide what the model can and cannot learn. Experimental deployment adds a sim-to-real gap: calibration, resolution, preprocessing, mixtures, and model inadequacy must be represented or validated separately.
Computed collections supply controlled training data; measured archives test whether a model survives the sim-to-real gap.
- computed · crystals
500,000+ site-resolved K-edge XANES spectra for inorganic materials, computed with FEFF.
- computed · molecules
Downloadable structure–spectrum pairs for molecular transition-metal and specialized XAS problems.
- computed · ML-ready
Features, spectra, site identifiers, and data splits for eight transition-metal K-edges (Ti–Cu).
- measured · references
Experimental spectra with sample, beamline, edge, and measurement-mode context.
Before combining sources, match the absorber, edge, site, structural domain, energy convention, broadening, and preprocessing, and split by chemistry or structure rather than by individual spectrum.
Surrogates and inversion
A validated forward model can be reused inside an inverse inference, but inversion is not simply the same neural network run backward. Bayes' rule makes the added assumptions explicit:
Learn the forward map
A surrogate can predict a spectrum in milliseconds within its validated domain. In the simulated Ti coordination series below, pre-edge intensity falls as coordination rises.
A surrogate can learn such a map from a simulated library, then answer far faster than the underlying calculation. In the modeled Ti series, lower symmetry and stronger p–d mixing enhance dipole intensity, while centrosymmetric octahedral coordination suppresses it. Coordination is a proxy here, not a universal cause or calibration axis.
- Kharel, S. R. et al., OmniXAS: a universal deep-learning framework for materials X-ray absorption spectra (Phys. Rev. Materials, 2025)multitask pretraining across the K-edges of eight 3d transition metals (Ti–Cu), followed by element-specific fine-tuning
- Rankine, C. D. & Penfold, T. J., deep neural networks for rapid XANES prediction (J. Phys. Chem. A, 2020)an early Fe K-edge demonstration of rapid spectrum prediction from local structure
When the surrogate is wrong
Drag the query past the edge of the training set. The model keeps returning an ordinary-looking prediction while the truth walks away, and nothing in that number announces the change.
Inside the training range the surrogate tracks the reference closely. In-domain status lowers extrapolation risk, but validation error and model bias still matter.
Invert with uncertainty
The inverse question runs backward: given a measured spectrum, what coordination values are plausible? The estimator below propagates measurement noise through a calibration slope. A complete uncertainty budget must separately test model error, domain shift, preprocessing sensitivity, and non-uniqueness.
Inversion is estimation, not lookup. The noise band on the measurement projects through the calibration slope into an uncertainty band on the answer. This band covers measurement noise only; model error, domain shift, preprocessing, and structural non-uniqueness need separate estimates.
- Timoshenko, J. et al., supervised machine-learning determination of 3D nanoparticle structure (J. Phys. Chem. Lett., 2017)an early simulation-trained demonstration that inferred nanoparticle descriptors and coordination information from experimental XANES
- Okubo, R. et al., generative inverse estimation of 3D atomic coordination from near-edge spectra via equivariant diffusion models (arXiv, 2026)a frontier preprint generating 3D candidates in a restricted Si–O domain, demonstrated on the O K-edge of α-quartz
Autonomy
If a model can predict the spectrum and quantify its own uncertainty, it can also decide where to measure next:
The acquisition function can reward uncertainty reduction, scientifically valuable features, task-specific information, or a cost-aware combination. Maximum predictive variance is one useful strategy, not the only one.
Spend the beamtime where it matters
A fixed budget of measurement points is placed uniformly or by predictive variance. With fewer points, the value of informed placement becomes increasingly visible.
Same point budget, different placement. The adaptive policy uses only its sparse pilot measurements, then bisects intervals with large measured slopes or slope changes. The hidden truth is used afterward only to score the simulated benchmark.
- Du, M. et al., demonstration of an AI-driven workflow for dynamic X-ray spectroscopy (npj Comput. Mater., 2025)knowledge-injected Bayesian optimization tested on static and dynamic XANES, including a live APS experiment; benchmark cases used roughly 15–20% of densely sampled points
An autonomous experiment couples an instrument, an uncertainty-aware model, and an acquisition policy that selects the next point from the evidence collected so far.
Close the evidence chain with measured spectra
The companion experiment begins with revision-pinned Fe K-edge XDI reference spectra and adds acquisition noise. Compare how the measured line shapes survive the acquisition and processing chain.
- 1Run both samples in transmission and state what changes in the measured edge and white line before looking at χ(k).
- 2Increase detector noise and identify which conclusions remain stable in μ(E), k³χ(k), and |χ(R)|.
- 3Record the operational E₀, background treatment, k window, and detection mode as part of the result, not as invisible setup.
- 4Write the weakest chemical claim supported by the comparison, then name the forward calculation or reference measurement that could falsify it.
Production work adds sample and detector artifacts (self-absorption, dead time, glitches, beam damage), polarization and orientation, mixtures and structural ensembles, plus solver-specific input preparation and convergence. Every transformation should be recorded, and every conclusion tested for sensitivity to those choices.