X-ray spectroscopy delivers strong impact across the physical and biological sciences by providing end-users with highly-detailed information about the electronic and geometric structure of matter. To decode this information in challenging cases, e.g. in operando catalysts, batteries, and temporally-evolving systems, advanced theoretical calculations are necessary. The complexity and resource requirements often render these out of reach for end-users, and therefore data are often not interpreted exhaustively, leaving a wealth of valuable information unexploited. In this paper, we introduce supervised machine learning of X-ray absorption spectra, by developing a deep neural network (DNN) that is able to estimate Fe K -edge X-ray absorption near-edge structure spectra in less than a second with no input beyond geometric information about the local environment of the absorption site. We predict peak positions with sub-eV accuracy and peak intensities with errors over an order of magnitude smaller than the spectral variations that the model is engineered to capture. The performance of the DNN is promising, as illustrated by its application to the structural refinement 1 of iron(II)tris(bipyridine) and nitrosylmyoglobin, but also highlights areas for which future developments should focus.

The development of high-brilliance third- and fourth-generation light sources such as synchrotrons and X-ray free-electron lasers (XFELs), the emergence of laboratory-based X-ray spectrometers, and instrumental and methodological advances in X-ray absorption (XAS) and (non)­resonant emission (XES and RXES/RIXS) spectroscopies have had far-reaching effects across the natural sciences. However, new kinds of experiments, and their ever-higher resolution and data acquisition rates, have brought acutely into focus the challenge of accurately, quickly, and cost-effectively analyzing the data; a far-from-trivial task that demands detailed theoretical calculations that are capable of capturing satisfactorily the underlying physics. The past decade has seen significant advances in the theory of core-hole spectroscopies for this purpose, driven by all of the developments above andcruciallya surge in demand. In this Perspective, we discuss the challenges of calculating core-excited states and spectra, and state-of-the-art developments in electronic structure theory, dynamics, and data-driven/machine-led approaches toward their better description.

The affordable, accurate, and reliable prediction of spectroscopic observables plays a key role in the analysis of increasingly-complex experiments. In this Article, we develop and deploy a deep neural network (DNN) - XANESNET - for predicting the lineshape of first-row transition metal K-edge X-ray absorption near-edge structure (XANES) spectra. XANESNET predicts the spectral intensities using only information about the local coordination geometry of the transition metal complexes encoded in a feature vector of weighted atom-centred symmetry functions (wACSF). We address in detail the calibration of the feature vector for the particularities of the problem at hand, and we explore the individual feature importances to reveal the physical insight that XANESNET obtains at the Fe K-edge. XANES- NET relies on only a few judiciously-selected features - radial information on the first and second coordination shells suffices, along with angular information sufficient to separate satisfactorily key coordination geometries. The feature importance is found to reflect the XANES spectral window under consideration and is consistent with the expected underlying physics. We subsequently apply XANESNET at nine first-row transition metal (Ti-Zn) K-edges. It can be optimised in as little as a minute, predicts instantaneously, and provides K-edge XANES spectra with an average accuracy of ca. {plus minus} 2-4% in which the positions of prominent peaks are matched with a > 90% hit rate to sub-eV (ca. 0.8 eV) error.

Understanding how deprotonation impacts the photophysics of UV filters is critical to better characterize how they behave in key alkaline environments including surface waters and coral reefs. Using anion photodissociation spectroscopy, we have measured the intrinsic absorption electronic spectroscopy (400–214 nm) and numerous accompanying ionic photofragmentation pathways of the benzophenone-4 anion ([BP4–H] − ). Relative ion yield plots reveal the locations of the bright S 1 and S 3 excited states. For the first time for an ionic UV filter, ab initio potential energy surfaces are presented to provide new insight into how the photofragment identity maps the relaxation pathways. These calculations reveal that [BP4–H] − undergoes excited-state decay consistent with a statistical fragmentation process where the anion breaks down on the ground state after nonradiative relaxation. The broader relevance of the results in providing a basis for interpreting the relaxation dynamics of a wide range of gas-phase ionic systems is discussed.

Non-adiabatic multiconfigurational molecular dynamics simulations have revealed a molecular "Newton's Cradle" that activates on absorption of light in the mid-UV and assists the S/S internal conversion process in 1,2-dithiane, protecting the disulfide bond from photodamage. This communication challenges contemporary understanding of the S/S internal conversion process in 1,2-dithiane and presents a classically-intuitive reinterpretation of experimental evidence.