Deciphering diffuse scattering with machine learning and the equivariant foundation model: the case of molten FeO.

Bridging the gap between diffuse x-ray or neutron scattering measurements and predicted structures derived from atom-atom pair potentials in disordered materials, has been a longstanding challenge in condensed matter physics. This perspective gives a brief overview of the traditional approaches employed over the past several decades. Namely, the use of approximate interatomic pair potentials that relate three-dimensional structural models to the measured structure factor and its' associated pair distribution function. The use of machine learned interatomic potentials has grown in the past few years, and has been particularly successful in the cases of ionic and oxide systems. Recent advances in large scale sampling, along with a direct integration of scattering measurements into the model development, has provided improved agreement between experiments and large-scale models calculated with quantum mechanical accuracy. However, details of local polyhedral bonding and connectivity in meta-stable disordered systems still require improvement. Here we leverage MACE-MP-0; a newly introduced equivariant foundation model and validate the results against high-quality experimental scattering data for the case of molten iron(II) oxide (FeO). These preliminary results suggest that the emerging foundation model has the potential to surpass the traditional limitations of classical interatomic potentials.

Plutonium oxide melt structure and covalency.

Advances in nuclear power reactors include the use of mixed oxide fuel, containing uranium and plutonium oxides. The high-temperature behaviour and structure of PuO2-x above 1,800 K remain largely unexplored, and these conditions must be considered for reactor design and planning for the mitigation of severe accidents. Here, we measure the atomic structure of PuO2-x through the melting transition up to 3,000 ± 50 K using X-ray scattering of aerodynamically levitated and laser-beam-heated samples, with O/Pu ranging from 1.57 to 1.76. Liquid structural models consistent with the X-ray data are developed using machine-learned interatomic potentials and density functional theory. Molten PuO1.76 contains some degree of covalent Pu-O bonding, signalled by the degeneracy of Pu 5f and O 2p orbitals. The liquid is isomorphous with molten CeO1.75, demonstrating the latter as a non-radioactive, non-toxic, structural surrogate when differences in the oxidation potentials of Pu and Ce are accounted for. These characterizations provide essential constraints for modelling pertinent to reactor safety design.

AL4GAP: Active learning workflow for generating DFT-SCAN accurate machine-learning potentials for combinatorial molten salt mixtures.

Machine learning interatomic potentials have emerged as a powerful tool for bypassing the spatiotemporal limitations of ab initio simulations, but major challenges remain in their efficient parameterization. We present AL4GAP, an ensemble active learning software workflow for generating multicomposition Gaussian approximation potentials (GAP) for arbitrary molten salt mixtures. The workflow capabilities include: (1) setting up user-defined combinatorial chemical spaces of charge neutral mixtures of arbitrary molten mixtures spanning 11 cations (Li, Na, K, Rb, Cs, Mg, Ca, Sr, Ba and two heavy species, Nd, and Th) and 4 anions (F, Cl, Br, and I), (2) configurational sampling using low-cost empirical parameterizations, (3) active learning for down-selecting configurational samples for single point density functional theory calculations at the level of Strongly Constrained and Appropriately Normed (SCAN) exchange-correlation functional, and (4) Bayesian optimization for hyperparameter tuning of two-body and many-body GAP models. We apply the AL4GAP workflow to showcase high throughput generation of five independent GAP models for multicomposition binary-mixture melts, each of increasing complexity with respect to charge valency and electronic structure, namely: LiCl-KCl, NaCl-CaCl2, KCl-NdCl3, CaCl2-NdCl3, and KCl-ThCl4. Our results indicate that GAP models can accurately predict structure for diverse molten salt mixture with density functional theory (DFT)-SCAN accuracy, capturing the intermediate range ordering characteristic of the multivalent cationic melts.

Machine learning interatomic potential for silicon-nitride (Si3N4) by active learning.

Silicon nitride (Si3N4) is an extensively used material in the automotive, aerospace, and semiconductor industries. However, its widespread use is in contrast to the scarce availability of reliable interatomic potentials that can be employed to study various aspects of this material on an atomistic scale, particularly its amorphous phase. In this work, we developed a machine learning interatomic potential, using an efficient active learning technique, combined with the Gaussian approximation potential (GAP) method. Our strategy is based on using an inexpensive empirical potential to generate an initial dataset of atomic configurations, for which energies and forces were recalculated with density functional theory (DFT); thereafter, a GAP was trained on these data and an iterative re-training algorithm was used to improve it by learning on-the-fly. When compared to DFT, our potential yielded a mean absolute error of 8 meV/atom in energy calculations for a variety of liquid and amorphous structures and a speed-up of molecular dynamics simulations by 3-4 orders of magnitude, while achieving a first-rate agreement with experimental results. Our potential is publicly available in an open-access repository.

Structural Phase Transitions between Layered Indium Selenide for Integrated Photonic Memory.

The primary mechanism of optical memoristive devices relies on phase transitions between amorphous and crystalline states. The slow or energy-hungry amorphous-crystalline transitions in optical phase-change materials are detrimental to the scalability and performance of devices. Leveraging an integrated photonic platform, nonvolatile and reversible switching between two layered structures of indium selenide (In2 Se3 ) triggered by a single nanosecond pulse is demonstrated. The high-resolution pair distribution function reveals the detailed atomistic transition pathways between the layered structures. With interlayer "shear glide" and isosymmetric phase transition, switching between the α- and ß-structural states contains low re-configurational entropy, allowing reversible switching between layered structures. Broadband refractive index contrast, optical transparency, and volumetric effect in the crystalline-crystalline phase transition are experimentally characterized in molecular-beam-epitaxy-grown thin films and compared to ab initio calculations. The nonlinear resonator transmission spectra measure of incremental linear loss rate of 3.3 GHz, introduced by a 1.5 µm-long In2 Se3 -covered layer, resulted from the combinations of material absorption and scattering.

Coarse-Grained Density Functional Theory Predictions via Deep Kernel Learning.

Scalable electronic predictions are critical for soft materials design. Recently, the Electronic Coarse-Graining (ECG) method was introduced to renormalize all-atom quantum chemical (QC) predictions to coarse-grained (CG) resolutions using deep neural networks (DNNs). While DNNs can learn complex representations that prove challenging for kernel-based methods, they are susceptible to overfitting and the overconfidence of uncertainty estimations. Here, we develop ECG within a GPU-accelerated Deep Kernel Learning (DKL) framework to enable CG QC predictions using range-separated hybrid density functional theory (DFT), obtaining a 107 speedup relative to naive all-atom QC. By treating the predicted electronic properties as random Gaussian Processes, DKL incorporates CG mapping degeneracy by learning the distribution of electronic energies as a function of CG configuration. DKL-ECG accurately reproduces molecular orbital energies from range-separated DFT while facilitating efficient training via active learning using the uncertainties provided by DKL. We show that while active learning algorithms enable efficient sampling of a more diverse configurational space relative to random sampling, all explored query methods exhibit comparable performance for the examined system. We attribute this result to the significant overlap of the feature space and output property distributions across multiple temperatures.

Uncertainty-Informed Deep Transfer Learning of Perfluoroalkyl and Polyfluoroalkyl Substance Toxicity.

Perfluoroalkyl and polyfluoroalkyl substances (PFAS) pose a significant hazard because of their widespread industrial uses, environmental persistence, and bioaccumulation. A growing, increasingly diverse inventory of PFAS, including 8163 chemicals, has recently been updated by the U.S. Environmental Protection Agency. However, with the exception of a handful of well-studied examples, little is known about their human toxicity potential because of the substantial resources required for in vivo toxicity experiments. We tackle the problem of expensive in vivo experiments by evaluating multiple machine learning (ML) methods, including random forests, deep neural networks (DNN), graph convolutional networks, and Gaussian processes, for predicting acute toxicity (e.g., median lethal dose, or LD50) of PFAS compounds. To address the scarcity of toxicity information for PFAS, publicly available datasets of oral rat LD50 for all organic compounds are aggregated and used to develop state-of-the-art ML source models for transfer learning. A total of 519 fluorinated compounds containing two or more C-F bonds with known toxicity are used for knowledge transfer to ensembles of the best-performing source model, DNN, to generate the target models for the PFAS domain with access to uncertainty. This study predicts toxicity for PFAS with a defined chemical structure. To further inform prediction confidence, the transfer-learned model is embedded within a SelectiveNet architecture, where the model is allowed to identify regions of prediction with greater confidence and abstain from those with high uncertainty using a calibrated cutoff rate.

Experimentally Driven Automated Machine-Learned Interatomic Potential for a Refractory Oxide.

Understanding the structure and properties of refractory oxides is critical for high temperature applications. In this work, a combined experimental and simulation approach uses an automated closed loop via an active learner, which is initialized by x-ray and neutron diffraction measurements, and sequentially improves a machine-learning model until the experimentally predetermined phase space is covered. A multiphase potential is generated for a canonical example of the archetypal refractory oxide, HfO_{2}, by drawing a minimum number of training configurations from room temperature to the liquid state at ∼2900 °C. The method significantly reduces model development time and human effort.

Automated Development of Molten Salt Machine Learning Potentials: Application to LiCl.

The in silico modeling of molten salts is critical for emerging "carbon-free" energy applications but is inhibited by the cost of quantum mechanically treating the high polarizabilities of molten salts. Here, we integrate configurational sampling using classical force fields with active learning to automate and accelerate the generation of Gaussian approximation potentials (GAP) for molten salts. This methodology reduces the number of expensive ab initio evaluations required for training set generation to O(100), enabling the facile parametrization of a molten LiCl GAP model that exhibits a 19 000-fold speedup relative to AIMD. The developed molten LiCl GAP model is applied to sample extended spatiotemporal scales, permitting new physical insights into molten LiCl's coordination structure as well as experimentally validated predictions of structures, densities, self-diffusion constants, and ionic conductivities. The developed methodology significantly lowers the barrier to the in silico understanding and design of molten salts across the periodic table.

Electrically sensing Hachimoji DNA nucleotides through a hybrid graphene/h-BN nanopore.

The feasibility of synthesizing unnatural DNA/RNA has recently been demonstrated, giving rise to new perspectives and challenges in the emerging field of synthetic biology, DNA data storage, and even the search for extraterrestrial life in the universe. In line with this outstanding potential, solid-state nanopores have been extensively explored as promising candidates to pave the way for the next generation of label-free, fast, and low-cost DNA sequencing. In this work, we explore the sensitivity and selectivity of a graphene/h-BN based nanopore architecture towards detection and distinction of synthetic Hachimoji nucleobases. The study is based on a combination of density functional theory and the non-equilibrium Green's function formalism. Our findings show that the artificial nucleobases are weakly binding to the device, indicating a short residence time in the nanopore during translocation. Significant changes in the electron transmission properties of the device are noted depending on which artificial nucleobase resides in the nanopore, leading to a sensitivity in distinction of up to 80%. Our results thus indicate that the proposed nanopore device setup can qualitatively discriminate synthetic nucleobases, thereby opening up the feasibility of sequencing even unnatural DNA/RNA.

Comparative dataset of experimental and computational attributes of UV/vis absorption spectra.

The ability to auto-generate databases of optical properties holds great prospects in data-driven materials discovery for optoelectronic applications. We present a cognate set of experimental and computational data that describes key features of optical absorption spectra. This includes an auto-generated database of 18,309 records of experimentally determined UV/vis absorption maxima, λmax, and associated extinction coefficients, ϵ, where present. This database was produced using the text-mining toolkit, ChemDataExtractor, on 402,034 scientific documents. High-throughput electronic-structure calculations using fast (simplified Tamm-Dancoff approach) and traditional (time-dependent) density functional theory were executed to predict λmax and oscillation strengths, f (related to ϵ) for a subset of validated compounds. Paired quantities of these computational and experimental data show strong correlations in λmax, f and ϵ, laying the path for reliable in silico calculations of additional optical properties. The total dataset of 8,488 unique compounds and a subset of 5,380 compounds with experimental and computational data, are available in MongoDB, CSV and JSON formats. These can be queried using Python, R, Java, and MATLAB, for data-driven optoelectronic materials discovery.

Unsupervised speaker adaptation for speaker independent acoustic to articulatory speech inversion.

Speech inversion is a well-known ill-posed problem and addition of speaker differences typically makes it even harder. Normalizing the speaker differences is essential to effectively using multi-speaker articulatory data for training a speaker independent speech inversion system. This paper explores a vocal tract length normalization (VTLN) technique to transform the acoustic features of different speakers to a target speaker acoustic space such that speaker specific details are minimized. The speaker normalized features are then used to train a deep feed-forward neural network based speech inversion system. The acoustic features are parameterized as time-contextualized mel-frequency cepstral coefficients. The articulatory features are represented by six tract-variable (TV) trajectories, which are relatively speaker invariant compared to flesh point data. Experiments are performed with ten speakers from the University of Wisconsin X-ray microbeam database. Results show that the proposed speaker normalization approach provides an 8.15% relative improvement in correlation between actual and estimated TVs as compared to the system where speaker normalization was not performed. To determine the efficacy of the method across datasets, cross speaker evaluations were performed across speakers from the Multichannel Articulatory-TIMIT and EMA-IEEE datasets. Results prove that the VTLN approach provides improvement in performance even across datasets.

Diamondoid-based molecular junctions: a computational study.

In this work, we deal with the computational investigation of diamondoid-based molecular conductance junctions and their electronic transport properties. A small diamondoid is placed between the two gold electrodes of the nanogap and is covalently bonded to the gold electrodes through two different molecules, a thiol group and a N-heterocyclic carbene molecule. We have shown that the thiol linker is more efficient as it introduces additional electron paths for transport at lower energies. The influence of doping the diamondoid on the properties of the molecular junctions has been investigated. We find that using a nitrogen atom to dope the diamondoids leads to a considerable increase of the zero bias conductance. For the N-doped system we show an asymmetric feature of the I-V curve of the junctions resulting in rectification within a very small range of bias voltages. The rectifying nature is the result of the characteristic shift in the bias-dependent highest occupied molecular orbital state. In all cases, the efficiency of the device is manifested and is discussed in view of novel nanotechnological applications.

Benchmark investigation of diamondoid-functionalized electrodes for nanopore DNA sequencing.

Small diamond-like particles, diamondoids, have been shown to effectively functionalize gold electrodes in order to sense DNA units passing between the nanopore-embedded electrodes. In this work, we present a comparative study of Au(111) electrodes functionalized with different derivatives of lower diamondoids. Focus is put on the electronic and transport properties of such electrodes for different DNA nucleotides placed within the electrode gap. The functionalization promotes a specific binding to DNA leading to different properties for the system, which provides a tool set to systematically improve the signal-to-noise ratio of the electronic measurements across the electrodes. Using quantum transport calculations, we compare the effectiveness of the different functionalized electrodes in distinguishing the four DNA nucleotides. Our results point to the most effective diamondoid functionalization of gold electrodes in view of biosensing applications.

Diamondoid-functionalized gold nanogaps as sensors for natural, mutated, and epigenetically modified DNA nucleotides.

Modified tiny hydrogen-terminated diamond structures, known as diamondoids, show a high efficiency in sensing DNA molecules. These diamond cages, as recently proposed, could offer functionalization possibilities for gold junction electrodes. In this investigation, we report on diamondoid-functionalized electrodes, showing that such a device would have a high potential in sensing and sequencing DNA. The smallest diamondoid including an amine modification was chosen for the functionalization. Here, we report on the quantum tunneling signals across diamondoid-functionalized Au(111) electrodes. Our work is based on quantum-transport calculations and predicts the expected signals arising from different DNA units within the break junctions. Different gating voltages are proposed in order to tune the sensitivity of the functionalized electrodes with respect to specific nucleotides. The relation of this sensitivity to the coupling or decoupling of the electrodes is discussed. Our results also shed light on the sensing capability of such a device in distinguishing the DNA nucleotides, in their natural and mutated forms.

The role of a diamondoid as a hydrogen donor or acceptor in probing DNA nucleobases.

It has been shown that diamondoids can interact with DNA by forming relatively strong hydrogen bonds to DNA units, such as nucleobases. For this interaction to occur the diamondoids must be chemically modified in order to provide donor/acceptor groups for the hydrogen bond. We show here that the exact arrangement of an amine-modified adamantane with respect to a neighboring nucleobase has a significant influence on the strength of the hydrogen bond. Whether the diamondoid acts as a hydrogen donor or acceptor in the hydrogen binding to the nucleobase affects the electronic structure and thereby the electronic band-gaps of the diamondoid-nucleobase complex. In a donor arrangement of the diamondoid close to a nucleobase, the interaction energies are weak, but the electronic band-gaps differ significantly. Exactly the opposite trend is observed in an acceptor arrangement of the diamondoid. In each of these cases the frontier orbitals of the diamondoid and the nucleobase play a different role in the binding. The results are discussed in view of a diamondoid-based biosensing device.

Chemically modified diamondoids as biosensors for DNA.

Understanding the interaction of biological molecules with materials is essential in view of the novel potential applications arising when these two are combined. To this end, we investigate the interaction of DNA with diamondoids, a broad family of tiny hydrogen-terminated diamond clusters with high technological potential. We model this interaction through quantum-mechanical computer simulations and focus on the hydrogen bonding possibilities of the different DNA nucleobases to the lower amine-modified diamondoids with respect to their relative distance and orientation. Our aim is to promote the binding between these two units, and probe this through the association energy, the electronic structure of the nucleobase-diamondoid system, and the specific role of their frontier orbitals. We discuss the relevance of our results in view of biosensing applications and specifically nanopore sequencing of DNA.