Search

Forecasting oil production from oilfields with multiple wells is an important problem in petroleum and geothermal energy extraction, as well as energy storage technologies. The accuracy of oil forecasts is a critical determinant of economic projections, hydrocarbon reserves estimation, construction of fluid processing facilities, and energy price fluctuations. Leveraging generative AI techniques, we model time series forecasting of oil and water productions across four multi-well sites spanning four decades. Our goal is to effectively model uncertainties and make precise forecasts to inform decision-making processes at the field scale. We utilize an autoregressive model known as TimeGrad and a variant of a transformer architecture named Informer, tailored specifically for forecasting long sequence time series data. Predictions from both TimeGrad and Informer closely align with the ground truth data. The overall performance of the Informer stands out, demonstrating greater efficiency compared to TimeGrad in forecasting oil production rates across all sites.

High electric fields can significantly alter catalytic environments and the resultant chemical processes. Such fields arise naturally in biological systems but can also be artificially induced through localized excitations at nanoscale. Recently, strong field excitation of dielectric nanoparticles has emerged as an avenue for studying catalysis in highly ionized environments producing extreme electric fields. While the dynamics of surface ion emission driven by ultrafast laser ionization has been heavily explored, understanding the molecular dynamics leading to fragmentation has remained elusive. To address this, we employed a multiscale approach utilizing non-adiabatic quantum molecular dynamics (NAQMD) simulations on hydrogenated silica surfaces in both bare and wetted environments under field conditions mimicking those of an ionized nanoparticle. Our findings indicate that hole localization drives fragmentation dynamics, leading to surface silanol dissociation within 50 fs and charge transfer-induced water splitting in wetted environments within 150 fs. Further insight into such ultrafast mechanisms is critical for advancement of catalysis on the surface of charged nanosystems.

Surface charges play a fundamental role in physics and chemistry, particularly in shaping the catalytic properties of nanomaterials. Tracking nanoscale surface charge dynamics remains challenging due to the involved length and time scales. Here, we demonstrate real-time access to the nanoscale charge dynamics on dielectric nanoparticles employing reaction nanoscopy. We present a four-dimensional visualization of the non-linear charge dynamics on strong-field irradiated single SiO$_2$ nanoparticles with femtosecond-nanometer resolution and reveal how surface charges affect surface molecular bonding with quantum dynamical simulations. We performed semi-classical simulations to uncover the roles of diffusion and charge loss in the surface charge redistribution process. Understanding nanoscale surface charge dynamics and its influence on chemical bonding on a single nanoparticle level unlocks an increased ability to address global needs in renewable energy and advanced healthcare., Comment: 26 pages with (4+6(SI)) figures

Diffusion in solids is a slow process that dictates rate-limiting processes in key chemical reactions. Unlike crystalline solids that offer well-defined diffusion pathways, the lack of similar structural motifs in amorphous or glassy materials poses a great scientific challenge in estimating slow diffusion time. To tackle this problem, we have developed an AI-guided long-time atomistic simulation approach: Molecular Autonomous Pathfinder (MAP) framework based on Deep Reinforcement Learning (RL), where RL agent is trained to uncover energy efficient diffusion pathways. We employ Deep Q-Network architecture with distributed prioritized replay buffer enabling fully online agent training with accelerated experience sampling by an ensemble of asynchronous agents. After training, the agents provide atomistic configurations of diffusion pathways with their energy profile. We use a piecewise Nudged Elastic Band to refine the energy profile of the obtained pathway and corresponding diffusion time on the basis of transition state theory. With MAP, we have successfully identified atomistic mechanisms along molecular diffusion pathways in amorphous silica, with time scales comparable to experiments.

Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and "smooth") model was shown to elongate the time-to-failure $t_\textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{\textrm{failure}} \propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $\left(t_{\textrm{failure}} \propto N^{-0.29}\right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia., Comment: This paper is published at International Supercomputing Conference 2023

Understanding oxidation mechanisms of layered semiconducting transition-metal dichalcogenide (TMDC) is important not only for controlling native oxide formation but also for synthesis of oxide and oxysulfide products. Here, reactive molecular dynamics simulations show that oxygen partial pressure controls not only the ZrS2 oxidation rate but also the oxide morphology and quality. We find a transition from layer-by-layer oxidation to amorphous-oxide-mediated continuous oxidation as the oxidation progresses, where different pressures selectively expose different oxidation stages within a given time window. While the kinetics of the fast continuous oxidation stage is well described by the conventional Deal-Grove model, the layer-by-layer oxidation stage is dictated by reactive bond-switching mechanisms. This work provides atomistic details and a potential foundation for rational pressure-controlled oxidation of broad TMDC materials.

Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which amino-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predicting contacts with a wide range of distances (commonly classified into short-, medium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the ProteinNet dataset show improved accuracy for contacts of all ranges using the proposed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction.

We present MISTIQS, a Multiplatform Software for Time-dependent Quantum Simulations. MISTIQS delivers end-to-end functionality for simulating the quantum many-body dynamics of systems governed by time-dependent Heisenberg Hamiltonians across multiple quantum computing platforms. It provides high-level programming functionality for generating intermediate representations of quantum circuits which can be translated into a variety of industry-standard representations. Furthermore, it offers a selection of circuit compilation and optimization methods and facilitates execution of the quantum circuits on currently available cloud-based quantum computing backends. MISTIQS serves as an accessible and highly flexible research and education platform, allowing a broader community of scientists and students to perform quantum many-body dynamics simulations on current quantum computers., Comment: 12 pages, 3 figures

The increased energy and power density required in modern electronics poses a challenge for designing new dielectric polymer materials with high energy density while maintaining low loss at high applied electric fields. Recently, an advanced computational screening method coupled with hierarchical modelling has accelerated the identification of promising high energy density materials. It is well known that the dielectric response of polymeric materials is largely influenced by their phases and local heterogeneous structures as well as operational temperature. Such inputs are crucial to accelerate the design and discovery of potential polymer candidates. However, an efficient computational framework to probe temperature dependence of the dielectric properties of polymers, while incorporating effects controlled by their morphology is still lacking. In this paper, we propose a scalable computational framework based on reactive molecular dynamics with a valence-state aware polarizable charge model, which is capable of handling practically relevant polymer morphologies and simultaneously provide near-quantum accuracy in estimating dielectric properties of various polymer systems. We demonstrate the predictive power of our framework on high energy density polymer systems recently identified through rational experimental-theoretical co-design. Our scalable and automated framework may be used for high-throughput theoretical screenings of combinatorial large design space to identify next-generation high energy density polymer materials.

We have developed a novel differential equation solver software called PND based on the physics-informed neural network for molecular dynamics simulators. Based on automatic differentiation technique provided by Pytorch, our software allows users to flexibly implement equation of atom motions, initial and boundary conditions, and conservation laws as loss function to train the network. PND comes with a parallel molecular dynamics (MD) engine in order for users to examine and optimize loss function design, and different conservation laws and boundary conditions, and hyperparameters, thereby accelerate the PINN-based development for molecular applications.

Engineering thermal transport in two dimensional materials, alloys and heterostructures is critical for the design of next-generation flexible optoelectronic and energy harvesting devices. Direct experimental characterization of lattice thermal conductivity in these ultra-thin systems is challenging and the impact of dopant atoms and hetero-phase interfaces, introduced unintentionally during synthesis or as part of deliberate material design, on thermal transport properties is not understood. Here, we use non-equilibrium molecular dynamics simulations to calculate lattice thermal conductivity of (Mo|W)Se$_2$ monolayer crystals including Mo$_{1-x}$W$_x$Se$_2$ alloys with substitutional point defects, periodic MoSe$_2$|WSe$_2$ heterostructures with characteristic length scales and scale-free fractal MoSe$_2$|WSe$_2$ heterostructures. Each of these features has a distinct effect on phonon propagation in the crystal, which can be used to design fractal and periodic alloy structures with highly tunable thermal conductivities. This control over lattice thermal conductivity will enable applications ranging from thermal barriers to thermoelectrics.

Parameterization of interatomic forcefields is a necessary first step in performing molecular dynamics simulations. This is a non-trivial global optimization problem involving quantification of multiple empirical variables against one or more properties. We present EZFF, a lightweight Python library for parameterization of several types of interatomic forcefields implemented in several molecular dynamics engines against multiple objectives using genetic-algorithm-based global optimization methods. The EZFF scheme provides unique functionality such as the parameterization of hybrid forcefields composed of multiple forcefield interactions as well as built-in quantification of uncertainty in forcefield parameters and can be easily extended to other forcefield functional forms as well as MD engines.

Predictive materials synthesis is the primary bottleneck in realizing new functional and quantum materials. Strategies for synthesis of promising materials are currently identified by time-consuming trial and error approaches and there are no known predictive schemes to design synthesis parameters for new materials. We use reinforcement learning to predict optimal synthesis schedules, i.e. a time-sequence of reaction conditions like temperatures and reactant concentrations, for the synthesis of a prototypical quantum material, semiconducting monolayer MoS$_{2}$, using chemical vapor deposition. The predictive reinforcement leaning agent is coupled to a deep generative model to capture the crystallinity and phase-composition of synthesized MoS$_{2}$ during CVD synthesis as a function of time-dependent synthesis conditions. This model, trained on 10000 computational synthesis simulations, successfully learned threshold temperatures and chemical potentials for the onset of chemical reactions and predicted new synthesis schedules for producing well-sulfidized crystalline and phase-pure MoS$_{2}$, which were validated by computational synthesis simulations. The model can be extended to predict profiles for synthesis of complex structures including multi-phase heterostructures and can also predict long-time behavior of reacting systems, far beyond the domain of the MD simulations used to train the model, making these predictions directly relevant to experimental synthesis.

High quality Van der Waals chalcogenides are important for phase change data storage, thermoelectrics, and spintronics. Using a combination of statistical design of experiments and density functional theory, we clarify how the out-of-equilibrium van der Waals epitaxial deposition methods can improve the crystal quality of Sb2Te3 films. We compare films grown by radio frequency sputtering and pulsed laser deposition (PLD). The growth factors that influence the crystal quality for each method are different. For PLD grown films a thin amorphous Sb2Te3 seed layer most significantly influences the crystal quality. In contrast, the crystalline quality of films grown by sputtering is rather sensitive to the deposition temperature and less affected by the presence of a seed layer. This difference is somewhat surprising as both methods are out-of-thermal-equilibrium plasma-based methods. Non-adiabatic quantum molecular dynamics simulations show that this difference originates from the density of excited atoms in the plasma. The PLD plasma is more intense and with higher energy than that used in sputtering, and this increases the electronic temperature of the deposited atoms, which concomitantly increases the adatom diffusion lengths in PLD. In contrast, the adatom diffusivity is dominated by the thermal temperature for sputter grown films. These results explain the wide range of Sb2Te3 and superlattice crystal qualities observed in the literature. These results indicate that, contrary to popular belief, plasma-based deposition methods are suitable for growing high quality crystalline chalcogenides., Comment: 24 pages, 8 figs

We employ few-femtosecond extreme ultraviolet (XUV) transient absorption spectroscopy to reveal simultaneously the intra- and interband carrier relaxation and the light-induced structural dynamics in nanoscale thin films of layered 2H-MoTe$_{2}$ semiconductor. By interrogating the valence electronic structure via localized Te 4$\textit{d}$ (39-46 eV) and Mo 4$\textit{p}$ (35-38 eV) core levels, the relaxation of the photoexcited hole distribution is directly observed in real time. We obtain hole thermalization and cooling times of 15$\pm$5 fs and 380$\pm$90 fs, respectively, and an electron-hole recombination time of 1.5$\pm$0.1 ps. Furthermore, excitations of coherent out-of-plane A$_{1g}$ (5.1 THz) and in-plane E$_{1g}$ (3.7 THz) lattice vibrations are visualized through oscillations in the XUV absorption spectra. By comparison to Bethe-Salpeter equation simulations, the spectral changes are mapped to real-space excited-state displacements of the lattice along the dominant A$_{1g}$ coordinate. By directly and simultaneously probing the excited carrier distribution dynamics and accompanying femtosecond lattice displacement in 2H-MoTe$_{2}$ within a single experiment, our work provides a benchmark for understanding the interplay between electronic and structural dynamics in photoexcited nanomaterials.

A thorough understanding of native oxides is essential for designing semiconductor devices. Here we report a study of the rate and mechanisms of spontaneous oxidation of bulk single crystals of ZrS$_x$Se$_{2-x}$ alloys and MoS$_2$. ZrS$_x$Se$_{2-x}$ alloys oxidize rapidly, and the oxidation rate increases with Se content. Oxidation of basal surfaces is initiated by favorable O$_2$ adsorption and proceeds by a mechanism of Zr-O bond switching, that collapses the van der Waals gaps, and is facilitated by progressive redox transitions of the chalcogen. The rate-limiting process is the formation and out-diffusion of SO$_2$. In contrast, MoS$_2$ basal surfaces are stable due to unfavorable oxygen adsorption. Our results provide insight and quantitative guidance for designing and processing semiconductor devices based on ZrS$_x$Se$_{2-x}$ and MoS$_2$, and identify the atomistic-scale mechanisms of bonding and phase transformations in layered materials with competing anions.

Simulation of the dynamics of quantum materials is emerging as a promising scientific application for noisy intermediate-scale quantum (NISQ) computers. Due to their high gate-error rates and short decoherence times, however, NISQ computers can only produce high-fidelity results for those quantum circuits smaller than some given circuit size. Dynamic simulations, therefore, pose a challenge as current algorithms produce circuits that grow in size with each subsequent time-step of the simulation. This underscores the crucial role of quantum circuit compilers to produce executable quantum circuits of minimal size, thereby maximizing the range of physical phenomena that can be studied within the NISQ fidelity budget. Here, we present two domain-specific quantum circuit compilers for the Rigetti and IBM quantum computers, specifically designed to compile circuits simulating dynamics under a special class of time-dependent Hamiltonians. The compilers outperform state-of-the-art general-purpose compilers in terms of circuit size reduction by around 25-30% as well as wall-clock compilation time by around 40% (dependent on system size and simulation time-step). Drawing on heuristic techniques commonly used in artificial intelligence, both compilers scale well with simulation time-step and system size. Code for both compilers is included to enhance the results of dynamic simulations for future researchers. We anticipate that our domain-specific compilers will enable dynamic simulations of quantum materials on near-future NISQ computers that would not otherwise be possible with general-purpose compilers., Comment: 22 pages, 3 figures, 2 tables, 2 algorithms

A highly anticipated application for quantum computers is as a universal simulator of quantum many-body systems, as was conjectured by Richard Feynman in the 1980s. The last decade has witnessed the growing success of quantum computing for simulating static properties of quantum systems, i.e., the ground state energy of small molecules. However, it remains a challenge to simulate quantum many-body dynamics on current-to-near-future noisy intermediate-scale quantum computers. Here, we demonstrate successful simulation of nontrivial quantum dynamics on IBM's Q16 Melbourne quantum processor and Rigetti's Aspen quantum processor; namely, ultrafast control of emergent magnetism by THz radiation in an atomically-thin two-dimensional material. The full code and step-by-step tutorials for performing such simulations are included to lower the barrier to access for future research on these two quantum computers. As such, this work lays a foundation for the promising study of a wide variety of quantum dynamics on near-future quantum computers, including dynamic localization of Floquet states and topological protection of qubits in noisy environments., Comment: 6 pages, 3 figures

We present a comparison of two technically distinct methods for the generation of rotationally cold, pulsed supersonic beams of methyl radicals (CH3): a plate discharge source operating in the glow regime, and a dielectric barrier discharge source (DBD). The results imply that the efficiency of both sources is comparable, and that molecular beams with similar translational and rotational temperatures are formed. Methane (CH4) proved to be the most suitable radical precursor species.