SEARCH · Engineering Papers

Results for “predictive mapping”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 595 records · Page 33

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Event generator for jet tomography in electron-ion collisions

We develop the first event generator, the electron-heavy-ion-jet-interaction-generator (eHIJING), for the jet tomography study of electron-ion collisions. In this generator, energetic jet partons produced from the initial hard scattering undergo multiple collisions with the nuclear target. The collision rate is proportional to the transverse-momentum-dependent (TMD) gluon density in the nucleus, which is given by a simple model inspired by the physics of gluon saturation. Medium-modified QCD splitting functions within the higher-twist (HT) and generalized higher-twist (GHT) frameworks are utilized to simulate parton showering in the nuclear medium that takes into account the non-Abelian Landau-Pomeranchuck-Midgal interference effect. Employing eHIJING, we revisit hadron production in semi-inclusive deep inelastic scattering (SIDIS) as measured by EMC, HERMES, and recent CLAS experiments. eHIJING with both GT and GHT frameworks gives reasonably good descriptions of these experimental data. Predictions for experiments at the future electron-ion colliders are also provided. It is demonstrated that future measurements of the transverse momentum broadening of single hadron spectra can be used to map out the two-dimensional kinematic (Q 2 , x B ) dependence of the jet transport coefficient $\hat{q}$ in cold nuclear matter.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2020

Exciton-Phonon Interaction and Relaxation Times from First Principles

Electron-phonon interactions are key to understanding the dynamics of electrons in materials and can be modeled accurately from first principles. However, when electrons and holes form Coulomb-bound states (excitons), quantifying their interactions and scattering processes with phonons remains an open challenge. Here we show a rigorous approach for computing exciton-phonon (ex-ph) interactions and the associated exciton dynamical processes from first principles. Starting from the ab initio Bethe-Salpeter equation, we derive expressions for the ex-ph matrix elements and relaxation times. Finally, we apply our method to bulk hexagonal boron nitride, for which we map the ex-ph relaxation times as a function of exciton momentum and energy, analyze the temperature and phonon-mode dependence of the ex-ph scattering processes, and accurately predict the phonon-assisted photoluminescence. The approach introduced in this work is general and provides a framework for investigating exciton dynamics in a wide range of materials.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2024

DS-GL: Advancing Graph Learning via Harnessing the Power of Nature within Dynamic Systems

With the rapid digitization of the world, an increasing number of real-world applications are turning to nonEuclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising machines, i.e., dynamic systems composed of CMOS components, have emerged as a new approach that harnesses the inherent power of natural annealing within dynamic systems to efficiently resolve binary optimization problems and have been adopted for traditional graph computation, such as max-cut. However, when performing complex Graph Learning (GL) tasks, Ising machines face significant hurdles: (i) they are inherently binary and thus ill-suited for real-valued problems; (ii) their expensive all-to-all coupling network that guarantees effective natural annealing poses daunting scalability concerns. To address these challenges, this paper proposes a nature-powered graph learning framework dubbed DS-GL, which is the first effort to transform the process of solving graph learning problems into the natural annealing process within a parameterized dynamic system embodied as a CMOS chip. To tackle the two major hurdles, DS-GL first augments the Ising machine architecture to modify the self-reaction term of its Hamiltonian function from linear to quadratic, effectively serving as an energy regulator. This adjustment maintains the system’s original physical interpretation while enabling it to process continuous, real-valued data. Second, to address the scaling issue, DS-GL further upgrades the real-valued dense Ising machine by decomposing it into a mesh-based multi-PE dynamic system that supports efficient distributed spatial-temporal co-annealing across different PEs through sparse interconnects. By exploiting the inherent sparsity and component structures in real-world graphs, DS-GL is able to map complex graph learning tasks onto the scalable dynamic system while maintaining high accuracy. Evaluations with three diverse GL applications across six real-world datasets, including traffic flow and COVID-19 prediction, show that DS-GL can deliver from 102× to 106× speedups and 500× energy reduction over Graph Neural Networks on GPUs, with 5% - 20% accuracy enhancement.

Song, Ruibing↗

DOE OSTI2024

ML-based Dimension Reduction Strategies

Deep learning (DL)--based surrogate models have achieved success in various applications in carbon capture and storage (CCS). However, the model training on high-dimensional spaces is computationally expensive and impractical for large-scale and complex geological models, because the models usually contain hundreds of thousands to millions of grid cells, each with a set of parameters. Furthermore, the high cost of generating training data with sufficient variation is another limitation of model training on high-dimensional spaces, which may result in overfitting and reduce the model efficiency and prediction performance. We proposed the workflow incorporating dimension reduction methods and deep learning models, which aim to extract the latent variables of input parameters and output state variables, and then build the mapping function at the latent spaces. The proposed workflow can significantly reduce the computational complexity in solving both forward and inverse problems compared to models trained on high-dimensional spaces. Dimensionality reduction models showed great potential in workflows for fast reservoir simulation, history matching, prior model generation, visualization, and more, ultimately enhancing DL model performance in related SMART Work Packages.

Hosseini, Seyyed↗

DOE OSTI2025

Compare low-gain 1D and 3D models toward a storage ring-based X-ray free-electron-laser oscillator

Fourth-generation diffraction-limited synchrotron light sources (DL-SLS) present a compelling platform for advanced light source applications due to their ultra-low emittance (around tens of picometers), sub-micrometer beam stability, and high repetition rates (greater than 1 MHz). Despite these advantages, fundamental limitations, such as long bunch durations (tens of picoseconds), large relative energy spread (~10⁻³), and low peak current (<300 A), have hindered their effectiveness in free-electron laser (FEL) applications. Using a low-gain three-dimensional (3D) model based on NSLS-II upgrade lattice parameters, we demonstrate that a 6% single-pass gain is achievable with an optimized transverse gradient undulator (TGU). Concurrently, recent advances in X-ray optics—specifically, a four-mirror bow-tie resonator utilizing diamond mirrors and beryllium compound refractive lenses (CRLs)—enable total round-trip losses below 4% and an output coupling efficiency near 1%, rendering a Storage Ring based X-ray FEL oscillator (XFELO) a realistic possibility. In the 3D framework, the TGU effectively mitigates the detrimental effects of large energy spread by spatially dispersing the beam, leading to enhanced gain relative to conventional one-dimensional (1D) models. We establish both analytical and numerical connections between the 1D and 3D descriptions, leveraging GENESIS simulations to map equivalent gain conditions. While 1D resonance is defined in the energy domain, the 3D TGU system shifts the resonance dependence to transverse gradient and dispersion parameters. Once optimized, this framework allows predictive modeling using 1D formulas, which can then be validated through full 3D simulations.

43 PARTICLE ACCELERATORS↗

DOE OSTI2023

Data for Genome-Wide Association and Genomic Prediction for Yield and Component Traits of Miscanthus sacchariflorus

Accelerating biomass improvement is a major goal of miscanthus breeding. The development and implementation of genomic-enabled breeding tools, like marker-assisted selection (MAS) and genomic selection, has the potential to improve the efficiency of miscanthus breeding. The present study conducted genome-wide association (GWA) and genomic prediction of biomass yield and 14 yield-components traits in Miscanthus sacchariflorus . We evaluated a diversity panel with 590 accessions of M. sacchariflorus grown across four years in one subtropical and three temperate locations and genotyped with 268,109 single-nucleotide polymorphisms (SNPs). The GWA study identified a total of 835 significant SNPs and 674 candidate genes across all traits and locations. Of the significant SNPs identified, 280 were localized in mapped quantitative trait loci intervals and proximal to SNPs identified for similar traits in previously reported miscanthus studies, providing additional support for the importance of these genomic regions for biomass yield. Our study gave insights into the genetic basis for yield-component traits in M. sacchariflorus that may facilitate marker-assisted breeding for biomass yield. Genomic prediction accuracy for the yield-related traits ranged from 0.15 to 0.52 across all locations and genetic groups. Prediction accuracies within the six genetic groupings of M. sacchariflorus were limited due to low sample sizes. Nevertheless, the Korea/NE China/Russia (N = 237) genetic group had the highest prediction accuracy of all genetic groups (ranging 0.26–0.71), suggesting that with adequate sample sizes, there is strong potential for genomic selection within the genetic groupings of M. sacchariflorus . This study indicated that MAS and genomic prediction will likely be beneficial for conducting population-improvement of M. sacchariflorus .

Biomass Analytics↗

DOE OSTI2020

Modeling the Functional Forms of Grid Disturbances

This report introduces a functional form that may be used to quantitatively predict the impacts of new grid tools and changing system qualities on the likelihoods, durations, and depths of various grid disturbances. Each disturbance scenario is modeled to have three component stages—avoidance, reactance and recovery, which together parametrically estimate one disturbance’s impacts. The modeled scenario is then placed and replicated within an analysis period to represent the likelihood or frequency of the scenario and its consequent impacts. Whereas analysts have struggled to define and apply metrics for grid resilience, the functional form introduced by this report shares units of measurement with accepted grid-status measures (e.g., numbers of customers currently experiencing a service outage). Furthermore, the integrated and averaged functional form over an analysis period provides a meaningful normalized performance metric (e.g., customer outage minutes per year) that is ultimately independent of the duration of the period of. The approach may be applied similarly regardless of the severity or frequency of the disturbances that are being analyzed. Because metrics can be chosen to be identical in both the hypothetical future and the actual historical past, the historical past eventually becomes the test of the future predictions, at least in a statistical sense. The authors originally developed this approach to facilitate analysis of the effects of transactive energy (TE) systems effects on electric power grid resilience. TE systems invite energy suppliers and consumers to actively collaborate toward the discovery of, and their responses to, the locational value of energy. The findings from this process are often embodied as energy prices, the dynamics of which indicate the locational value of energy and can further represent important grid service needs. While some academic papers claim to quantify the value of a specific TE system design toward grid resilience, the answer, in general, has been elusive. Not only do multiple and conflicting definitions of resilience and reliability exist, but countless TE systems are being invented. We conclude the following: (1) The ideal analysis should harmonize rather than differentiate resilience and reliability. Therefore, this report uses the more general term disturbance whenever the overloaded terms resilience and reliability can be avoided. (2) The effectiveness of TE systems must be mapped to underlying qualities of a TE system, thereby avoiding presumptions that every TE design offers similar advantages. The authors seek to evaluate the parametric effects of TE system qualities (e.g., spatial granularity, granularity of time steps, length of future prediction horizon) on avoiding, reacting to, and recovering from grid disturbances. Furthermore, any advantages (or disadvantages) must be fairly compared with the many alternative tools, systems, and strategies that might offer comparable benefits.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

Dual-map framework for noise characterization of quantum computers

In order to understand the capabilities and limitations of quantum computers, it is necessary to develop methods that efficiently characterize and benchmark error channels present on these devices. In this paper, we present a method that faithfully reconstructs a marginal (local) approximation of the effective noise (MATEN) channel, that acts as a single layer at the end of the circuit. We first introduce a dual-map framework that allows us to analytically derive expectation values of observables with respect to noisy circuits. These findings are supported by numerical simulations of the quantum approximate optimization algorithm (QAOA) that also justify the MATEN, even in the presence of nonlocal errors that occur during a circuit. Finally, we demonstrate the performance of the method on Rigetti's Aspen-11 quantum computer for QAOA circuits up to six qubits, successfully predicting the observed measurements on a majority of the qubits.

Sud, James↗

DOE OSTI2021

Quartic cumulant of baryon number in the presence of a QCD critical point

In the context of the ongoing search for the QCD critical point at the Relativistic Heavy-Ion Collider, we study the equation of state near the critical point in the temperature and baryon chemical potential plane. We use the parametric representation introduced in earlier literature, which maps the universal three-dimensional Ising equation of state onto the QCD phase diagram using several non-universal parameters. We focus on the quartic cumulant of the baryon number, or baryon number susceptibility χ$^ B_4$, which can be accessed experimentally via net-proton fluctuation kurtosis measurements. It was originally predicted, through universality arguments based on the leading singular contribution, that χ$^ B_4$ and net-proton kurtosis should show a specific nonmonotonic behavior due to the critical point. In particular, when following the freeze-out curve on the phase diagram by decreasing beam energy, the kurtosis is expected to dip, and then peak, when the beam energy scan passes close to the critical point. We study the effects of the nonuniversal and thus far unknown parameters of the Ising-to-QCD mapping on the behavior of χ$^ B_4$. We find that, while the peak remains a solid feature, the presence of the critical point does not necessarily cause a dip in χ$^ B_4$ on the freeze-out line below the transition temperature. The critical point contribution to the dip appears only for a narrow set of mapping parameters, when subleading singular terms are sufficiently suppressed.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2024

Estimating snow cover from high-resolution satellite imagery by thresholding blue wavelengths: Supporting Data

The extent and duration of snow cover is predicted to be altered as the climate changes. Developing high-resolution estimates of snow cover change is crucial for estimating changes in snow cover and the effects of these changes on watershed and ecosystems processes. Remote sensing tools have been a common method for rapidly mapping snow covered area (SCA) across a landscape. The most common remote sensing method for estimating SCA uses satellite-based calculations of the normalized difference snow index (NDSI), which relies on spectral measurements in the shortwave-infrared wavelengths (SWIR). NDSI is effective at catchment- to regional-scale estimates of SCA, but due to spatial resolution limitations of SWIR measurements, NDSI cannot be used to assess fine-scale SCA. In this work, we develop a new algorithm, called the Blue Snow Threshold (BST) algorithm, that maps high-resolution SCA by calculating a threshold on the blue wavelengths from high-resolution satellite imagery. This data package includes Orthorectified IKONOS-2 imagery (IkonosTestImage.tif) from August 14, 2004 at 1.00 meters Ground Sample Distance for Cook Inlet, Alaska (59.966414 , -152.982975). The Blue Snow Threshold algorithm (BST.py) was then used to produce a snow cover estimate (IkonosTestImage_BST.tif) for this study area. Additional imagery metadata is included in the ImageInfo.txt file. See Thaler et al., 2023 (https://doi.org/10.1016/j.rse.2022.113403) for more information about the BST algorithm.The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a 15-year research effort (2012-2027) to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research.The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Neural operators for stochastic modeling of nonlinear structural system response to natural hazards

Traditionally, neural networks have been employed to learn the mapping between finite-dimensional Euclidean spaces. However, recent research has opened up new horizons, focusing on the utilization of deep neural networks to learn operators capable of mapping infinite-dimensional function spaces. Here, in this work, we employ two state-of-the-art neural operators, the deep operator network (DeepONet) and the Fourier neural operator (FNO) for the prediction of the nonlinear time history response of structural systems exposed to natural hazards, such as earthquakes and windstorms. Specifically, we propose two architectures, a self-adaptive FNO and a fast Fourier transform-based DeepONet (DeepFNOnet), where we employ a FNO beyond the DeepONet to learn the discrepancy between the ground truth and the solution predicted by the DeepONet. To demonstrate the efficiency and applicability of the architectures, two problems are considered. In the first, we use the proposed model to predict the seismic nonlinear dynamic response of a six-story shear building subject to stochastic ground motions. In the second problem, we employ the operators to predict the wind-induced nonlinear dynamic response of a high-rise building while explicitly accounting for the stochastic nature of the wind excitation. In both cases, the trained metamodels achieve high accuracy while being orders of magnitude faster than their corresponding high-fidelity models.

DeepONet↗

DOE OSTI2021

An antisite defect mechanism for room temperature ferroelectricity in orthoferrites

Single-phase multiferroic materials that allow the coexistence of ferroelectric and magnetic ordering above room temperature are highly desirable, motivating an ongoing search for mechanisms for unconventional ferroelectricity in magnetic oxides. Here, we report an antisite defect mechanism for room temperature ferroelectricity in epitaxial thin films of yttrium orthoferrite, YFeO 3 , a perovskite-structured canted antiferromagnet. A combination of piezoresponse force microscopy, atomically resolved elemental mapping with aberration corrected scanning transmission electron microscopy and density functional theory calculations reveals that the presence of Y Fe antisite defects facilitates a non-centrosymmetric distortion promoting ferroelectricity. This mechanism is predicted to work analogously for other rare earth orthoferrites, with a dependence of the polarization on the radius of the rare earth cation. Our work uncovers the distinctive role of antisite defects in providing a mechanism for ferroelectricity in a range of magnetic orthoferrites and further augments the functionality of this family of complex oxides for multiferroic applications.

36 MATERIALS SCIENCE↗

DOE OSTI2023

A smart alarm for particle accelerator beamline operations

We present the initial results of a proof-of-concept 'smart alarm' for the Continuous Electron Beam Accelerator Facility injector beamline at Jefferson Lab. To minimize machine downtime and improve operational efficiency, an autonomous alarm system able to identify and diagnose unusual machine states is needed. Our approach leverages a trained neural network capable of alerting operators (a) when an anomalous condition exists in the beamline and (b) identifying the element setting that is the root cause. The tool is based on an inverse model that maps beamline readings (diagnostic readbacks) to settings (beamline attributes operators can modify). The model takes as input readings from the machine and computes machine settings which are compared to control setpoints. Instances where predictions differ from setpoints by a user-defined threshold are flagged as anomalous. Given data corresponding to 354 anomalous injector configurations, the model can narrow the root cause of an anomalous condition to three potential candidates with 94.6% accuracy. Furthermore, compared to the current method of identifying anomalous conditions which raises an alarm when machine parameters drift outside their normal tolerances, the data-driven model can identify 83% more anomalous conditions.

43 PARTICLE ACCELERATORS↗

DOE OSTI2020

Selective Sampling for Sensor Type Classification in Buildings

A key barrier to applying any smart technology to a building is the requirement of locating and connecting to the necessary resources among the thousands of sensing and control points, i.e., the metadata mapping problem. Existing solutions depend on exhaustive manual annotation of sensor metadata --- a laborious, costly, and hardly scalable process. To reduce the amount of manual effort required, this paper presents a multi-oracle selective sampling framework to leverage noisy labels from information sources with unknown reliability such as existing buildings, which we refer to as weak oracles, for metadata mapping. This framework involves an interactive process, where a small set of sensor instances are progressively selected and labeled for it to learn how to aggregate the noisy labels as well as to predict sensor types. Two key challenges arise in designing the framework, namely, weak oracle reliability estimation and instance selection for querying. To address the first challenge, we develop a clustering-based approach for weak oracle reliability estimation to capitalize on the observation that weak oracles perform differently in different groups of instances. For the second challenge, we propose a disagreement-based query selection strategy to combine the potential effect of a labeled instance on both reducing classifier uncertainty and improving the quality of label aggregation. We evaluate our solution on a large collection of real-world building sensor data from 5 buildings with more than 11,000 sensors of 18 different types. The experiment results validate the effectiveness of our solution, which outperforms a set of state-of-the-art baselines.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2021

Halfway to Zero: Progress towards a Carbon-Free Power Sector

Sharply reducing carbon emissions is imperative to prevent the worst effects of climate change. Yet even in the power sector—often viewed as the lynchpin to economy-wide decarbonization, and where low-carbon solutions are increasingly plentiful and cost-effective—the pace and scale of the required transformation can be daunting. A review of historical trends, however, shows the progress the power sector has already made in reducing emissions. Fifteen years ago, many business-as-usual projections anticipated that annual carbon dioxide (CO 2 ) emissions from power supply in the United States would reach 3,000 million metric tons (MMT) in 2020. In fact, direct power-sector CO 2 emissions in 2020 were 1,450 MMT—roughly 50% below the earlier projections. By this metric, in only 15 years the country’s power sector has gone halfway to zero emissions. Other metrics also evolved differently than projected: total consumer electricity costs (i.e., bills) were 18% lower; costs to human health and the climate were 92% and 52% lower, respectively; and the number of jobs in electricity generation was 29% higher. Economic, technical, and policy factors contributed to this success, including sectoral changes, energy efficiency, wind and solar, continued operations of the nuclear fleet, and coal-to-gas fuel switching. This historical record demonstrates the ability of technological and policy changes to set the power sector on a dramatically different emissions trajectory. Past success, however, does not trivialize the challenges that remain for further decarbonization in the power sector and beyond. Nor does it offer a specific roadmap for how best to achieve additional power-sector emissions reductions. Numerous challenges confront a zero-emissions pathway, and future strategies will likely differ from those of the past. Many recent studies have assessed how to make further progress in decarbonizing the power sector on the pathway to decarbonizing the economy as a whole. We summarize the core results of those studies, but the primary goal of this report is to highlight the progress that has already been made in reducing power-sector emissions. As the country maps out a plan for further decarbonization, experience from the past 15 years offers two central lessons. First, policy and technology advancement are imperative to achieving significant emissions reductions. Second, our ability to predict the future is limited, and so it will be crucial to adapt as we gain policy experience and as technologies advance in unexpected ways.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Uncertainty-Driven Rapid Thermodynamic Assessment of Nb-Ta-Zr System and Effects of C impurities (L25GF9298S): Annual Progress Report

An integrated computational materials engineering (ICME) method is in development for rapid thermodynamic experimental investigation and high-fidelity computational modeling of refractory multi-principal element alloys (RMPEAs). These ultra-high-temperature (UHT) alloys are of interest for structural applications in extreme environments, but deficiency of reliable data, especially melting temperatures, impedes the prediction of alloys with favorable properties. The method leverages UHT capabilities and computational expertise of LLNL’s Materials Science Division and the McCormack Lab’s UHT conical nozzle levitation (CNL) system to iteratively map the Nb-Ta-Zr phase space, with focus on the liquidus surface, through targeted experiments selected by quantifying uncertainty in the thermodynamic model fitting parameters. This method will reduce the time to map uncharted RMPEA phase space and thereby accelerate discovery and development of advanced materials for applications in extreme environments.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Transfer learning of neural surrogates on multifidelity groundwater simulations

Multifidelity data used in the paper published in Advances in Water Resources 206 (2025) 105140, https://doi.org/10.1016/j.advwatres.2025.105140 The code used to process the data is openly available on GitHub at https://github.com/Model-Reduction-and-UQ-Group/Transfer_Learning_K_reconstruction Computationally inexpensive surrogates of process-based models, such as deep neural networks, enable ensemble-based computations used in risk assessment, data assimilation, etc. However, generation of large datasets required to train a neural network can be as expensive as the ensemble simulations themselves. We ameliorate this challenge by using data from multifidelity (MF) groundwater simulations and transfer learning (TL) to reduce data generation costs while maintaining model accuracy. As a computational example, we train a deep convolutional neural network (CNN) to reconstruct permeability fields from saturation maps derived from a multiphase flow model. Starting with very low- and low-fidelity data generated on increasingly coarse meshes, we pretrain the CNN, followed by output-layer training and fine-tuning using only a limited number of high-fidelity samples. We demonstrate the surrogate’s robustness when interpreting low-quality inputs—such as interpolated maps or data affected by noise—which has strong implications for the applicability in practical hydrogeological scenarios. This multilevel MF-TL strategy achieves a favorable trade-off between computational efficiency and predictive accuracy, significantly outperforming high-fidelity-only approaches under the same computational budget.

Chiofalo, Alessia [University of Bologna] (ORCID:0↗

DOE OSTI2023

Accurate prediction of global-density-dependent range-separation parameters based on machine learning

In this work, we develop an accurate and efficient XGBoost machine learning model for predicting the global-density-dependent range-separation parameter, ωGDD, for long-range corrected functional (LRC)-ωPBE. This ωGDDML model has been built using a wide range of systems (11 466 complexes, ten different elements, and up to 139 heavy atoms) with fingerprints for the local atomic environment and histograms of distances for the long-range atomic correlation for mapping the quantum mechanical range-separation values. The promising performance on the testing set with 7046 complexes shows a mean absolute error of 0.001 117 a0−1 and only five systems (0.07%) with an absolute error larger than 0.01 a0−1, which indicates the good transferability of our ωGDDML model. In addition, the only required input to obtain ωGDDML is the Cartesian coordinates without electronic structure calculations, thereby enabling rapid predictions. LRC-ωPBE(ωGDDML) is used to predict polarizabilities for a series of oligomers, where polarizabilities are sensitive to the asymptotic density decay and are crucial in a variety of applications, including the calculations of dispersion corrections and refractive index, and surpasses the performance of all other popular density functionals except for the non-tuned LRC-ωPBE. Finally, LRC-ωPBE (ωGDDML) combined with (extended) symmetry-adapted perturbation theory is used in calculating noncovalent interactions to further show that the traditional ab initio system-specific tuning procedure can be bypassed. The present study not only provides an accurate and efficient way to determine the range-separation parameter for LRC-ωPBE but also shows the synergistic benefits of fusing the power of physically inspired density functional LRC-ωPBE and the data-driven ωGDDML model.

Chemistry↗