Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep energy method”

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.

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

At least 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Role of Intermolecular Interactions in Deep Eutectic Solvents for CO 2 Capture: Vibrational Spectroscopy and Quantum Chemical Studies

Recent research and reviews on CO 2 capture methods, along with advancements in industry, have highlighted high costs and energy-intensive nature as the primary limitations of conventional direct air capture and storage (DACS) methods. In response to these challenges, deep eutectic solvents (DESs) have emerged as promising absorbents due to their scalability, selectivity, and lower environmental impact compared to other absorbents. However, the molecular origins of their enhanced thermal stability and selectivity for DAC applications have not been explored before. Therefore, the current study focuses on a comprehensive investigation into the molecular interactions within an alkaline DES composed of potassium hydroxide (KOH) and ethylene glycol (EG). Combining Fourier transform infrared (FT-IR) and quantum chemical calculations, the study reports structural changes and intermolecular interactions induced in EG upon addition of KOH and its implications on CO 2 capture. Experimental and computational spectroscopic studies confirm the presence of noncovalent interactions (hydrogen bonds) within both EG and the KOH-EG system and point to the aggregation of ions at higher KOH concentrations. Additionally, molecular electrostatic potential (MESP) surface analysis, natural bond orbital (NBO) analysis, quantum theory of atoms-in-molecules (QTAIM) analysis, and reduced density gradient-noncovalent interaction (RDG-NCI) plot analysis elucidate changes in polarizability, charge distribution, hydrogen bond types, noncovalent interactions, and interaction strengths, respectively. Evaluation of explicit and hybrid models assesses their effectiveness in representing intermolecular interactions. This research enhances our understanding of molecular interactions in the KOH-EG system, which are essential for both the absorption and desorption of CO 2 . The study also aids in predicting and selecting DES components, optimizing their ratios with salts, and fine-tuning the properties of similar solvents and salts for enhanced CO 2 capture efficiency.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta $p$ T > $500$ GeV.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Quantum Solver of Contracted Eigenvalue Equations for Scalable Molecular Simulations on Quantum Computing Devices

The accurate computation of ground and excited states of many-fermion quantum systems is one of the most consequential, contemporary challenges in the physical and computational sciences whose solution stands to benefit significantly from the advent of quantum computing devices. Existing methodologies using phase estimation or variational algorithms have potential drawbacks such as deep circuits requiring substantial error correction or non-trivial high-dimensional classical optimization. In this work, we introduce a quantum solver of contracted eigenvalue equations, the quantum analogue of classical methods for the energies and reduced density matrices of ground and excited states. The solver does not require deep circuits or difficult classical optimization and achieves an exponential speed-up over its classical counterpart. We demonstrate the algorithm though computations on both a quantum simulator and two IBM quantum processing units.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Integrating Applied Energy and BER Smart Data Capabilities to Develop a DOE Data Fabric for Energy-Water R&D

Focal Area(s): 1) Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization, unsupervised learning (including deep learning), and hardware-related efforts involving AI (e.g., edge computing). Science Challenge: DOE R&D, including DOE’s Basic Energy Research (BER)’s Environmental Systems Science Division (EESSD) program and DOE’s applied energy research (AER) programs (EERE, FE, and NE) are producers and consumers of Earth systems datasets. This white paper focuses on the first topic area from the call in relation to how crosscutting resources and innovations from DOE’s EESSD and AER can be brought to bear to mutual benefit and more efficient energy-water, Earth system data resources through improved. The overarching challenge posed by this call focuses on how DOE can directly leverage artificial intelligence (AI) to engineer a substantial (paradigm-changing) improvement in Earth System Predictability? While stemming from DOE BER’s EESSD program, this is a challenge that is faced and also being addressed by DOE’s AER programs. Over the past decade plus, FE, EERE, and NE programs have made important strides towards addressing this need. These strides are in many ways highly complementary to EESSD’s MODEX efforts. Energy water systems spanning metocean to groundwater to surface water systems all are data driven whether for basic energy or applied energy. These are remote, multi-variate, complex natural, and in many cases engineered, systems. Key needs and challenges of both EESSD and AER include developing data-focused tools to enhance data search and discovery to fill in knowledge gaps (address sparse data challenge), and rapidly transform datasets, including disparate and multi-source data. Leveraging DOE on-premise computing (HPC, exascale) infrastructure supports the computing-intensive algorithms required to execute these data acquisition and transformation processes to derive enriched knowledge and data, driving AI/ML and big data analytics for these systems. The opportunity lies in combining BER and AER efforts to provide a more robust, advanced, efficient and complete computing data fabric to address energy-water data acquisition and assimilation needs which currently pose significant impediments to AI/ML predictions and research.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2003

The Burst and Transient Source Experiment(BATSE)Earth Occultation Catalog of Low-Energy Gamma-Ray Sources. Short title: BATSE Earth Occultation Catalog v2.0

The Burst and Transient Source Experiment (BATSE), aboard the Compton Gamma Ray Observatory (CGRO), provided a record of the low-energy gamma-ray sky (approx. 20-1000 keV) between 1991 April and 2000 May (9.1y). BATSE monitored the high energy sky using the Earth occultation technique (EOT) for point sources whose emission extended for times on the order of the CGRO orbital period (approx. 92m) or greater. Using the EOT to extract flux - 2 - information, a catalog of sources using data from the BATSE large area detectors has been prepared. The first part of the catalog consists of results from the all-sky monitoring of 58 sources, mostly Galactic, with intrinsic variability on timescales of hours to years. For these sources, we have included tables of flux and spectral data, and outburst times for transients. Light curves (or flux histories) covering the entire nine mission are being placed on the world wide web. We then performed a deep-sampling of these 58 objects, plus a selection of 121 more objects, combining data from the entire 9.ly BATSE dataset. Source types considered were primarily accreting binaries, but a small number of representative active galaxies, X-ray-emitting stars, and supernova remnants were also included. The sample represents a compilation of sources monitored and/or discovered with BATSE and other high energy instruments between 1991 and 2000, known sources taken from the HEAO 1 A-4 (Levine et al. 1984) and Macomb and Gehrels (1999) catalogs. The deep sample results include definite detections of 82 objects and possible detections of 36 additional objects. The definite detections spanned three classes of sources: accreting black hole and neutron star binaries, active galaxies and supernova remnants. The average fluxes measured for the fourth class, the X-ray emitting stars, were below the confidence limit for definite detection. Flux data for the deep sample are presented in four energy bands: 20-40, 40-70, 70-160, and 160-430 keV. The limiting average flux level (9.1 y) for the sample varies from 3.5 to 20 mCrab (5delta) between 20 and 430 keV, depending on systematic error, which in turn is primarily dependent on the sky location. To strengthen the credibility of detection of weaker sources (approx.5-25 mCrab), we generated Earth occultation images, searched for periodic behavior using FFT and epoch folding methods, and critically evaluated the energy-dependent emission in the four flux bands. The deep sample results are intended for guidance in performing future all-sky surveys or pointed observations in the hard X-ray and low-energy gamma-ray band, as well as more detailed studies with the BATSE EOT.

Harmon, B. A.↗
DOE OSTI2022

Posterior Regularized Bayesian Neural Network incorporating soft and hard knowledge constraints

Neural Networks (NNs) have been widely used in supervised learning due to their ability to model complex nonlinear patterns, often presented in high-dimensional data such as images and text. However, traditional NNs often lack the ability for uncertainty quantification. Bayesian NNs (BNNS) could help measure the uncertainty by considering the distributions of the NN model parameters. Besides, domain knowledge is commonly available and could improve the performance of BNNs if it can be appropriately incorporated. In this work, we propose a novel Posterior-Regularized Bayesian Neural Network (PR-BNN) model by incorporating different types of knowledge constraints, such as the soft and hard constraints, as a posterior regularization term. Furthermore, we propose to combine the augmented Lagrangian method and the existing BNN solvers for efficient inference. Furthermore, the experiments in simulation and two case studies about aviation landing prediction and solar energy output prediction have shown the knowledge constraints and the performance improvement of the proposed model over traditional BNNs without the constraints.

14 SOLAR ENERGY↗
DOE OSTI2025

PAC in DESI. I. Galaxy stellar mass function into the 10 6 M ⊙ frontier

The Photometric objects Around Cosmic webs (PAC) method integrates cosmological photometric and spectroscopic surveys, offering valuable insights into galaxy formation. PAC measures the excess surface density of photometric objects, $\bar{n}_2w_{{\rm {p}}}$, with specific physical properties around spectroscopic tracers. In this study, we improve the PAC method to make it more rigorous and eliminate the need for redshift bins. We apply the enhanced PAC method to the DESI Y1 BGS Bright spectroscopic sample and the deep Dark Energy Camera Legacy Survey (DECaLS) photometric sample, obtaining $\bar{n}_2w_{{\mathrm {p}}}$ measurements across the complete stellar mass range, from $10^{5.3}$ to $10^{11.5}\,{\rm M}_{\odot }$ for blue galaxies, and from $10^{6.3}$ to $10^{11.9}\,{\rm M}_{\odot }$ for red galaxies. We combine $\bar{n}_2w_{{\rm {p}}}$ with $w_{{\rm {p}}}$ measurements from the BGS sample, which is not necessarily complete in stellar mass. Assuming that galaxy bias is primarily determined by stellar mass and colour, we derive the galaxy stellar mass functions (GSMFs) down to $10^{5.3}\,{\rm M}_{\odot }$ for blue galaxies and $10^{6.3}\,{\rm M}_{\odot }$ for red galaxies, while also setting lower limits for smaller masses. The blue and red GSMFs are well described by single and double Schechter functions, respectively, with low-mass end slopes of $\alpha _{\rm {blue}}=-1.54^{+0.02}_{-0.02}$ and $\alpha _{\rm {red}}=-2.50^{+0.08}_{-0.08}$, resulting in the dominance of red galaxies below $10^{7.6}\,{\rm M}_{\odot }$. Stage-IV cosmological photometric surveys, capable of reaching 2–3 mag deeper than DECaLS, present an opportunity to explore the entire galaxy population in the local universe with PAC. This advancement allows us to address critical questions regarding the nature of dark matter, the physics of reionization, and the formation of dwarf galaxies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Data-Driven Prediction and Optimization of Energy Use for Transit Fleets of Electric and ICE Vehicles

Due to the high upfront cost of electric vehicles, many public transit agencies can afford only mixed fleets of internal combustion and electric vehicles. Optimizing the operation of such mixed fleets is challenging because it requires accurate trip-level predictions of electricity and fuel use as well as efficient algorithms for assigning vehicles to transit routes. We present a novel framework for the data-driven prediction of trip-level energy use for mixed-vehicle transit fleets and for the optimization of vehicle assignments, which we evaluate using data collected from the bus fleet of CARTA, the public transit agency of Chattanooga, TN. We first introduce a data collection, storage, and processing framework for system-level and high-frequency vehicle-level transit data, including domain-specific data cleansing methods. We train and evaluate machine learning models for energy prediction, demonstrating that deep neural networks attain the highest accuracy. Based on these predictions, we formulate the problem of minimizing energy use through assigning vehicles to fixed-route transit trips. We propose an optimal integer program as well as efficient heuristic and meta-heuristic algorithms, demonstrating the scalability and performance of these algorithms numerically using the transit network of CARTA.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Towards deep computer vision for in-line defect detection in polymer electrolyte membrane fuel cell materials

Polymer Electrolyte Membrane (PEM) fuel cells are a promising source of alternative energy. However, their production is limited by a lack of well-established methods for quality control of their constituent materials like the membrane-electrode assembly during roll-to-roll manufacturing. One potential solution is the implementation of deep learning methods to detect unwanted defects through their detection in scanned images. Here we explore the detection of defects like scratches, pinholes, and scuffs in a sample dataset of PEM optical images using two deep learning algorithms: Patch Distribution Modeling (PaDiM) for unsupervised anomaly detection and Faster-RCNN for supervised object detection. Both methods achieve scores on performance metrics (ROC-AUC and PRO-AUC for PaDiM and AP for Faster-RCNN) that are comparable to their scores on benchmark datasets. These methods also have the potential to detect a wider range of defects compared to IR thermography and previous optical inspection methods. Overall, deep learning shows promise at detecting relevant defects of interest and has the potential to achieve real-time defect detection.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

Operator learning for energy-efficient building ventilation control with computational fluid dynamics simulation of a real-world classroom

Energy-efficient ventilation control plays an important role in reducing building energy consumption while ensuring occupant health and comfort. While Computational Fluid Dynamics (CFD) simulations provide detailed and physically accurate representations of indoor airflow, their high computational cost limits their use in real-time building control. In this work, we present a neural operator learning framework that combines the physical accuracy of CFD with the computational efficiency of machine learning to enable building ventilation control with the high-fidelity fluid dynamics models. Our method jointly optimizes the airflow supply rates and vent angles to reduce energy use and adhere to air quality constraints. We train an ensemble of neural operator transformer models to learn the mapping from building control actions to airflow fields using high-resolution CFD data. This learned neural operator is then embedded in an optimization-based control framework for building ventilation control. Experimental results show that our approach achieves significant energy savings compared to maximum airflow rate control, rule-based control, as well as data-driven control methods using spatially averaged CO 2 prediction and deep learning–based reduced-order models, while consistently maintaining safe indoor air quality. These results highlight the practicality and scalability of our method in maintaining energy efficiency and indoor air quality in real-world buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2011

Imaging the Moon's Core with Seismology

Constraining the structure of the lunar core is necessary to improve our understanding of the present-day thermal structure of the interior and the history of a lunar dynamo, as well as the origin and thermal and compositional evolution of the Moon. We analyze Apollo deep moonquake seismograms using terrestrial array processing methods to search for the presence of reflected and converted energy from the lunar core. Although moonquake fault parameters are not constrained, we first explore a suite of theoretical focal spheres to verify that fault planes exist that can produce favorable core reflection amplitudes relative to direct up-going energy at the Apollo stations. Beginning with stacks of event seismograms from the known distribution of deep moonquake clusters, we apply a polarization filter to account for the effects of seismic scattering that (a) partitions energy away from expected components of ground motion, and (b) obscures all but the main P- and S-wave arrivals. The filtered traces are then shifted to the predicted arrival time of a core phase (e.g. PcP) and stacked to enhance subtle arrivals associated with the Moon s core. This combination of filtering and array processing is well suited for detecting deep lunar seismic reflections, since we do not expect scattered wave energy from near surface (or deeper) structure recorded at varying epicentral distances and stations from varying moonquakes at varying depths to stack coherently. Our results indicate the presence of a solid inner and fluid outer core, overlain by a partial-melt-containing boundary layer (Table 1). These layers are consistently observed among stacks from four classes of reflections: P-to-P, S-to-P, P-to-S, and S-to-S, and are consistent with current indirect geophysical estimates of core and deep mantle properties, including mass, moment of inertia, lunar laser ranging, and electromagnetic induction. Future refinements are expected following the successful launch of the GRAIL lunar orbiter and SELENE 2 lunar lander missions.

Weber, Renee C.↗
DOE OSTI2025

Performance evaluation of automated data-driven feature extraction and selection methods for practical and scalable building energy consumption prediction models

Here, this study quantifies the impact of automated feature engineering methods (feature extraction and selection) on the quality and accuracy of machine learning models that predict building energy consumption. The case study compares model performance for three main scenarios: baseline (no feature extraction and selection), feature extraction only, and feature extraction combined with feature selection (filter and/or wrapper methods) for fully trained machine learning models for 200 metered/sub-metered energy measurements across 118 real buildings. For consistency, the same machine learning model architecture (a black box deep learning neural network with probabilistic forecast output) was used for all scenarios. Based on results, all feature engineering methods provided noticeable prediction accuracy improvements (e.g., 29%-68% median prediction improvement) compared to baseline scenarios. However, in this application, feature selection methods provide little practical value due to their limited performance gains and high computational cost. Smarter algorithm development supported by better computational environments will be needed before feature selection methods can reliably and efficiently improve predictive model performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Development of interatomic potential for Al–Tb alloys using a deep neural network learning method

An interatomic potential for the Al–Tb alloy around the composition of Al 90 Tb 10 is developed using the deep neural network (DNN) learning method. The atomic configurations and the corresponding total potential energies and forces on each atom obtained from ab initio molecular dynamics (AIMD) simulations are collected to train a DNN model to construct the interatomic potential for the Al–Tb alloy. Here we show that the obtained DNN model can well reproduce the energies and forces calculated by AIMD simulations. Molecular dynamics (MD) simulations using the DNN interatomic potential also accurately describe the structural properties of the Al 90 Tb 10 liquid, such as partial pair correlation functions (PPCFs) and bond angle distributions, in comparison with the results from AIMD simulations. Furthermore, the developed DNN interatomic potential predicts the formation energies of the crystalline phases of the Al–Tb system with an accuracy comparable to ab initio calculations. The structure factors of the Al 90 Tb 10 metallic liquid and glass obtained by MD simulations using the developed DNN interatomic potential are also in good agreement with the experimental X-ray diffraction data. The development of short-range order (SRO) in the Al 90 Tb 10 liquid and the undercooled liquid is also analyzed and three dominant SROs, i.e., Al-centered distorted icosahedron (DISICO) and Tb-centered ‘3661’ and ‘15551’ clusters, respectively, are identified.

36 MATERIALS SCIENCE↗
NASA NTRS2016

Graphene Based Ultra-Capacitors for Safer, More Efficient Energy Storage

Current power storage methods must be continuously improved in order to keep up with the increasingly competitive electronics industry. This technological advancement is also essential for the continuation of deep space exploration. Today's energy storage industry relies heavily on the use of dangerous and corrosive chemicals such as lithium and phosphoric acid. These chemicals can prove hazardous to the user if the device is ruptured. Similarly they can damage the environment if they are disposed of improperly. A safer, more efficient alternative is needed across a wide range of NASA missions. One solution would a solid-state carbon based energy storage device. Carbon is a safer, less environmentally hazardous alternative to current energy storage materials. Using the amorphous carbon nanostructure, graphene, this idea of a safer portable energy is possible. Graphene was electrochemically produced in the lab and several coin cell devices were built this summer to create a working prototype of a solid-state graphene battery.

Composite battery↗
DOE OSTI2024

Deep Learning for Full Waveform Inversion of Elastic Active-Source Seismic Data to Estimate P-Wave Velocity Models

Seismic imaging methods are critical for Global Security and Energy & Homeland Security missions and activities that rely on subsurface characterization, but traditional methods remain computationally expensive and require significant labor hours and expertise to execute. Within the past few years, machine learning (ML), namely deep learning (DL), has been used to develop data-driven end-to-end full waveform inversion (FWI) methods to estimate 2D P-wave velocity (Vp) models in a fraction of the time as conventional FWI. These methods, however, are trained on simplistic acoustic wave seismic data and Vp models that are not realistic nor representative of real-world observations, leaving a large gap between the state-of-the-art and deployable, feasible, and practical DL FWI methods. Here, we generate a synthetic active-source, 3D, elastic wave seismic data set and a variety of Vp models with realistic geologic structure for training DL FWI methods. We evaluate six different methods that have performed well for acoustic DL FWI or medical imaging tasks using our more realistic dataset. We find that these six trained models do not match the performance of published acoustic end-to-end DL FWI methods, indicating more training data may be needed, physics may need to be incorporated to achieve good accuracy at the sacrifice of the end-to-end advantage, and/or novel methods need to be developed to enable end-to-end DL FWI methods to perform well for real-world seismic data.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2024

Transforming the bootstrap: using Transformers to compute scattering amplitudes in planar N = 4 Super Yang-Mills theory

Abstract We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to the theory that describes Higgs boson production at the Large Hadron Collider; its scattering amplitudes are large mathematical expressions containing integer coefficients. In this paper, we apply Transformers to predict these coefficients. The problem can be formulated in a language-like representation amenable to standard cross-entropy training objectives. We design two related experiments and show that the model achieves high accuracy (> 98%) on both tasks. Our work shows that Transformers can be applied successfully to problems in theoretical physics that require exact solutions.

Cai, Tianji (ORCID:0000000232359486)↗
DOE OSTI2024

Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory

We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to the theory that describes Higgs boson production at the Large Hadron Collider; its scattering amplitudes are large mathematical expressions containing integer coefficients. In this paper, we apply Transformers to predict these coefficients. The problem can be formulated in a language-like representation amenable to standard cross-entropy training objectives. We design two related experiments and show that the model achieves high accuracy (> 98%) on both tasks. Our work shows that Transformers can be applied successfully to problems in theoretical physics that require exact solutions.

Lance, Dixon↗