Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep potential”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Unsaturated alluvium disposal modelling with improved geological realism

This report describes specific activities in the Fiscal Year (FY) 2023 associated with the Geologic Disposal Safety Assessment (GDSA) Repository Systems Analysis (RSA) work package funded by the Spent Fuel and Waste Science and Technology (SFWST) Campaign of the U.S. Department of Energy Office of Nuclear Energy (DOE-NE), Office of Spent Fuel and Waste Disposition (SFWD). The overall objective of the GDSA RSA work package is to develop generic deep geologic repository concepts and system performance assessment (PA) models in several potential host-rock environments, and to simulate and analyze these generic repository concepts and models using the GDSA Framework toolkit and other tools as needed. The specific GDSA goal addressed in this report is reference case development, simulation, and analysis for the unsaturated alluvium (UZ), one of the four potential host-rocks considered by the GDSA. Further, we aim to exercise the simulation tools and methodologies under development by GDSA for PA modelling.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

Defining Infrastructure Feasibility for Hub-Scale Offshore Atlantic Carbon Storage in the Northeastern United States

In the Northeast U.S., deep rock formations along the Atlantic outer continental shelf may have the potential to sequester 150–1136 million metric tons of CO2. However, the design and infrastructure necessary to develop offshore carbon storage in this region is not well defined because there has been little oil and gas exploration and no commercial production. Consequently, an infrastructure feasibility design was completed for a hub-scale offshore CO2 storage system along the Northeast U.S. Atlantic. The design included development of a detailed, site-specific geological model for a location near the Great Stone Dome geological structure in the Baltimore Canyon Trough off the coast of Delaware, Maryland, and New Jersey. A field injection system topology design was completed to portray a design with eight wells in two clusters connected by central manifolds. Reservoir simulations were completed for the injection system that showed the hub may be able to inject 17 million metric tons (MMT) of CO2 per year for thirty years, but injection rates varied substantially across the eight wells. A CO2 pipeline design determined feasible routes from the east coast shoreline to the injection field. Finally, the CO2 injection system design included subsea injection trees, manifolds, and power umbilicals. This is the first study to define large-scale carbon storage design and infrastructure options for the offshore Atlantic, which can help to progress this region towards field characterization and early-mover deployment for future decarbonization in the region.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Probing the Wind Component of Radio Emission in Luminous High-redshift Quasars

We discuss a probe of the contribution of wind-related shocks to the radio emission in otherwise radio-quiet quasars. Given (1) the nonlinear correlation between UV and X-ray luminosity in quasars, (2) that such a correlation leads to higher likelihood of radiation-line-driven winds in more luminous quasars, and (3) that luminous quasars are more abundant at high redshift, deep radio observations of high-redshift quasars are needed to probe potential contributions from accretion disk winds. We target a sample of 50 z ≃ 1.65 color-selected quasars that span the range of expected accretion disk wind properties as traced by broad C iv emission. 3 GHz observations with the Very Large Array to an rms of ≈10 μJy beam -1 probe to star formation rates of ~400 M ⊙ yr -1 , leading to 22 detections. Supplementing these pointed observations are survey data of 388 sources from the LOFAR Two-meter Sky Survey Data Release 1 that reach comparable depth (for a typical radio spectral index), where 123 sources are detected. These combined observations reveal a radio detection fraction that is a nonlinear function of C iv emission-line properties and suggest that the data may require multiple origins of radio emission in radio-quiet quasars. We find evidence for radio emission from weak jets or coronae in radio-quiet quasars with low Eddington ratios, with either (or both) star formation and accretion disk winds playing an important role in optically luminous quasars and correlated with increasing Eddington ratio. Additional pointed radio observations are needed to fully establish the nature of radio emission in radio-quiet quasars.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

On fast simulation of dynamical system with neural vector enhanced numerical solver

The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of step sizes when estimating integration, resulting in a trade-off between accuracy and computational efficiency. To address this challenge, we introduce a deep learning-based corrector called Neural Vector (NeurVec), which can compensate for integration errors and enable larger time step sizes in simulations. Our extensive experiments on a variety of complex dynamical system benchmarks demonstrate that NeurVec exhibits remarkable generalization capability on a continuous phase space, even when trained using limited and discrete data. NeurVec significantly accelerates traditional solvers, achieving speeds tens to hundreds of times faster while maintaining high levels of accuracy and stability. Moreover, NeurVec’s simple-yet-effective design, combined with its ease of implementation, has the potential to establish a new paradigm for fast-solving differential equations based on deep learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Recent Advances in the Use of Ionic Liquids and Deep Eutectic Solvents for Lignocellulosic Biorefineries and Biobased Chemical and Material Production

Biorefineries, which process biomass feedstocks into valuable (bio)products, aim to replace fossil fuel-based refineries to produce energy and chemicals, reducing environmental and health hazards, including climate change, and supporting a sustainable economy. In particular, lignocellulose-based biorefineries, utilizing the most abundant renewable feedstock on Earth, have significant potential to supply sustainable energy, chemicals and materials. Ionic liquids (ILs, organic salts with low melting temperatures) and deep eutectic solvents (DESs, mixtures with eutectic points lower than the ideal mixture) are capable of dissolving some of the key lignocellulose polymers, and even the whole biomass. Furthermore, they have intrinsic advantages over molecular solvents, including safer usage profiles and high tunability, which allow tailored physicochemical properties. Such properties provide unique opportunities for the development of new processes that could unlock the full potential of future biorefineries. Here, we review the current state of lignocellulosic biomass processing with ILs and DESs, with a specific focus on the pretreatment chemistry, process flow and products from each component; followed by discussions on sustainability assessments and technological challenges. We aim to inform the research community about the opportunities, challenges and perspectives in developing truly sustainable lignocellulose-based biorefineries.

09 BIOMASS FUELS↗
DOE OSTI2020

Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short–Term Memory Models for Soil Moisture Predictions

Recently, recurrent deep networks have shown promise to harness newly available satellite–sensed data for long–term soil moisture projections. However, to be useful in forecasting, deep networks must also provide uncertainty estimates. Here we evaluated Monte Carlo dropout with an input–dependent data noise term (MCD+N), an efficient uncertainty estimation framework originally developed in computer vision, for hydrologic time series predictions. MCD+N simultaneously estimates a heteroscedastic input–dependent data noise term (a trained error model attributable to observational noise) and a network weight uncertainty term (attributable to insufficiently constrained model parameters). Although MCD+N has appealing features, many heuristic approximations were employed during its derivation, and rigorous evaluations and evidence of its asserted capability to detect dissimilarity were lacking. To address this, we provided an in–depth evaluation of the scheme's potential and limitations. We showed that for reproducing soil moisture dynamics recorded by the Soil Moisture Active Passive (SMAP) mission, MCD+N indeed gave a good estimate of predictive error, provided that we tuned a hyperparameter and used a representative training data set. The input–dependent term responded strongly to observational noise, while the model term clearly acted as a detector for physiographic dissimilarity from the training data, behaving as intended. However, when the training and test data were characteristically different, the input–dependent term could be misled, undermining its reliability. Additionally, due to the data–driven nature of the model, data noise also influences network weight uncertainty, and therefore the two uncertainty terms are correlated. Altogether, this approach has promise, but care is needed to interpret the results.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Accelerating Resonance Searches via Signature-Oriented Pre-training

The search for heavy resonances beyond the Standard Model (BSM) is a key objective at the LHC. While the recent use of advanced deep neural networks for boosted-jet tagging significantly enhances the sensitivity of dedicated searches, it is limited to specific final states, leaving vast potential BSM phase space underexplored. We introduce a novel experimental method, Signature-Oriented Pre-training for Heavy-resonance ObservatioN (Sophon), which leverages deep learning to cover an extensive number of boosted final states. Pre-trained on the comprehensive JetClass-II dataset, the Sophon model learns intricate jet signatures, ensuring the optimal constructions of various jet tagging discriminates and enabling high-performance transfer learning capabilities. We show that the method can not only push widespread model-specific searches to their sensitivity frontier, but also greatly improve model-agnostic approaches, accelerating LHC resonance searches in a broad sense.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

DeepPhenoMem V1.0: deep learning modelling of canopy greenness dynamics accounting for multi-variate meteorological memory effects on vegetation phenology

Abstract. Vegetation phenology plays a key role in controlling the seasonality of ecosystem processes that modulate carbon, water and energy fluxes between the biosphere and atmosphere. Accurate modelling of vegetation phenology in the interplay of Earth's surface and the atmosphere is thus crucial to understand how the coupled system will respond to and shape climatic changes. Phenology is controlled by meteorological conditions at different timescales: on the one hand, changes in key meteorological variables (temperature, water, radiation) can have immediate effects on the vegetation development; on the other hand, phenological changes can be driven by past environmental conditions, known as memory effects. However, the processes governing meteorological memory effects on phenology are not completely understood, resulting in their limited performance of vegetation phenology represented in land surface models. A deep learning model, specifically a long short-term memory network (LSTM), has the potential to capture and model the meteorological memory effects on vegetation phenology. Here, we apply the LSTM to model the vegetation phenology using meteorological drivers and high-temporal-resolution canopy greenness observations through digital repeat photography by the PhenoCam network. We compare a multiple linear regression model, a no-memory-effect LSTM model and a full-memory-effect LSTM model to predict the whole seasonal greenness trajectory and the corresponding phenological transition dates across 50 sites and 317 site years during 2009–2018, covering deciduous broadleaf forests, evergreen needleleaf forests and grasslands. Results show that the deep learning model outperforms the multiple linear regression model, and the full-memory-effect LSTM model performs better than the no-memory-effect model for all three plant function types (median R2 of 0.878, 0.957 and 0.955 for broadleaf forests, evergreen needleleaf forests and grasslands). We also find that the full-memory-effect LSTM model is capable of predicting the seasonal dynamic variations of canopy greenness and reproducing trends in shifting phenological transition dates. We also performed a sensitivity analysis of the full-memory-effect LSTM model to assess its plausibility, revealing its coherence with established knowledge of vegetation phenology sensitivity to meteorological conditions, particularly changes in temperature. Our study highlights that (1) multi-variate meteorological memory effects play a crucial role in vegetation phenology, and (2) deep learning opens up new avenues for improving the representation of vegetation phenological processes in land surface models via a hybrid modelling approach.

Geology↗
DOE OSTI2024

Can Glacial Sea‐Level Drop‐Induced Gas Hydrate Dissociation Cause Submarine Landslides?

Abstract We conducted two‐dimensional numerical simulations to investigate the mechanisms underlying the strong spatiotemporal correlation observed between submarine landslides and gas hydrate dissociation due to glacial sea‐level drops. Our results suggest that potential plastic deformation or slip could occur at localized and small scales in the shallow‐water portion of the gas hydrate stability zone (GHSZ). This shallow‐water portion of the GHSZ typically lies within the area enclosed by three points: the BGHSZ–seafloor intersection, the seafloor at ∼600 m below sea level (mbsl), and the base of the GHSZ (BGHSZ) at ∼1,050 mbsl in low‐latitude regions. The deep BGHSZ (>1,050 mbsl) could not slip; therefore, the entire BGHSZ was not a complete slip surface. Glacial hydrate dissociation alone is unlikely to cause large‐scale submarine landslides. Observed deep‐water (much greater than 600 mbsl) turbidites containing geochemical evidence of glacial hydrate dissociation potentially formed from erosion or detachment in the GHSZ pinch‐out zone.

58 GEOSCIENCES↗
DOE OSTI2021

Enabling deeper learning on big data for materials informatics applications

Abstract The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Deep learning-enhanced design for functionally graded auxetic lattices

Auxetic materials with counterintuitive negative Poisson’s ratio have been of significant interest due to potential applications across diverse engineering fields. Functionally grading such auxetics further enables customization of the structural response and harnesses the potential for multi-functional applications. However, a critical challenge in designing functionally graded lattices is to efficiently determine the spatial variation of the functional gradient and the corresponding geometric designs to achieve the desired response. In this paper, a highly efficient deep learning-based inverse design framework for functionally graded tetra-petal auxetics with spatially tailored properties is presented. This framework significantly improves the efficiency of tailoring functionally graded auxetics where many unit cells need to be tailor-designed. The graded tetra-petal auxetics obtained from the inverse design framework are additively manufactured and subjected to impact tests. The results show superior impact performance compared with uniform designs, demonstrating the effectiveness of the proposed inverse design framework, which can be inspirable to promote advanced structures/materials with enhanced impact resistance.

42 ENGINEERING↗
DOE OSTI2024

Unifying Quantum Materials Modeling and Experiments: The Role of Machine Learning Interatomic Potentials

Computational experiments have emerged as a powerful complement to traditional experiments in the design of new materials. The development of machine learning (ML) and deep learning techniques, combined with database construction and data mining, has significantly enhanced traditional quantum mechanical methods. This synergy enables the rapid development of structure-property relationships. In this talk, I will discuss our recent efforts in applying Machine Learning Interatomic Potentials (MLIAPs) to accelerate materials modeling across various material classes and challenging applications where traditional methods fall short. First, I will highlight the success of MLIAPs in accurately modeling the melting behavior of complex materials. Our results demonstrate high fidelity with experimental observations and also with calculated reference melting temperatures. In the second application, I will discuss how MLIAPs are trained and applied to elucidate the interplay between segregation tendencies and surface reconstructions in CuNi alloys under oxidizing conditions. A key factor in the success of these MLIAP applications is the design of minimalistic yet flexible datasets along with a computational framework for training MLIAPs.

Saidi, Wissam↗
DOE OSTI2023

Domain Adaptation for Measurements of Strong Gravitational Lenses

Upcoming surveys are predicted to discover galaxy-scale strong lenses on the magnitude of 105, making deep learning methods necessary in lensing data analysis. Currently, there is insufficient real lensing data to train deep learning algorithms, but training only on simulated data results in poor performance on real data. Domain adaptation can bridge the gap between simulated and real datasets. We adopt domain adaptation on the estimation of Einstein radius in simulated galaxy-scale gravitational lensing images. We evaluate two domain adaptation techniques - domain adversarial neural networks (DANN) and maximum mean discrepancy (MMD). We train on a source domain of simulated lenses and apply it to a target domain with emulation of DES survey conditions. We show that both domain adaptation techniques can significantly improve the model performance on the more complex target domain datasets. Our results show the potential of using domain adaptation to perform analysis on future survey data with a deep neural network trained on simulated data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Deep Learning Based Approach to Integrate MyShake's Trigger Data with ShakeAlert for Faster and Robust EEW Alerts

Earthquake Early Warning (EEW) systems depend on the dense seismic network to make fast and accurate earthquake detections to issue useful early alerts. The recent development and implementation of the ShakeAlert system is relying on the west coast seismic network to detect and estimate the earthquake parameters in real-time. While working on making improvements on the current system, one potential approach is to include more seismic recordings from various sources, such as the low-cost smartphone seismic network, such as the MyShake network, or the Google Android smartphones, since these smartphone seismic networks have much more portable stations (phones) to potentially provide useful data to the system. This report summarizes the initial exploration of using a deep learning approach to combine the data from both traditional seismic stations and the smartphone data in California. Due to the heterogeneity nature of the data, we aggregate data from the phones (using simulation data), as well as that from traditional seismic stations to grid cells. By generating real-time triggering ratio grid cell maps, the designed deep learning algorithm can process the data from multiple sources and detect the earthquake faster than only using that from a traditional seismic network.

58 GEOSCIENCES↗
DOE OSTI2022

High Temperature, High Pressure Stability of Aqueous Foams for Potential Application in Enhanced Geothermal System (EGS)

Enhanced Geothermal Systems (EGS) are typically constructed by injecting high-pressure water into deep hot dry rocks (HDR) under carefully controlled conditions to create new or re-open existing fractures, which usually uses an immense quantity of water. In lieu, a more sustainable technique is to utilize aqueous foams as fracturing fluid to reduce water consumption and waste-water treatments of conventional hydraulic fracturing. Although foam-based fracturing has shown promising results in oil and gas industries, its feasibility is not demonstrated in EGS conditions that usually involve high temperature and high pressures. One potential barrier of utilizing foams in EGS applications is that foams are thermodynamically unstable and will become more unstable with increasing temperature due to liquid drainage, bubble coarsening, and coalescence. This work focuses on evaluation of the stability of selected aqueous foams under high-temperature and high-pressure conditions. Specifically, foams generated with surfactant alfa olefin sulfonate (AOS) were studied at temperature up to 200oC, while the pressure ranged between 100 psi and 1000 psi. The effect of additional stabilizing agents was also examined, including guar gum, bentonite clay, borate salt crosslinker, silicon dioxide nanoparticles (SiO2), and graphene oxide (GO) dispersion. Results showed that the stabilizing agents can enhance the foam thermal stability. Foams made with AOS and the borate salt crosslinker exhibited the longest half-life of 20 min at 200°C when the pressure was at 1000 psi. Data fitting showed that foam stability decreased exponentially as temperature increased. On the other hand, pressure increased the foam half-life which followed a power model. This study indicates that it may be possible to obtain highly stable foams at high-temperature and high-pressure conditions with appropriate stabilizing agents.

Thakore, Viren↗
DOE OSTI2020

Sequim Bay Underwater UXO (SBU2) Prototype Demonstration Site: Field Operations Summary, 2019

The U.S. Department of Defense (DoD) has identified more than 400 underwater sites that are potentially contaminated with munitions. Many of these sites are in shallow water (0–35 m deep) where the munitions pose a threat to human health and the environmental. To address this challenge, the Strategic Environmental Research and Development Program (SERDP) and Environmental Security Technology Certification Program (ESTCP) held a workshop in 2018 to establish the requirements and framework for developing a series of underwater unexploded ordnance (UXO) Standardized Demonstration sites (“test beds”) to support the evaluation of sensors, equipment, and technologies to detect UXO. Sequim Bay in Washington State was evaluated as a potential test bed and was determined to meet initial qualifying criteria with respect to environmental setting, and operational, logistical, and facilities support provided by the Pacific Northwest National Laboratory (PNNL).

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2022

Time-lapse seismic data inversion for estimating reservoir parameters using deep learning

Geologic carbon sequestration involves the injection of captured carbon dioxide ([Formula: see text]) into subsurface formations for long-term storage. The movement and fate of the injected [Formula: see text] plume is of great concern to regulators because monitoring helps to identify potential leakage zones and determines the possibility of safe long-term storage. To address this concern, we design a deep-learning framework for [Formula: see text] saturation monitoring to determine the geologic controls on the storage of the injected [Formula: see text]. We use different combinations of porosities and permeabilities for a given reservoir to generate saturation and velocity models. We train the deep-learning model with a few time-lapse seismic images and their corresponding changes in saturation values for a particular [Formula: see text] injection site. The deep-learning model learns the mapping from the change in the time-lapse seismic response to the change in [Formula: see text] saturation during the training phase. We then apply the trained model to data sets comprising different time-lapse seismic image slices (corresponding to different time instances) generated using different porosity and permeability distributions that are not part of the training to estimate the [Formula: see text] saturation values along with the plume extent. Our algorithm provides a deep-learning assisted framework for the direct estimation of [Formula: see text] saturation values and plume migration in heterogeneous formations using the time-lapse seismic data. Our method improves the efficiency of time-lapse inversion by streamlining the large number of intermediate steps in the conventional time-lapse inversion workflow. This method also helps to incorporate the geologic uncertainty for a given reservoir by accounting for the statistical distribution of porosity and permeability during the training phase. Tests on different examples verify the effectiveness of our approach.

Geochemistry & Geophysics↗