Search NASA⌕ Search

SEARCH · Search NASA

Results for “DL Reasoning”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Towards Cache-Enabled, Order-Aware, Ontology-Based Stream Reasoning Framework

While streaming data have become increasingly more popular in business and research communities, semantic models and processing software for streaming data have not kept pace. Traditional semantic solutions have not addressed transient data streams. Semantic web languages (e.g., RDF, OWL) have typically addressed static data settings and linked data approaches have predominantly addressed static or growing data repositories. Streaming data settings have some fundamental differences; in particular, data are consumed on the fly and data may expire. Stream reasoning, a combination of stream processing and semantic reasoning, has emerged with the vision of providing "smart" processing of streaming data. C-SPARQL is a prominent stream reasoning system that handles semantic (RDF) data streams. Many stream reasoning systems including C-SPARQL use a sliding window and use data arrival time to evict data. For data streams that include expiration times, a simple arrival time scheme is inadequate if the window size does not match the expiration period. In this paper, we propose a cache-enabled, order-aware, ontology-based stream reasoning framework. This framework consumes RDF streams with expiration timestamps assigned by the streaming source. Our framework utilizes both arrival and expiration timestamps in its cache eviction policies. In addition, we introduce the notion of "semantic importance" which aims to address the relevance of data to the expected reasoning, thus enabling the eviction algorithms to be more context- and reasoning-aware when choosing what data to maintain for question answering. We evaluate this framework by implementing three different prototypes and utilizing five metrics. The trade-offs of deploying the proposed framework are also discussed.

Data Discovery↗
NASA NTRSDate not supplied

A Temporal Differential Dynamic Logic Formal Embedding

Differential dynamic logic is a formal framework to specify and reason about hybrid programs (HPs). The core of dL is a proof calculus that contains a collection of axioms and rules for the rigorous verification of properties of HPs. Recently, dL has been embedded within the theorem prover Prototype Verification System (PVS) resulting in the tool Plaidypvs2. The integration of dL into PVS expands its expressive power; user defined functions, such as trigonometric and other transcendental functions, can be used inside the dL framework, and meta-reasoning about HPs can be performed, including reasoning about entire classes of HPs, specified using dependent types in PVS. The differential temporal dynamic logic (dTL2) extends dL with temporal logic operators to reason about all the states reachable during the execution of an HP. This paper presents a work in progress focusing on embedding dTL2 in PVS as an extension of Plaidypvs. Plaidypvs is expanded with the formalization of a trace semantics for HPs, the definition of the LTL temporal operators eventually and globally, and the implementation of the proof calculus for dTL2. This new embedding has the same capabilties as Plaidypvs, which allows user defined functions and meta-reasoning of properties of HPs. To the best of the authors’ knowledge this is the first implementation of dTL2.

differential dynamic logic↗
DOE OSTI2022

Deep learning to estimate permeability using geophysical data

Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.

58 GEOSCIENCES↗
NASA NTRS1973

The hydrolysis of polyimides

Thermal polymerization of aspartic acid produces a polysuccinimide (I), a chain of aspartoyl residues. An investigation was made of the alkaline hydrolysis of the imide rings of (I) which converts the polyimide to a polypeptide. The alkaline hydrolysis of polyimides can be expected to be kinetically complex due to increasing negative charge generated by carboxylate groups. For this reason, a diimide, phthaloyl-DL-aspartoyl-beta-alanine (IIA) was synthesized for a progressive study of the hydrolysis of polyimides. In addition, this diimide (IIA) can be related to thalidomide and might be expected to exhibit similar reactivity during hydrolysis of the phthalimide ring.

Hoagland, P. D.↗
DOE OSTI2024

Yet Another Discriminant Analysis (YADA): A Probabilistic Model for Machine Learning Applications

This paper presents a probabilistic model for various machine learning (ML) applications. While deep learning (DL) has produced state-of-the-art results in many domains, DL models are complex and over-parameterized, which leads to high uncertainty about what the model has learned, as well as its decision process. Further, DL models are not probabilistic, making reasoning about their output challenging. In contrast, the proposed model, referred to as Yet Another Discriminate Analysis(YADA), is less complex than other methods, is based on a mathematically rigorous foundation, and can be utilized for a wide variety of ML tasks including classification, explainability, and uncertainty quantification. YADA is thus competitive in most cases with many state-of-the-art DL models. Ideally, a probabilistic model would represent the full joint probability distribution of its features, but doing so is often computationally expensive and intractable. Hence, many probabilistic models assume that the features are either normally distributed, mutually independent, or both, which can severely limit their performance. YADA is an intermediate model that (1) captures the marginal distributions of each variable and the pairwise correlations between variables and (2) explicitly maps features to the space of multivariate Gaussian variables. Numerous mathematical properties of the YADA model can be derived, thereby improving the theoretic underpinnings of ML. Validation of the model can be statistically verified on new or held-out data using native properties of YADA. However, there are some engineering and practical challenges that we enumerate to make YADA more useful.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Embedding Differential Dynamic Logic in PVS

Differential dynamic logic (dL) is a formal framework for specifying and reasoning about hybrid systems, i.e., dynamical systems that exhibit both continuous and discrete behaviors. These kinds of systems arise in many safety- and mission-critical applications. This paper presents a formalization of dL in the Prototype Verification System (PVS) that includes the semantics of hybrid programs and dL’s proof calculus. The formalization embeds dL into the PVS logic, resulting in a version of dL whose proof calculus is not only formally verified, but is also available for the verification of hybrid programs within PVS itself. This embedding, called Plaidypvs (Properly Assured Implementation of dL for Hybrid Program Verification and Specification), supports standard dL style proofs, but further leverages the capabilities of PVS to allow reasoning about entire classes of hybrid programs. The embedding also allows the user to import the well-established definitions and mathematical theories available in PVS.

PVS↗
NASA NTRS2022

Towards an Implementation of Differential Dynamic Logic in PVS

This paper describes an ongoing effort to embed and verify differential dynamic logic (dL) in the Prototype Verification System (PVS). dL is a logic for specifying and formally reasoning about hybrid systems, which employ both continuous and discrete dynamics. There are several benefits of this effort. First, the embedding of dL in PVS offers an independent formal verification of the semantics and rules of dL. Second, the embedding is fully operational within PVS, giving PVS practitioners the ability to use dL in the formal specification and verification process. Third, the rich specification language, type system, and powerful interactive prover of PVS can be used on dL objects. In addition to the embedding and verification of dL, a custom extension for Visual Studio Code has been developed, so that a stylized dL syntax can be used to specify hybrid programs and their properties.

Differential Dynamic Logic↗
DOE OSTI2025

Advancing the Frontiers of Deep Learning for Low-Dose 3D Cone-Beam CT Reconstruction

X-ray computed tomography (CT) is an important noninvasive medical imaging modality for studying the structural details of internal organs. Image reconstruction in CT is an inverse problem of recovering an object's internal structure from the absorption profile of X-ray beams (sinogram) measured using a detector. The classical variational approach for CT reconstruction minimizes an energy functional using an appropriate iterative algorithm. Motivated by the success of deep learning (DL), researchers have begun to leverage training data and enhanced computing capabilities in recent years to produce high-fidelity reconstructed images. Nonetheless, much of the academic research in DL algorithms for CT has focused primarily on the two-dimensional setting (with simplified forward operators and noise model) for proofs-of-concept, and a comprehensive benchmarking of various classical and data-driven CT reconstruction approaches has not beenundertaken. The key objective of our CT reconstruction grand challenge was to promote methodological advancements for both classical and DL-based approaches for clinical CT with a reasonably accurately simulated 3D CT forward operator and noise model. We have utilized the publicly available LIDC-IDRI dataset and simulated sinograms and FDK images corresponding to two dose levels (clinical- and low-dose, constituting two tracks of the challenge) starting from the normal-dose images as the ground truth. In this paper, we summarize the motivation, context, and results of our challenge, and highlight the future research directions in DL for clinical CT.

X-ray tomography↗
DOE OSTI2021

Unleashing the Power of Industrial Big Data through Scalable Manual Labeling

Big Data plays a central role in the remarkable results achieved by Machine Learning (ML) and especially Deep Learning (DL) in the recent years. However, the difficulty in obtaining a reasonable amount of labeled samples limits ML/DL application in various domains, including industrial equipment and system monitoring. In this paper the need for methods that turn manual labeling into a scalable process is highlighted. A real world problem is analyzed for which weak supervision methods, successfully employed in other domains, did not produce acceptable results. An alternative approach based on clustering ensembles is described and tested, achieving good performance.

Paes Leao, Bruno↗
DOE OSTI2024

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Using multiple geophysical methods has become a prevailing approach in numerous geophysical applications to investigate subsurface structures and parameters. These multimethod-based exploration strategies have the potential to greatly diminish uncertainties and ambiguities encountered during geophysical data analysis and interpretation. One of the applications is the cooperative inversion of airborne magnetic and gravity gradient data for the interpretation of data obtained in mineral, oil and gas, and geothermal explorations. In this paper, a unified cooperative inversion framework is designed by combining the standard separate inversions with a deep neural network (DNN), which serves as the link between different types of data. A well-trained DNN takes the separately inverted susceptibility and density models as the inputs and provides improved models that will be used as the initial models of deterministic inversions. A two-round iteration strategy is adopted to guarantee the reasonability of the recovered models and overall efficiency of the inversion. In addition, this deep-learning (DL)-based framework demonstrates excellent generalization abilities when tested on models that are entirely distinct from the training data sets. The framework can easily incorporate multiphysics without necessitating any structural changes to the network. Synthetic experiments validate that our DL-based method outperforms conventional separate inversions and cross-gradient-based joint inversion in view of the accuracy of the recovered models and inversion efficiency. Successful application to field data further verifies the effectiveness of our DL-based method.

Geochemistry & Geophysics↗
DOE OSTI2019

An Efficient Bayesian Method for Advancing the Application of Deep Learning in Earth Science

Despite their wide and successful applications, deep learning (DL) models are prone to overfitting for small training datasets, produce a poor predictive performance for uncertain data, and provide point estimations without any indication of the accuracy and credibility. These limitations of the deterministic DL models hinder their effective application in Earth system science where the labelled data are sparse, noisy and incomplete with large uncertainty and where the predictive uncertainty quantification is needed for scientific understanding and policy decision making. Integration of Bayesian inference into DL models adds an estimate of uncertainty and regularization in the predictions. However, traditional Bayesian methods are computationally unaffordable and inflexible for high-dimensional problems, which limits their application to DL systems that typically have millions of model parameters. In this effort, we propose an efficient and general-purpose Bayesian inference method to advance DL model optimization and uncertainty quantification, so as to facilitate the adoption of DL in Earth sciences. In a demonstration, we integrate the proposed Bayesian method with a feedforward neural network (NN) to build a fast-to-evaluate surrogate of the complex Energy Exascale Earth System Land Model for efficient modeling. The formulated Bayesian NN, using a small number of training data, produces an accurate prediction with high credibility, whereas with the same small training size, the deterministic NN cannot yield a reasonable estimation and does not provide confidence information. The proposed Bayesian method is computationally efficient and flexible, capable of integration with diverse network variants such as convolutional NNs and recurrent NNs to advance the application of DL in Earth sciences.

Lu, Dan↗
DOE OSTI2020

Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94]

Accurate energy forecasting is becoming critical due to many reasons: i ) optimal distributed energy resources operations and dispatch, ii) fault detection and diagnostics, and iii) meeting operational energy efficiency targets. Wattile uses deep learning (DL) for the building's short-term load forecasting application. Two specific types of neural networks called, Long Short Term Memory (LSTM) and Sequence-to-Sequence (S2S) models are used to make predictions. Forecasting models are trained using online historical weather and occupancy indicator data streams from the Intelligent Campus Program's data acquisition systems at the National Renewable Energy Laboratory (NREL) for main meters and sub-meters of multiple building types. These models use probabilistic methods to provide quantile-based forecasts in addition to nominal conditional median predictions of electricity consumption.

Frank, Stephen↗
NASA NTRS1972

Effects of diffusion impairment on O2 and CO2 time courses in pulmonary capillaries.

Simultaneous time courses for O2 and CO2 exchange along the capillary have been calculated for homogeneous lungs, allowing for O2-CO2 interactions, dissolved O2, and chemical reaction rates. As diffusing capacity (Dl) was reduced, the transfer of CO2 and O2 was impaired by similar amounts, in spite of the 20-fold greater diffusing capacity for CO2. The reason why CO2 is affected so much is that the slope of the content against partial pressure is so much greater in blood than tissue for this gas. Because of the shapes of their respective dissociation curves, O2 transfer was most affected at normal ventilation-perfusion ratios, whereas CO2 was most affected at high ratios. Exercise exaggerated the impairment of transfer of both gases.

Wagner, P. D.↗
DOE OSTI2023

Predicting future well performance for environmental remediation design using deep learning

Here in this study, we developed a deep learning (DL) framework with a multi-channel three-dimensional convolutional neural network (MC3D-CNN) to predict well performance and thereby assist future environmental remediation design. Such prediction of extraction well performance at designated locations is critical for configuring pump-and-treat (P&T) well network design and operation, setting reasonable target closure dates for overall remedying, and estimating remedy costs. The framework is developed with operational and monitoring data routinely collected during P&T remedy operations, including well extraction and injection rates as well as in situ contaminant concentrations. Traditionally, the collected data were rarely used for purposes other than assessing past well performance and the accuracy of the conceptual site model. However, recent advances in data-driven computational approaches enable better use of the large datasets to inform future well performance, enhance site characterization, and improve remediation planning. In this study, we established a DL framework to integrate transient three-dimensional contaminant plumes and multiple aquifer properties (e.g., hydraulic conductivity and hydrostratigraphic maps) to identify characteristic patterns controlling and representing extraction well mass recovery, aiming at providing future mass recovery estimates for existing wells and candidate wells at any proposed locations. We evaluated our framework by using a realistic synthetic dataset generated from a well-calibrated flow and transport model used in the 200 West Area of the U.S. Department of Energy’s Hanford Site in southeastern Washington state. The multi-channel feature in our framework allows integration of various types and temporal densities of training datasets for DL model development. Overall, we found that the trained DL model achieved an accuracy of over 90% in ranking extraction well performance in validation datasets, and over 80% in predicting high-performance-ranking well locations. This data-informed approach provides a flexible tool to support adaptive site management, streamline decision-making, and potentially reduce remediation time and costs. Our DL framework can be used as a filtering tool to improve the current P&T network optimization design by reducing the number of candidate well locations.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Next Generation Thermal Protection System for Outer Planet Probes and Orbiter

Saturn Probe and Ice Giant Orbiter along with in-situ Probe Missions continue to be very high priority mis-sions. A result of the advocacy by OPAG and other Analysis Groups, the 3D Woven, Dual-Layer HEEET thermal protection system, mature at TRL 6, has closed the TPS gap for extreme environment missions. A mid density follow on to DL HEEET, developed to meet earth entry requirements, is a Single Layer vari-ant of the 3D woven TPS, which provides a mass effi-cient single layer 3D Mid-Density TPS (3MDCP) that has been baselined as the heatshield for MSR EEV. Continued development of 3MDCP will elevate it to TRL 6 by 2025. Conformal-PICA (C-PICA) devel-opment was pursued to establish a more efficient and robust alternate to PICA, and it is at TRL 4+. Our rationale for the next generation of TPS de-velopment is based on the on the missions needs of the next decade Outer Planet missions that are unique and more demanding than any other destinations. Taking advantage of the recent planned development of sev-eral materials, the next generation of TPS offers a much more mass efficient option for small, medium, and large class Outer Planet missions. Saturn Probes: While mission designers are gen-erally interested in shallow entry to maintain the g-load during entry around 50g, the heat-load for shallow entry can range between (100 kJ/cm2 – 300 kJ/cm2), two orders of magnitude higher than Venus or Sample Return missions. TPS must not only offer protection but must be mass efficient to perform reasonable sci-ence. TPS mass can quickly become 50% or more of the mass of the entire entry system. Recent analysis performed shows Saturn Probe missions could signifi-cantly benefit from the single layer HEEET (SL-HEEET/3MDCP). A DL-HEEET based heatshield mass could be ~ (40% -50%), SL-HEEET can provide additional (30% - 50%) mass savings. At the same time, C-PICA can provide (30% - 50%) mass savings on the backshell. The combined mass savings can be significant enough to carry an additional probe, if de-sired. Ice Giant Aerocapture Missions: Aerocapture mission architectures can provide significant ad-vantage over traditional propulsive insertion missions in multiple ways. 1) Reduced trip time ~ (4- 6) years (30% -40%), 2) Enables placing the orbiter, probe, and lander, all together and 3) Allows for greater science mass (probes and landers) due to mass efficiency. The delivery of a probe from orbit makes it easier and eliminates mission design constraints by HEEET for direct entry [4] of probes and allows for more targeted in-situ science once the Orbiter is able to collect data. In the past 20 years, progress made in GN&C for lift-guided entry missions (MSL, Orion EFT1, Mars 2020) and the expertise in blunt body aerodynamics at large scale (~ 5m) has led the EDL community to conclude that aerocapture is a “go do” engineering activity. An aerocapture mission that will deplete the excess energy of a fast arrival mission will require a mass efficient TPS that can handle extreme heat-load, ~ (100 kJ/cm2 – 500 kJ/cm2). Hence TPS, feasibility as well as mass efficiency requires assessment. Utilizing the recent developments, a comprehensive, bounding analysis was done to establish the potential for SOA (HEEET) system as well as emerging new TPS such as SL-HEEET and C-PICA. In this proposed poster, we will outline the process by which we establish bounding aerocapture trajecto-ries for hyperbolic excess velocities ranging from 27 km/s to 35 km/s, for low L/D (~ 0.4) configurations and determine conservative/bounding estimate of aer-othermal environment by using a combination of CFD simulations and stagnation point heating estimates [7]. This engineering approach allows us to assess the TPS need vs. TPS capability and determine the applicability of existing TPS. Once an applicable suite of TPS is determined, the TPS thickness and mass are comput-ed. We show that the TPS mass fraction can be as low as 5% to as high as 20%, depending on the use of ad-vanced TPS, while HEEET is sufficient but will require 50% of the entry mass.

E Venkatapathy↗
NASA NTRS1984

Beta-decay, Bremsstrahlen, and the origin of molecular chirality

A brief review is presented of the Vester-Ulbricht beta-decay Bremsstrahlen hypothesis for the origin of optical activity, and of subsequent experiments designed to test it. Certain experiments along these lines, begun in 1974 and involving the irradiation of racemic and optically active amino acids in a 61.7 KCi Sr-90-Y-90 Bremsstrahlen source, have now been completed and are described. After 10.89 years of irradiation with a total Bremsstrahlen dose of 2.5 x 10 to the 9th rads, crystalline DL-leucine, norleucine, and norvaline suffered 47.2, 33.6, and 27.4 percent radiolysis, respectively, but showed no evidence whatsoever of asymmetric degradation. Dand L-Leucine underwent about 48 percent radiolysis and showed 2.4-2.9 percent radioracemization. Other samples in solution were too severely degraded to analyze. Probable intrinsic reasons for the failure of the Vester-Ulbricht mechanism to afford asymmetric radiolysis in the present and related experiments involving beta-decay Bremsstrahlen are enumerated.

Bonner, W. A.↗
DOE OSTI2022

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. Here, in this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations—content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a human-understandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
NASA NTRS1984

Experimental evidence for beta-decay as a source of chirality by enantiomer analysis

Earlier experiments testing the Vester-Ulbricht beta-decay hypothesis for the origin of molecular chirality are reviewed, followed by descriptions of experiments involving attempted asymmetric radiolysis of DL-amino acids using quantitative gas chromotography as a probe for optical activity. The radiation sources included Sr-90-Y-90, C-14, and P-32 Bremsstrahlen, longitudinally polarized electrons from a linear accelerator and longitudinally polarized protons from a cyclotron. With the possible exception of the linear accelerator irradiations, these experiments failed to produce g.c.-detectable enantiomeric excesses, even at 50-70 percent gross radiolysis. Thus no unambiguous support for the Vester-Ulbricht hypothesis is found in any of the attempted asymmetric radiolyses performed to date. Radioracemization, a possible reason for these failures, is discussed.

Bonner, W. A.↗