Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep space”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Bayesian reduced-order deep learning surrogate model for dynamic systems described by partial differential equations

We propose a reduced-order deep-learning surrogate model for dynamic systems described by time-dependent partial differential equations. This method employs space–time Karhunen–Loève expansions (KLEs) of the state variables and space-dependent KLEs of space-varying parameters to identify the reduced (latent) dimensions. Subsequently, a deep neural network (DNN) is used to map the parameter latent space to the state variable latent space. An approximate Bayesian method is developed for uncertainty quantification (UQ) in the proposed KL-DNN surrogate model. The KL-DNN method is tested for the linear advection–diffusion and nonlinear diffusion equations, and the Bayesian approach for UQ is compared with the deep ensembling (DE) approach, commonly used for quantifying uncertainty in DNN models. It was found that the approximate Bayesian method provides a more informative distribution of the PDE solutions in terms of the coverage of the reference PDE solutions (the percentage of nodes where the reference solution is within the confidence interval predicted by the UQ methods) and log predictive probability. The DE method is found to underestimate uncertainty and introduce bias. For the nonlinear diffusion equation, we compare the KL-DNN method with the Fourier Neural Operator (FNO) method and find that KL-DNN is 10% more accurate and needs less training time than the FNO method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Automating Discovery of Physics-Informed Neural State Space Models via Learning and Evolution

Recent works exploring deep learning application to dynamical systems modeling have demonstrated that embedding physical priors into neural networks can yield more effective, physically-realistic, and data-efficient models. However, in the absence of complete prior knowledge of a dynamical system's physical characteristics, determining the optimal structure and optimization strategy for these models can be difficult. In this work, we explore methods for discovering neural state space dynamics models for system identification. Starting with a design space of block-oriented state space models and structured linear maps with strong physical priors, we encode these components into a model genome alongside network structure, penalty constraints, and optimization hyperparameters. Demonstrating the overall utility of the design space, we employ an asynchronous genetic search algorithm that alternates between model selection and optimization and obtains accurate physically consistent models of three physical systems: an aerodynamics body, a continuous stirred tank reactor, and a two tank interacting system.

genetic algorithms, neural architecture search, ne↗
DOE OSTI2022

Weathering of chlorite from grain to watershed: The role and distribution of oxidation reactions in the subsurface

The reaction mechanism of weathering of chlorite, an important rock-forming phyllosilicate, is not well understood in natural settings. Here, in this work we investigated the weathering of Fe-rich chlorite from deep protolith to saprock to soil across a small shale-underlain watershed in the Appalachian Mountains, USA (Shale Hills). We found that oxidation of Fe(II) in chlorite always occurs prior to dissolution of the interlayers of the mineral. The oxidation of pyrite and chlorite commence near the water table across narrow depth intervals under the upper-catchment ridges, but well below the water table across wide depth intervals under the valley. We hypothesize that these patterns can be explained by hydrological and geochemical differences between the ridge and the valley: oxygenated water descends sub-vertically (1D flow) under the ridge, while under the valley, oxygen-depleted water moves upward to the stream and laterally out of the watershed in the subsurface (3D flow). Geochemical and mineralogical characterization indicates that the transformation of Fe-rich chlorite at Shale Hills is initiated by the oxidation of Fe(II). Next, the interlayer hydroxide sheet dissolves to form hydroxy-interlayered vermiculite and then vermiculite. During the transformation, Mg and Fe are released into solution and Fe is reprecipitated as goethite in pore space. Delivery of oxygen to the deep subsurface by infiltration of meteoric water is thought to control the initial transformation of chlorite at Shale Hills. It is possible that weathering of many Fe(II)-rich minerals is initiated by oxidation as mediated by rates of subsurface oxygen delivery.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study

Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a complete theoretical framework for understanding these scaling laws remains underdeveloped. In this paper, we explore the neural scaling laws for deep operator networks, which involve learning mappings between function spaces, with a focus on the Chen and Chen style architecture. These approaches, which include the popular Deep Operator Network (DeepONet), approximate the output functions using a linear combination of learnable basis functions and coefficients that depend on the input functions. We establish a theoretical framework to quantify the neural scaling laws by analyzing its approximation and generalization errors. We articulate the relationship between the approximation and generalization errors of deep operator networks and key factors such as network model size and training data size. Moreover, we address cases where input functions exhibit low-dimensional structures, allowing us to derive tighter error bounds. These results also hold for deep ReLU networks and other similar structures. Our results offer a partial explanation of the neural scaling laws in operator learning and provide a theoretical foundation for their applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Spectroscopic confirmation of a mature galaxy cluster at a redshift of 2

Galaxy clusters are the most massive virialized structures in the Universe and are formed through the gravitational accretion of matter over cosmic time. The discovery of an evolved galaxy cluster at redshift z = 2, corresponding to a look-back time of 10.4 billion years, provides an opportunity to study its properties. The galaxy cluster XLSSC 122 was originally detected as a faint, extended X-ray source in the XMM Large Scale Structure survey and was revealed to be coincident with a compact over-density of galaxies with photometric redshifts of 1.9 ± 0.2. Subsequent observations at millimetre wavelengths detected a Sunyaev–Zel’dovich decrement along the line of sight to XLSSC 122, thus confirming the existence of hot intracluster gas, while deep imaging spectroscopy from the European Space Agency’s X-ray Multi-Mirror Mission (XMM-Newton) revealed an extended, X-ray-bright gaseous atmosphere with a virial temperature of 60 million Kelvin, enriched with metals to the same extent as are local clusters. Here we report optical spectroscopic observations of XLSSC 122 and identify 37 member galaxies at a mean redshift of 1.98, corresponding to a look-back time of 10.4 billion years. We use photometry to determine a mean, dust-free stellar age of 2.98 billion years, indicating that star formation commenced in these galaxies at a mean redshift of 12, when the Universe was only 370 million years old. The full range of inferred formation redshifts, including the effects of dust, covers the interval from 7 to 13. These observations confirm that XLSSC 122 is a remarkably mature galaxy cluster with both evolved stellar populations in the member galaxies and a hot, metal-rich gas composing the intracluster medium.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

A Cohesive Deep Drilling Field Strategy for LSST Cosmology

The Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will image billions of astronomical objects in the wide–fast–deep primary survey and in a set of minisurveys including intensive observations of a group of deep drilling fields (DDFs). The DDFs are a critical piece of three key aspects of the LSST Dark Energy Science Collaboration (DESC) cosmological measurements: they provide a required calibration for photometric redshifts (photo- z ) and weak gravitational lensing (WL) measurements and they directly contribute to cosmological constraints from the most distant Type Ia supernovae (SNe Ia). We present a set of cohesive DDF strategies fulfilling science requirements relevant to DESC and following the guidelines of the Survey Cadence Optimization Committee. We propose a method to estimate the observing strategy parameters and we perform simulations of the corresponding surveys. We define a set of metrics for each science case to assess the performance of the proposed observing strategies. We show that the most promising results are achieved with deep rolling surveys characterized by two sets of fields: ultradeep fields ( z ≲ 1.1) observed at a high cadence with a large number of visits over a limited number of seasons, and deep fields ( z ≲ 0.7), observed with a cadence of ~3 nights for 10 yr. These encouraging results should be confirmed with realistic simulations using the LSST scheduler. A DDF budget of ~8.5% is required to design observing strategies satisfying all the cosmological requirements. A lower DDF budget leads to surveys that either do not fulfill the photo- z /WL requirements or are not optimal for SN Ia cosmology.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
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 OSTI2024

Integrating the PanDA Workload Management System with the Vera C. Rubin Observatory

The Vera C. Rubin Observatory will produce an unprecedented astronomical data set for studies of the deep and dynamic universe. Its Legacy Survey of Space and Time (LSST) will image the entire southern sky every three to four days and produce tens of petabytes of raw image data and associated calibration data over the course of the experiment’s run. More than 20 terabytes of data must be stored every night, and annual campaigns to reprocess the entire dataset since the beginning of the survey will be conducted over ten years. The Production and Distributed Analysis (PanDA) system was evaluated by the Rubin Observatory Data Management team and selected to serve the Observatory’s needs due to its demonstrated scalability and flexibility over the years, for its Directed Acyclic Graph (DAG) support, its support for multi-site processing, and its highly scalable complex workflows via the intelligent Data Delivery Service (iDDS). PanDA is also being evaluated for prompt processing where data must be processed within 60 seconds after image capture. This paper will briefly describe the Rubin Data Management system and its Data Facilities (DFs). Finally, it will describe in depth the work performed in order to integrate the PanDA system with the Rubin Observatory to be able to run the Rubin Science Pipelines using PanDA.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Computational Workflow for Accelerated Molecular Design Using Quantum Chemical Simulations and Deep Learning Models

Efficient methods for searching the chemical space of molecular compounds are needed to automate and accelerate the design of new functional molecules such as pharmaceuticals. Given the high cost in both resources and time for experimental efforts, computational approaches play a key role in guiding the selection of promising molecules for further investigation. Here, we construct a workflow to accelerate design by combining approximate quantum chemical methods [i.e. density-functional tight-binding (DFTB)], a graph convolutional neural network (GCNN) surrogate model for chemical property prediction, and a masked language model (MLM) for molecule generation. Property data from the DFTB calculations are used to train the surrogate model; the surrogate model is used to score candidates generated by the MLM. The surrogate reduces computation time by orders of magnitude compared to the DFTB calculations, enabling an increased search of chemical space. Furthermore, the MLM generates a diverse set of chemical modifications based on pre-training from a large compound library. We utilize the workflow to search for near-infrared photoactive molecules by minimizing the predicted HOMO-LUMO gap as the target property. Our results show that the workflow can generate optimized molecules outside of the original training set, which suggests that iterations of the workflow could be useful for searching vast chemical spaces in a wide range of design problems.

Blanchard, Andrew↗
DOE OSTI2021

A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration

Climate change is reshaping vulnerable ecosystems, leading to uncertain effects on ecosystem dynamics, including evapotranspiration (ET) and ecosystem respiration (R eco ). However, accurate estimation of ET and R eco still remains challenging at sparsely monitored watersheds, where data and field instrumentation are limited. In this study, we developed a hybrid predictive modeling approach (HPM) that integrates eddy covariance measurements, physically based model simulation results, meteorological forcings, and remote-sensing datasets to estimate ET and R eco in high space–time resolution. HPM relies on a deep learning algorithm and long short-term memory (LSTM) and requires only air temperature, precipitation, radiation, normalized difference vegetation index (NDVI), and soil temperature (when available) as input variables. We tested and validated HPM estimation results in different climate regions and developed four use cases to demonstrate the applicability and variability of HPM at various FLUXNET sites and Rocky Mountain SNOTEL sites in Western North America. To test the limitations and performance of the HPM approach in mountainous watersheds, an expanded use case focused on the East River Watershed, Colorado, USA. The results indicate HPM is capable of identifying complicated interactions among meteorological forcings, ET, and R eco variables, as well as providing reliable estimation of ET and R eco across relevant spatiotemporal scales, even in challenging mountainous systems. The study documents that HPM increases our capability to estimate ET and R eco and enhances process understanding at sparsely monitored watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Learning in continuous action space for developing high dimensional potential energy models

Reinforcement learning (RL) approaches that combine a tree search with deep learning have found remarkable success in searching exorbitantly large, albeit discrete action spaces, as in chess, Shogi and Go. Many real-world materials discovery and design applications, however, involve multi-dimensional search problems and learning domains that have continuous action spaces. Exploring high-dimensional potential energy models of materials is an example. Traditionally, these searches are time consuming (often several years for a single bulk system) and driven by human intuition and/or expertise and more recently by global/local optimization searches that have issues with convergence and/or do not scale well with the search dimensionality. Here, in a departure from discrete action and other gradient-based approaches, we introduce a RL strategy based on decision trees that incorporates modified rewards for improved exploration, efficient sampling during playouts and a “window scaling scheme" for enhanced exploitation, to enable efficient and scalable search for continuous action space problems. Using high-dimensional artificial landscapes and control RL problems, we successfully benchmark our approach against popular global optimization schemes and state of the art policy gradient methods, respectively. We demonstrate its efficacy to parameterize potential models (physics based and high-dimensional neural networks) for 54 different elemental systems across the periodic table as well as alloys. We analyze error trends across different elements in the latent space and trace their origin to elemental structural diversity and the smoothness of the element energy surface. Broadly, our RL strategy will be applicable to many other physical science problems involving search over continuous action spaces.

36 MATERIALS SCIENCE↗
DOE OSTI2026

The effect of hydroxyl spacing in diols on the solvation structure, dynamics, and transport properties of choline chloride-based deep eutectic solvents

Deep eutectic solvents (DESs) are a class of liquids that offer great potential in alleviating some of the challenges present in today's long-term energy storage methods because they have physical properties that are favorable for storable electrolyte solutions. In this work, a series of glycols (ethylene glycol, 1,3-propanediol, 1,4-butanediol, and 1,5-pentanediol) were studied as potential hydrogen bond donors (HBD) with a common choline chloride (ChCl) as the hydrogen bond acceptor (HBA). The solvation dynamics of the prepared systems were studied by measuring the solvent reorganization response using femtosecond transient absorption spectroscopy (fs-TA). Conductivity, viscosity, density, ET(30) polarity, and dynamics of the prepared DESs were analyzed, with a particular interest in determining the effect of HBD chain length on these parameters. Here, classical molecular dynamics simulations were employed to investigate how the local liquid structure, solvent dynamics, and bulk solvent properties vary with changes in glycol chain length.

Conductivity↗
DOE OSTI2022

Epidural anesthesia needle guidance by forward-view endoscopic optical coherence tomography and deep learning

Epidural anesthesia requires injection of anesthetic into the epidural space in the spine. Accurate placement of the epidural needle is a major challenge. To address this, we developed a forward-view endoscopic optical coherence tomography (OCT) system for real-time imaging of the tissue in front of the needle tip during the puncture. We tested this OCT system in porcine backbones and developed a set of deep learning models to automatically process the imaging data for needle localization. A series of binary classification models were developed to recognize the five layers of the backbone, including fat, interspinous ligament, ligamentum flavum, epidural space, and spinal cord. The classification models provided an average classification accuracy of 96.65%. During puncture, it is important to maintain a safe distance between the needle tip and the dura mater. Regression models were developed to estimate that distance based on the OCT imaging data. Based on the Inception architecture, our models achieved a mean absolute percentage error of 3.05% ± 0.55%. Overall, our results validated the technical feasibility of using this novel imaging strategy to automatically recognize different tissue structures and measure the distances ahead of the needle tip during the epidural needle placement.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Astronomical image time series classification using CONVolutional attENTION (ConvEntion)

Aims: The treatment of astronomical image time series has won increasing attention in recent years. Indeed, numerous surveys following up on transient objects are in progress or under construction, such as the Vera C. Rubin Observatory Legacy Survey for Space and Time (LSST), which is poised to produce huge amounts of these time series. The associated scientific topics are extensive, ranging from the study of objects in our galaxy to the observation of the most distant supernovae for measuring the expansion of the universe. With such a large amount of data available, the need for robust automatic tools to detect and classify celestial objects is growing steadily. Methods: This study is based on the assumption that astronomical images contain more information than light curves. In this paper, we propose a novel approach based on deep learning for classifying different types of space objects directly using images. We named our approach ConvEntion, which stands for CONVolutional attENTION. It is based on convolutions and transformers, which are new approaches for the treatment of astronomical image time series. Our solution integrates spatio-temporal features and can be applied to various types of image datasets with any number of bands. Results: In this work, we solved various problems the datasets tend to suffer from and we present new results for classifications using astronomical image time series with an increase in accuracy of 13%, compared to state-of-the-art approaches that use image time series, and a 12% increase, compared to approaches that use light curves.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Testing convolutional neural network based deep learning systems: a statistical metamorphic approach

Machine learning technology spans many areas and today plays a significant role in addressing a wide range of problems in critical domains,i.e., healthcare, autonomous driving, finance, manufacturing, cybersecurity,etc. Metamorphic testing (MT) is considered a simple but very powerful approach in testing such computationally complex systems for which either an oracle is not available or is available but difficult to apply. Conventional metamorphic testing techniques have certain limitations in verifying deep learning-based models (i.e., convolutional neural networks (CNNs)) that have a stochastic nature (because of randomly initializing the network weights) in their training. In this article, we attempt to address this problem by using a statistical metamorphic testing (SMT) technique that does not require software testers to worry about fixing the random seeds (to get deterministic results) to verify the metamorphic relations (MRs). We propose seven MRs combined with different statistical methods to statistically verify whether the program under test adheres to the relation(s) specified in the MR(s). We further use mutation testing techniques to show the usefulness of the proposed approach in the healthcare space and test two CNN-based deep learning models (used for pneumonia detection among patients). The empirical results show that our proposed approach uncovers 85.71% of the implementation faults in the classifiers under test (CUT). Furthermore, we also propose an MRs minimization algorithm for the CUT, thus saving computational costs and organizational testing resources.

Computer Science↗
DOE OSTI2024

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in scientific computations due to conveniently offering a ``shared-memory''-like model and convenient interfaces that separate communication with synchronization. Traditionally, PGAS communication models have been applied to dense/contiguously distributed data, but most modern applications depict varied levels of sparsity. Existing PGAS models require certain adaptations to support distributed sparse computations, since associated computations often require matrix arithmetic, in addition to data movement. The Global Arrays toolkit from Pacific Northwest National Laboratory (PNNL) is one of the earliest PGAS models to combine one-sided data communication and distributed matrix operations and is still used in the popular NWChem quantum chemistry suite. Recently, we have expanded the Global Arrays toolkit to support common sparse operations, like sparse matrix-dense matrix multiplies (SpMM), sparse matrix-sparse matrix multiplication (SpGEMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). As it turns out, these operations are the bedrock of sparse Deep Learning (DL); sparse deep neural networks and Graph Neural Networks (GNNs) have gained increasing attention recently in achieving speedups on training and inference with reduced memory footprints. Unlike scientific applications in High Performance Computing (HPC), modern (distributed-memory capable) DL toolkits often rely on non-standardized and closed-source vendor software optimizations, creating challenges in software-hardware co-design at scale. Our goal is to support a variety of distributed-memory sparse matrix operations and helper functions in the newly created Sparse Global Arrays (SGA), such that it is possible to build portable and productive Machine Learning scenarios for algorithm/software and hardware codesign purposes. Contemporary data-parallel schemes for training/inference are undergoing a major overhaul since model replication limits scalability and causes resource inefficiencies. As such, we have adopted tensor parallelism in decomposing the model and inputs, to mitigate memory issues. Current implementation is built on top of MPI and uses CPUs to maximize the portability across the platforms.

Distributed computing, machine learning↗
DOE OSTI2024

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Abstract Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

97 MATHEMATICS AND COMPUTING↗