Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learned priors”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Three-dimensional coherent X-ray diffraction imaging via deep convolutional neural networks

Abstract As a critical component of coherent X-ray diffraction imaging (CDI), phase retrieval has been extensively applied in X-ray structural science to recover the 3D morphological information inside measured particles. Despite meeting all the oversampling requirements of Sayre and Shannon, current phase retrieval approaches still have trouble achieving a unique inversion of experimental data in the presence of noise. Here, we propose to overcome this limitation by incorporating a 3D Machine Learning (ML) model combining (optional) supervised learning with transfer learning. The trained ML model can rapidly provide an immediate result with high accuracy which could benefit real-time experiments, and the predicted result can be further refined with transfer learning. More significantly, the proposed ML model can be used without any prior training to learn the missing phases of an image based on minimization of an appropriate ‘loss function’ alone. We demonstrate significantly improved performance with experimental Bragg CDI data over traditional iterative phase retrieval algorithms.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

DG2DAG: Learning Directed Acyclic Graphs from Functional Priors

Physics-based systems-of-systems models are computationally expensive. Reduced graphical models can decrease computational complexity, but may not proffer an end-to-end model from upstream inputs to downstream outputs. We consequently are interested in reducing models on directed graphs to models on a directed acyclic subgraph such that preserves accurate reconstruction of nodes. The consequence is a model with a topological ordering, providing a one-way flow of computation, and a causal interpr

Voronin, Alexey [Sandia National Laboratories (SNL↗
DOE OSTI2024

From Latent Dynamics to Meaningful Representations

While representation learning has been central to the rise of machine learning and artificial intelligence, a key problem remains in making the learnt representations meaningful. For this the typical approach is to regularize the learned representation through prior probability distributions. However such priors are usually unavailable or are ad hoc. To deal with this, recent efforts have shifted towards leveraging the insights from physical principles to guide the learning process. In this spirit, we propose a purely dynamics-constrained representation learning framework. Instead of relying on predefined probabilities, we restrict the latent representation to follow overdamped Langevin dynamics with a learnable transition density — a prior driven by statistical mechanics. We show this is a more natural constraint for representation learning in stochastic dynamical systems, with the crucial ability to uniquely identify the ground truth representation. We validate our framework for different systems including a real-world fluorescent DNA movie dataset. Here, we show that our algorithm can uniquely identify orthogonal, isometric and meaningful latent representations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2005

Learning from the Mars Rover Mission: Scientific Discovery, Learning and Memory

Purpose: Knowledge management for space exploration is part of a multi-generational effort. Each mission builds on knowledge from prior missions, and learning is the first step in knowledge production. This paper uses the Mars Exploration Rover mission as a site to explore this process. Approach: Observational study and analysis of the work of the MER science and engineering team during rover operations, to investigate how learning occurs, how it is recorded, and how these representations might be made available for subsequent missions. Findings: Learning occurred in many areas: planning science strategy, using instrumen?s within the constraints of the martian environment, the Deep Space Network, and the mission requirements; using software tools effectively; and running two teams on Mars time for three months. This learning is preserved in many ways. Primarily it resides in individual s memories. It is also encoded in stories, procedures, programming sequences, published reports, and lessons learned databases. Research implications: Shows the earliest stages of knowledge creation in a scientific mission, and demonstrates that knowledge management must begin with an understanding of knowledge creation. Practical implications: Shows that studying learning and knowledge creation suggests proactive ways to capture and use knowledge across multiple missions and generations. Value: This paper provides a unique analysis of the learning process of a scientific space mission, relevant for knowledge management researchers and designers, as well as demonstrating in detail how new learning occurs in a learning organization.

Linde, Charlotte↗
DOE OSTI2025

The influence of exposure to early-life adversity on agency-modulated reinforcement learning

Agency beliefs influence how humans learn from different contexts and outcomes. Research demonstrates that stressors, such as exposure to early-life adversity (ELA), are associated with both agency beliefs and learning, but how these processes interact remains unclear. The current study investigated whether exposure to ELA influences agency and interacts with reinforcement learning in adults. Replicating prior behavioral and computational work, ELA resulted in decreased learning, while increased adversity severity was associated with decreased latent agency beliefs. These findings suggest that exposure to adversity in childhood has a nuanced impact on reinforcement learning and agency beliefs in adulthood.

Neurosciences & Neurology↗
DOE OSTI2025

Unrolled Video Super-Resolution Network with Autoregressive Prior for the Case of Known Motion

Real-time detection and classification of distant objects is necessary for many national security applications. However, when objects are far from the sensor, they occupy only a small number of pixels in the captured video, limiting the amount of visual detail available for recognition. State-of-the-art classification methods typically rely on high-resolution (HR) video streams to capture characteristic object features, but obtaining such detail is challenging for distant objects that occupy only a few pixels. This motivates the development of video super-resolution (VSR) methods that enhance object classification by recovering fine details from low-pixel representations. Current VSR methods rely either on model-based optimization, which is interpretable but computationally expensive, or on learning-based approaches, which are efficient and high-performing but often lack flexibility and interpretability. In this report, we propose an end-to-end trainable unrolled VSR network, UVSRNet, which super-resolves each frame in a video by exploiting sub-pixel motion between neighboring low-resolution (LR) frames as well as incorporating high-frequency detail from previously super-resolved frames. In particular, by unrolling a plug-and-play (PnP) half-quadratic splitting (HQS) algorithm, we leverage a model-based data-fitting module alongside a learning-based autoregressive prior module. This combination yields a method that maintains the flexibility and interpretability of model-based methods while achieving the performance advantages of learning-based methods.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
NASA NTRS1999

Dimensionality Reduction Through Classifier Ensembles

In data mining, one often needs to analyze datasets with a very large number of attributes. Performing machine learning directly on such data sets is often impractical because of extensive run times, excessive complexity of the fitted model (often leading to overfitting), and the well-known "curse of dimensionality." In practice, to avoid such problems, feature selection and/or extraction are often used to reduce data dimensionality prior to the learning step. However, existing feature selection/extraction algorithms either evaluate features by their effectiveness across the entire data set or simply disregard class information altogether (e.g., principal component analysis). Furthermore, feature extraction algorithms such as principal components analysis create new features that are often meaningless to human users. In this article, we present input decimation, a method that provides "feature subsets" that are selected for their ability to discriminate among the classes. These features are subsequently used in ensembles of classifiers, yielding results superior to single classifiers, ensembles that use the full set of features, and ensembles based on principal component analysis on both real and synthetic datasets.

Oza, Nikunj C.↗
NASA NTRS1992

Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning

Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.

Berenji, Hamid R.↗
DOE OSTI2024

Learning Topological Operations on Meshes with Application to Block Decomposition of Polygons

We present a learning based framework for mesh quality improvement on unstructured triangular and quadrilateral meshes. Our model learns to improve mesh quality according to a prescribed objective function purely via self-play reinforcement learning with no prior heuristics. The actions performed on the mesh are standard local and global element operations. The goal is to minimize the deviation of the node degrees from their ideal values, which in the case of interior vertices leads to a minimization of irregular nodes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Graph Learning in Physical-informed Mesh-reduced Space for Real-world Dynamic Systems

This Git repository contains codes for the 'Graph Learning in Physical-informed Mesh-reduced Space for Real-world Dynamic Systems' paper that will be published in 2023 SIGKDD. This work uses physical-informed prior (PiP) information to learn and predict fluid dynamics in a reduced mesh space. We propose a two-stage graph-based model for fluid velocity field reconstruction and prediction. In the first stage, we learn a subgraph autoencoder to summarize the information in a mesh-reduced space using physical-informed priors. In the second stage, we learn a dynamics predictor to predict subgraph evolution. We demonstrate the effectiveness of our model on two fluid flow datasets: lid-driven cavity flow data and cylinder flow data. This code is also applicable for any other dynamic systems with corresponding data.

Lei, Bo↗
DOE OSTI2023

Oxidation Driven Thin‐Film Solid‐State Metal Dealloying Forming Bicontinuous Nanostructures

Abstract Solid‐state metal dealloying (SSMD) is a promising method for fabricating nanoscale metallic composites and nanoporous metals across a range of materials. Thin‐film SSMD is particularly attractive due to its ability to create fine features via solid‐state interfacial reactions within a thin‐film geometry, which can be integrated into devices for various applications. This work examines a new dealloying couple, namely the Nb–Al alloy with the dealloying agent Sc, as previously predicted in the machine‐learning (ML) models. Prior ML predictions aimed to guide the design of nanoarchitectured materials through dealloying, relying on intuition‐driven discovery within a large parameter space. However, this work reveals that at the nanoscale, the involvement of oxygen in thin film processing may instead drive the dealloying process, resulting in the formation of bicontinuous nanostructures similar to those formed by metal‐agent dealloying. The phase evolution, as well as chemical and morphological changes, are closely analyzed using a combination of X‐ray absorption spectroscopy, diffraction, and scanning transmission electron microscopy to understand the mechanisms behind nanostructure formation. The findings suggest a potential pathway for utilizing oxygen to drive the formation of bicontinuous metal–metal oxide nanocomposites, paving the way for further development of functional nanoporous materials in diverse fields.

36 MATERIALS SCIENCE↗
NASA NTRS2017

Synergies Between the Kepler, K2 and TESS Missions with the PLATO Mission (Revised)

Two transit survey missions will have been flown by NASA prior to the launch of ESA's PLATO Mission in 2026, laying the groundwork for exoplanet discovery via the transit method. The Kepler Mission, which launched in 2009, collected data on its 100+ square degree field of view for four years before failure of a reaction wheel ended its primary mission. The results from Kepler include 2300+ confirmed or validated exoplanets, 2200+ planetary candidates, 2100+ eclipsing binaries. Kepler also revolutionized the field of asteroseismology by measuring the pressure mode oscillations of over 15000 solar-like stars spanning the lifecycle of such stars from hydrogen-burning dwarfs to helium-burning red giants. The re-purposed Kepler Mission, dubbed K2, continues to observe fields of view in and near the ecliptic plane for 80 days each, significantly broadening the scope of the astrophysical investigations as well as discovering an additional 156 exoplanets to date. The TESS mission will launch in 2017 to conduct an all-sky survey for small exoplanets orbiting stars 10X closer and 100X brighter than Kepler exoplanet host stars, allowing for far greater follow-up and characterization of their masses as well as their sizes for at least 50 small planets. Future assets such as James Webb Space Telescope, and ground-based assets such as ESOs Very Large Telescope (VLT) array, the Exremely Large Telescope (ELT), and the Thirty Meter Telescope (TMT) will be able to characterize the atmospheric composition and properties of these small planets. TESS will observe each 24 X 96 field of view for 30 days and thereby cover first the southern and then the northern hemisphere over 13 pointings during each year of the primary mission. The pole-most camera will observe the James Webb continuous viewing zone for one year in each hemisphere, permitting much longer period planets to be detected in this region. The PLATO mission will seek to detect habitable Earth-like planets with an instrument composed of 26 small telescopes in several 2232 square deg FOVs with a range of observation durations over a mission lifetime of up to eight years. This paper summarizes the findings of the KeplerK2 missions, previews the likely results from the TESS mission, and explores the lessons learned and to be learned from these prior missions that can be incorporated into the observation and data reduction strategy for the PLATO Mission so as to maximize the science return.

exoplanet detection↗
DOE OSTI2024

Cluster expansion by transfer learning for phase stability predictions

Recent progress towards universal machine-learned interatomic potentials holds considerable promise for materials discovery. Yet the accuracy of these potentials for predicting phase stability may still be limited. In contrast, cluster expansions provide accurate phase stability predictions but are computationally demanding to parameterize from first principles, especially for structures of low dimension or with a large number of components, such as interfaces or multimetal catalysts. We overcome this trade-off via transfer learning. Using Bayesian inference, we incorporate prior statistical knowledge from machine-learned and physics-based potentials, enabling us to sample the most informative configurations and to efficiently fit first-principles cluster expansions. Furthermore, this algorithm is tested on Pt:Ni, showing robust convergence of the mixing energies as a function of sample size with reduced statistical fluctuations.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Automated Electric Vehicle Fleet Operations for On-Demand Service: Challenges and Opportunities

Automated/autonomous vehicle fleet operations within automated mobility districts have been studied over the past five years by the National Renewable Energy Laboratory, a US Department of Energy federally funded research and development center. This paper extends the analysis in this third phase of research underway to include considerations for electric vehicle operations and charging within a fleet of right-sized automated vehicles providing on-demand public mobility services. The current focus of research is on the operational complexities and associated challenges for automated/autonomous vehicles employing electric drivetrains and the resultant need for an efficient battery charging process while vehicles are operating in an "on-demand" mode of service. The blossoming of microtransit with shared-ride and point-to-point dispatching of each vehicle instills complex operations, with multiple mobility-on-demand transit operating sites being deployed, studied, and analyzed across North America. As a starting point, the authors' experience over the past 20 years with the analysis of automated transit network systems operating on and within dedicated and protected transitways provides initial insights into the system-level operational implications for maintaining a sufficient battery charge for a fleet of automated vehicles. Lessons learned through the prior analyses of automated transit network systems operating in on-demand service are identified, along with the capital cost implications for the requisite operating fleet size and charging station infrastructure for various approaches. These costs are summarized in juxtaposition with the benefits of realizing the higher goals of reducing environmental impacts and energy use within automated mobility districts as automated/autonomous vehicle technology matures. Finally, the discussion addresses key aspects of battery-electric propulsion for managed fleets in fully automated operation that will be studied as the third phase of research continues.

ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Sensitive Detection of Structural Differences using a Statistical Framework for Comparative Crystallography

Chemical and conformational changes underlie the functional cycles of proteins. Comparative crystallography can reveal these changes over time, over ligands, and over chemical and physical perturbations in atomic detail. A key difficulty, however, is that the resulting observations must be placed on the same scale by correcting for experimental factors. We recently introduced a Bayesian framework for correcting (scaling) X-ray diffraction data by combining deep learning with statistical priors informed by crystallographic theory. To scale comparative crystallography data, we here combine this framework with a multivariate statistical theory of comparative crystallography. By doing so, we find strong improvements in the detection of protein dynamics, element-specific anomalous signal, and the binding of drug fragments.

Hekstra, Doeke R. [Harvard Univ., Cambridge, MA (U↗
DOE OSTI2021

Generative Patch Priors for Practical Compressive Image Recovery

In this work, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-level priors that are restricted to the range space of a pre-trained generator, GPP can recover a wide variety of natural images using a pre-trained patch generator. Additionally, GPP retains the benefits of generative priors like high reconstruction quality at extremely low sensing rates, while also being much more generally applicable. We show that GPP outperforms several unsupervised and supervised techniques on three different sensing models – linear compressive sensing with known, and unknown calibration settings, and the non-linear phase retrieval problem. Finally, we propose an alternating optimization strategy using GPP for joint calibration-and-reconstruction which performs favorably against several baselines on a real world, uncalibrated compressive sensing dataset. The code and models for GPP are available on github.

compressed sensing↗
DOE OSTI2022

Current Status of the DOE/NNSA Nuclear Criticality Safety Program Hands-on Criticality Safety Training Courses [Slides]

The NCSP training and education program has been conducted since 2011 and has trained over 591 students. 388 students have been trained in the 2-week hands-on course for practitioners and 203 students have been trained in the 1-week manager courses. The course is continuously improved using lessons-learned from the prior year, and new course content is added as necessary. Special courses are developed and offered periodically at the discretion of the NCSP manager. The updated manager course for CSOs was successfully piloted at NCERC in June 2020 and was successfully piloted at Sandia in April 2022. Students interested in taking the courses should visit the DOE NCSP website for additional information about all course offerings and for information about course registration.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

An Analysis of Published DAS Studies for Application to SPE Phase III

Distributed Acoustic Sensing (DAS) is an emerging technology capable of recording the acoustic wavefield at unprecedented spatial resolution. However, this new tool requires significant refinements before it becomes operational for explosion monitoring objectives. Recent studies have shown significant development of array processing with DAS data. In this report we explore three such array processing methods including DAS strain-rate data versus geophone measured ground motion, beamforming for event parameters, and machine learning based denoising. Prior to applying these algorithms to the Source Physics Experiment Phase II and Phase III data, we validate these methods through replication analysis.

47 OTHER INSTRUMENTATION↗