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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Sensitive detection of structural dynamics using a statistical framework for comparative crystallography

Chemical and conformational changes are crucial to protein function and its pharmacological control. X-ray crystallography can reveal these changes in atomic detail, but standard analysis methods, which refine separate datasets, often overlook differences that are subtle or arise in only a subset of molecules. Direct comparison of crystallographic datasets is, in principle, more powerful, but systematic errors (“scales”) often mask changes in the crystallographic observables (“structure factors”). Machine learning algorithms that jointly estimate scales and structure factors can address this limitation. Here, we augment this approach with multivariate, structured priors derived from crystallographic theory, implemented in the variational deep learning framework Careless. Doing so strongly improves the detection of protein dynamics, element-specific anomalous signals, and the binding of drug candidates, offering a robust approach to comparative crystallography and, potentially, to detection of protein dynamics by other structure determination methods.

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

Neuroevolutionary Learning of Particles and Protocols for Self-Assembly

Within simulations of molecules deposited on a surface we show that neuroevolutionary learning can design particles and time-dependent protocols to promote self-assembly, without input from physical concepts such as thermal equilibrium or mechanical stability and without prior knowledge of candidate or competing structures. Furthermore, the learning algorithm is capable of both directed and exploratory design: it can assemble a material with a user-defined property, or search for novelty in the space of specified order parameters. In the latter mode it explores the space of what can be made, rather than the space of structures that are low in energy but not necessarily kinetically accessible.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2021

Latent map Gaussian processes for mixed variable metamodeling

Gaussian processes (GPs) are ubiquitously used in sciences and engineering as metamodels. Standard GPs, however, can only handle numerical or quantitative variables. Here we introduce latent map Gaussian processes (LMGPs) that inherit the attractive properties of GPs and are also applicable to mixed data which have both quantitative and qualitative inputs. The core idea behind LMGPs is to learn a continuous, low-dimensional latent space or manifold which encodes all qualitative inputs. To learn this manifold, we first assign a unique prior vector representation to each combination of qualitative inputs. We then use a low-rank linear map to project these priors on a manifold that characterizes the posterior representations. As the posteriors are quantitative, they can be directly used in any standard correlation function such as the Gaussian or Matern. Hence, the optimal map and the corresponding manifold, along with other hyperparameters of the correlation function, can be systematically learned via maximum likelihood estimation. Through a wide range of analytic and real-world examples, we demonstrate the advantages of LMGPs over state-of-the-art methods in terms of accuracy and versatility. In particular, we show that LMGPs can handle variable-length inputs, have an explainable neural network interpretation, and provide insights into how qualitative inputs affect the response or interact with each other. We also employ LMGPs in Bayesian optimization and illustrate that they can discover optimal compound compositions more efficiently than conventional methods that convert compositions to qualitative variables via manual featurization.

42 ENGINEERING↗
DOE OSTI2021

Machine Learning Predictions of Transition Probabilities in Atomic Spectra

Forward modeling of optical spectra with absolute radiometric intensities requires knowledge of the individual transition probabilities for every transition in the spectrum. In many cases, these transition probabilities, or Einstein A-coefficients, quickly become practically impossible to obtain through either theoretical or experimental methods. Complicated electronic orbitals with higher order effects will reduce the accuracy of theoretical models. Experimental measurements can be prohibitively expensive and are rarely comprehensive due to physical constraints and sheer volume of required measurements. Due to these limitations, spectral predictions for many element transitions are not attainable. In this work, we investigate the efficacy of using machine learning models, specifically fully connected neural networks (FCNN), to predict Einstein A-coefficients using data from the NIST Atomic Spectra Database. For simple elements where closed form quantum calculations are possible, the data-driven modeling workflow performs well but can still have lower precision than theoretical calculations. For more complicated nuclei, deep learning emerged more comparable to theoretical predictions, such as Hartree–Fock. Unlike experiment or theory, the deep learning approach scales favorably with the number of transitions in a spectrum, especially if the transition probabilities are distributed across a wide range of values. It is also capable of being trained on both theoretical and experimental values simultaneously. In addition, the model performance improves when training on multiple elements prior to testing. The scalability of the machine learning approach makes it a potentially promising technique for estimating transition probabilities in previously inaccessible regions of the spectral and thermal domains on a significantly reduced timeline.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2026

Exploring the Outer Heliosphere Through ENA Observations from IMAP

The Interstellar Mapping and Acceleration Probe (IMAP) mission is poised to revolutionize our understanding of two of the most central issues in heliophysics today: the nature of the interaction of the solar wind with the local interstellar medium (LISM), and the acceleration of energetic particles throughout the heliosphere. Here we focus on the anticipated contributions to this endeavor by measurement of hydrogen energetic neutral atoms (ENAs) that emanate from the solar wind–LISM interface region. ENA imaging allows us to remotely sense the structure and plasma characteristics of the heliosheath and the LISM just beyond the heliopause, and how these regions evolve in response to solar activity. These instruments, IMAP-Lo, IMAP-Hi, and IMAP-Ultra, cover energies from 10 eV to 300 keV with unprecedented angular resolution, energy resolution, and detection sensitivity. In this paper, we present the IMAP mission science specific to the study of the heliosphere/LISM interaction. We review what we have learned about the heliosphere interaction based on prior observations and theoretical studies. We then present the outstanding science questions that have consequently arisen and how IMAP plans to resolve them.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

The Illumination of Thunderclouds by Lightning: 4. Volumetric Thunderstorm Imagery

Optical instruments such as the Geostationary Lightning Mapper (GLM) detect lightning based on transient changes in cloud illumination. The horizontal location of lightning is determined from the coordinates of the pixels on the imaging array illuminated during the flash. However, the vertical position of the lightning pulses (approximated by GLM “groups”) below the cloud top cannot be routinely measured from a single space-based instrument. In our prior work, we have developed a machine learning algorithm that can infer optical source altitude for a given pulse based on how the optical energy is distributed across the group footprint and the local Advanced Baseline Imager Cloud-Top Height (CTH). In this fourth part of our thundercloud illumination study, we leverage these source altitudes to generate volumetric GLM imagery of a Colombia thunderstorm. We find that 3D versions of the current GLM meteorological imagery products (that describe thunderstorm kinematics) and thundercloud imagery products (that depict how the flashes appear from space) provide additional insights into lightning activity in the thunderstorm that are lost in the vertical integration used to generate the current 2D GLM gridded products. This new volumetric imaging capability provides a more comprehensive picture of where lightning occurs in the storm, how its physical characteristics vary across three-dimensional space, and how its optical emissions interact with surrounding the cloud medium.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Fast predictions of liquid-phase acid-catalyzed reaction rates using molecular dynamics simulations and convolutional neural networks

The rates of liquid-phase, acid-catalyzed reactions relevant to the upgrading of biomass into high-value chemicals are highly sensitive to solvent composition and identifying suitable solvent mixtures is theoretically and experimentally challenging. We show that the complex atomistic configurations of reactant–solvent environments generated by classical molecular dynamics simulations can be exploited by 3D convolutional neural networks to enable accurate predictions of Brønsted acid-catalyzed reaction rates for model biomass compounds. We develop a 3D convolutional neural network, which we call SolventNet, and train it to predict acid-catalyzed reaction rates using experimental reaction data and corresponding molecular dynamics simulation data for seven biomass-derived oxygenates in water–cosolvent mixtures. We show that SolventNet can predict reaction rates for additional reactants and solvent systems an order of magnitude faster than prior simulation methods. This combination of machine learning with molecular dynamics enables the rapid, high-throughput screening of solvent systems and identification of improved biomass conversion conditions.

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

Odor exposure during imprinting periods increases odorant-specific sensitivity and receptor gene expression in coho salmon ( Oncorhynchus kisutch )

ABSTRACT Pacific salmon are well known for their homing migrations; juvenile salmon learn odors associated with their natal streams prior to seaward migration, and then use these retained odor memories to guide them back from oceanic feeding grounds to their river of origin to spawn several years later. This memory formation, termed olfactory imprinting, involves (at least in part) sensitization of the peripheral olfactory epithelium to specific odorants. We hypothesized that this change in peripheral sensitivity is due to exposure-dependent increases in the expression of odorant receptor (OR) proteins that are activated by specific odorants experienced during imprinting. To test this hypothesis, we exposed juvenile coho salmon, Oncorhynchus kisutch, to the basic amino acid odorant l-arginine during the parr–smolt transformation (PST), when imprinting occurs, and assessed sensitivity of the olfactory epithelium to this and other odorants. We then identified the coho salmon ortholog of a basic amino acid odorant receptor (BAAR) and determined the mRNA expression levels of this receptor and other transcripts representing different classes of OR families. Exposure to l-arginine during the PST resulted in increased sensitivity to that odorant and a specific increase in BAAR mRNA expression in the olfactory epithelium relative to other ORs. These results suggest that specific increases in ORs activated during imprinting may be an important component of home stream memory formation and this phenomenon may ultimately be useful as a marker of successful imprinting to assess management strategies and hatchery practices that may influence straying in salmon.

Dittman, Andrew H. (ORCID:000000016482359X)↗
DOE OSTI2025

The BTSbot-nearby Discovery of SN 2024jlf: Rapid, Autonomous Follow-up Probes Interaction in an 18.5 Mpc Type IIP Supernova

We present observations of the Type IIP supernova (SN) SN 2024jlf, including spectroscopy beginning just 0.7 days (∼17 hr) after first light. Rapid follow-up was enabled by the new BTSbot-nearby program, which involves autonomously triggering target-of-opportunity requests for new transients in Zwicky Transient Facility data that are coincident with nearby (D < 60 Mpc) galaxies and identified by the BTSbot machine learning model. Early photometry and nondetections shortly prior to first light show that SN 2024jlf initially brightened by >4 mag day −1 , quicker than ∼90% of Type II SNe. Early spectra reveal weak flash ionization features: narrow, short-lived (1.3 < τ[days] < 1.8) emission lines of Hα, He II , and C IV . Assuming a wind velocity of v w = 50 km s −1 , these properties indicate that the red supergiant progenitor exhibited enhanced mass loss in the last year before explosion. We constrain the mass-loss rate to $1{0}^{-4}\lt \dot{M}\,[{M}_{\odot }\,{\mathrm{yr}}^{-1}]\lt 1{0}^{-3}$ by matching observations to model grids from two independent radiative hydrodynamics codes. BTSbot-nearby automation minimizes spectroscopic follow-up latency, enabling the observation of ephemeral early-time phenomena exhibited by transients.

core-collapse supernovae↗
DOE OSTI2020

The connectome of the adult Drosophila mushroom body provides insights into function

Making inferences about the computations performed by neuronal circuits from synapse-level connectivity maps is an emerging opportunity in neuroscience. The mushroom body (MB) is well positioned for developing and testing such an approach due to its conserved neuronal architecture, recently completed dense connectome, and extensive prior experimental studies of its roles in learning, memory, and activity regulation. Here, we identify new components of the MB circuit in Drosophila , including extensive visual input and MB output neurons (MBONs) with direct connections to descending neurons. We find unexpected structure in sensory inputs, in the transfer of information about different sensory modalities to MBONs, and in the modulation of that transfer by dopaminergic neurons (DANs). We provide insights into the circuitry used to integrate MB outputs, connectivity between the MB and the central complex and inputs to DANs, including feedback from MBONs. Our results provide a foundation for further theoretical and experimental work.

Li, Feng↗
NASA NTRS2008

Optimizing Requirements Decisions with KEYS

Recent work with NASA's Jet Propulsion Laboratory has allowed for external access to five of JPL's real-world requirements models, anonymized to conceal proprietary information, but retaining their computational nature. Experimentation with these models, reported herein, demonstrates a dramatic speedup in the computations performed on them. These models have a well defined goal: select mitigations that retire risks which, in turn, increases the number of attainable requirements. Such a non-linear optimization is a well-studied problem. However identification of not only (a) the optimal solution(s) but also (b) the key factors leading to them is less well studied. Our technique, called KEYS, shows a rapid way of simultaneously identifying the solutions and their key factors. KEYS improves on prior work by several orders of magnitude. Prior experiments with simulated annealing or treatment learning took tens of minutes to hours to terminate. KEYS runs much faster than that; e.g for one model, KEYS ran 13,000 times faster than treatment learning (40 minutes versus 0.18 seconds). Processing these JPL models is a non-linear optimization problem: the fewest mitigations must be selected while achieving the most requirements. Non-linear optimization is a well studied problem. With this paper, we challenge other members of the PROMISE community to improve on our results with other techniques.

requirements↗
NASA NTRS2012

JPL Innovation Foundry

NASA supports the community of mission principal investigators by helping them ideate, mature, and propose concepts for new missions. As NASA's Federally Funded Research and Development Center (FFRDC), JPL is a primary resource for providing this service. The environmental context for the formulation lifecycle evolves continuously. Contemporary trends include: more competitors; more-complex mission ideas; scarcer formulation resources; and higher standards for technical evaluation. Derived requirements for formulation support include: stable, clear, reliable methods tailored for each stage of the formulation lifecycle; on-demand access to standout technical and programmatic subject-matter experts; optimized, outfitted facilities; smart access to learning embodied in a vast oeuvre of prior formulation work; hands-on method coaching. JPL has retooled its provision of integrated formulation lifecycle support to PIs, teams, and program offices in response to this need. This mission formulation enterprise is the JPL Innovation Foundry.

foundry↗
DOE OSTI2024

Experimental Verification of Integrability in a Danilov-Nagaitsev Lattice using Machine Learning

In non-linear optics, achieving integrability can enhance the dynamic aperture in storage rings. We analyze turn-by-turn phase-space data from our Danilov-Nagaitsev lattice implementation at Fermilab's Integrable Optics Test Accelerator using machine learning. \textit{AI Poincar\'e} estimates conserved quantities from experimental data without prior knowledge of the invariant structure, showing qualitative agreement with theoretical predictions. Additionally, one of the two learned invariants exhibits comparable or better conservation compared to known theoretical expressions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS2008

Effects of Learning on Performance When Computerized Dynamic Posturography Assessments Are Repeated

Background: Computerized dynamic posturography is widely used to measure balance control performance. Clinically, performance is assessed by comparing individual data against standards obtained from a normative population. When performing repeated assessments to track performance changes, one must be concerned with the influence of learning effects. Subjects do not have the opportunity to practice before the first session, and often a second session is not performed prior to an experiment. Thus, the objective of this activity was to examine learning effects on balance control performance. We hypothesize that subjects will perform better on the second session when compared to the first, and that the difference will be greater for more difficult conditions. Methods: Data were collected from 204 subjects using the NeuroCom Equitest system during quiet stance with arms crossed at the chest on up to two sessions. All subjects performed standard sensory organization tests (SOTs) including 1) normal vision, fixed support; 2) absent vision, fixed support; 3) sway-referenced vision, fixed support; 4) normal vision, swayreferenced support; 5) absent vision, sway-referenced support; and 6) sway-referenced vision, sway-referenced support. 120 of these subjects performed modified sensory organization tests (mSOTs 2 and 5) which included static (20 back) and dynamic (20, 0.33Hz) head tilts. Median equilibrium scores (mEQ) were calculated from peak-to-peak anterior-posterior sway across trials. Data collected on the first session were then compared with the second to examine learning effect. Results: There were no differences in mEQ scores between the first and second sessions for SOTs 1, 2, and 4, while mEQ scores were higher for the second session when compared to the first for SOTs 3, 5, and 6 and for all mSOTs. Discussion: An additional familiarization session or practice trials prior to the first session may be necessary for more challenging SOT and mSOT conditions to minimize learning effect.

Taylor, Laura C.↗
NASA NTRS2019

Air Traffic Management Technology Demonstration-1 (ATD-1) Avionics Phase 2 Flight Test Training for Interval Management

Prior to the successful flight test validation of a new avionics prototype, participants from Boeing, Honeywell, and United Airlines underwent group training at NASA Langley Research Center. New prototype software for an algorithm which enables greater efficiency in high-density airspace, called Interval Management, was to be incorporated into Electronic Flight Bags and placed in the cockpit for pilot usage. The goals of the training were to teach the flight test pilots how to operate the new software, establish techniques to simultaneously position three aircraft prior to each test scenario, and ensure a common communication protocol among team members when coordinating the position of aircraft for the next scenario. The multi-tiered interactive training regimen consisted of a process that continually built upon previous foundational material. The primary learning elements were 1) a portable computer-based trainer that was provided to the pilots prior to classroom training sessions, 2) classroom learning, 3) full mock-up simulator training, and 4) refresher training just prior to the flight test. Each part of the regimen was designed to repeat and build upon the previous element. The purpose of this Technical Memorandum is to inform the aviation industry how flight training for Interval Management was conducted at Langley Research Center in order to reduce overall development costs of future Interval Management training programs. Secondly, the paper provides insight regarding the decision-making process when attempting to conduct a flight test.

Roper, Roy D.↗
NASA NTRS2006

Constellation Operations: Lessons Learned For Future Exploration

The Earth science community has long advocated placing numerous instruments in space to study the Earth and its environment. Space agencies from many countries have responded to this call with a wide range of orbiting satellites. Scientists also envisioned placing some satellites in constellations, to enable diverse remote sensing instruments to observe the same part of the Earth (or its atmosphere) at about the same time, thereby increasing the opportunities for coincident science observations. The Earth Science Afternoon Constellation is answering this call, but there have been unique challenges on the way to its deployment. Currently, the Afternoon Constellation is to comprise six satellites. Three are currently on orbit: NASA's Earth Observing System (EOS)-Aqua (2002) and EOS-Aura (2004), and CNES's Polarization & Anisotropy of Reflectances for Atmospheric Sciences coupled with Observations from a Lidar (PARASOL) (2004). Two more satellites, the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) and Cloudsat, are to be jointly launched in late 2005, followed by the Orbiting Carbon Observatory (OCO) in 2008. The Afternoon Constellation is unlike most satellite constellations in that: 1) It is not a homogenous mix of identical satellites; rather it comprises several satellites with complementary observational capabilities; 2) The satellites are not spaced around the Earth to provide instantaneous, global coverage (as for a communications satellite constellation); rather they orbit in close proximity so observations occur at about the same time over approximately the same region; and 3) Lastly, the satellites are not managed and controlled by one organization; rather the list of organizations is diverse: CNES in France, NASA Centers at Goddard, Langley, and the Jet Propulsion Laboratory, and the US Air Force facility in New Mexico. The PARASOL launch and early orbit (L&EO) phase proved to be a learning experience for constellation members (including Constellation management). Prior to launch, all members signed an operations coordination document that spelled out basic requirements for keeping the constellation safe and resolving non-nominal events. Once PARASOL reached orbit and the mission teams gained experience using the newly-developed constellation monitoring tools, it became clear that some of the guidelines in the signed agreements had to be adjusted. This paper presents the L&EO lessons learned and how they were used to prepare for the next phase - the period following the CloudSat/CALIPSO launch.

Kelly, Angelita C.↗
DOE OSTI2020

The importance of round-robin validation when assessing machine-learning-based vertical extrapolation of wind speeds

The extrapolation of wind speeds measured at a meteorological mast to wind turbine rotor heights is a key component in a bankable wind farm energy assessment and a significant source of uncertainty. Industry-standard methods for extrapolation include the power-law and logarithmic profiles. The emergence of machine-learning applications in wind energy has led to several studies demonstrating substantial improvements in vertical extrapolation accuracy in machine-learning methods over these conventional power-law and logarithmic profile methods. In all cases, these studies assess relative model performance at a measurement site where, critically, the machine-learning algorithm requires knowledge of the rotor-height wind speeds in order to train the model. This prior knowledge provides fundamental advantages to the site-specific machine-learning model over the power-law and log profiles, which, by contrast, are not highly tuned to rotor-height measurements but rather can generalize to any site. Furthermore, there is no practical benefit in applying a machine-learning model at a site where winds at the heights relevant for wind energy production are known; rather, its performance at nearby locations (i.e., across a wind farm site) without rotor-height measurements is of most practical interest. To more fairly and practically compare machine-learning-based extrapolation to standard approaches, we implemented a round-robin extrapolation model comparison, in which a random-forest machine-learning model is trained and evaluated at different sites and then compared against the power-law and logarithmic profiles. We consider 20 months of lidar and sonic anemometer data collected at four sites between 50 and 100 km apart in the central United States. We find that the random forest outperforms the standard extrapolation approaches, especially when incorporating surface measurements as inputs to include the influence of atmospheric stability. When compared at a single site (the traditional comparison approach), the machine-learning improvement in mean absolute error was 28 % and 23 % over the power-law and logarithmic profiles, respectively. Using the round-robin approach proposed here, this improvement drops to 20 % and 14 %, respectively. These latter values better represent practical model performance, and we conclude that round-robin validation should be the standard for machine-learning-based wind speed extrapolation methods.

17 WIND ENERGY↗