Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed training”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Deep learning models map rapid plant species changes from citizen science and remote sensing data

Anthropogenic habitat destruction and climate change are reshaping the geographic distribution of plants worldwide. However, we are still unable to map species shifts at high spatial, temporal, and taxonomic resolution. Here, we develop a deep learning model trained using remote sensing images from California paired with half a million citizen science observations that can map the distribution of over 2,000 plant species. Our model— Deepbiosphere— not only outperforms many common species distribution modeling approaches (AUC 0.95 vs. 0.88) but can map species at up to a few meters resolution and finely delineate plant communities with high accuracy, including the pristine and clear-cut forests of Redwood National Park. These fine-scale predictions can further be used to map the intensity of habitat fragmentation and sharp ecosystem transitions across human-altered landscapes. In addition, from frequent collections of remote sensing data, Deepbiosphere can detect the rapid effects of severe wildfire on plant community composition across a 2-y time period. These findings demonstrate that integrating public earth observations and citizen science with deep learning can pave the way toward automated systems for monitoring biodiversity change in real-time worldwide.

Gillespie, Lauren E.↗
DOE OSTI2022

Introduction to Special Section: Machine Learning for Image-based Geologic Interpretation

Image-based geological interpretation has been a labor-intensive and time-consuming process because it requires well-trained geoscientists to identify geological structures, features, and textures from various types of images. These images include scanning electron microscopic images, optical microscopic images, optical photos, resistivity images, seismic volumes, remote-sensing images, etc. With fast-evolving machine learning (ML) technology and computing power in recent decades, computers can achieve nearhuman-level to super-human-level performance with scalable high efficiency in the computer vision field. These technological revolutions facilitated image-based geological interpretation in petroleum exploration and production. For example, a fault picking method applied to 3-D seismic volume data using deep learning can achieve superior performance in comparison to conventional auto-picking methods. In addition, under the new normal of low oil prices, the petroleum industry seeks cost-effective strategies such as automating traditionally labor-intensive processes. Nevertheless, the potential of applying ML to geological image interpretation is still facing a few key challenges including data scarcity, data distribution, poor data and/or label quality, data leakage, learning algorithms, model architecture, training methodologies, testing and evaluation metrics, hyper-parameters optimization, model drift, production deployment, and the like.

58 GEOSCIENCES↗
DOE OSTI2021

ESPC ESA Training Series: Site-Specific/Stand-Alone Contract Vehicle

This webinar provides instructions and resources for financing distributed energy projects (e.g., on–site renewable energy, storage, and combined heat and power) using an energy savings performance contract (ESPC) energy sales agreement (ESA) through the site–specific/stand–alone contract vehicle. The site–specific/stand–alone contract vehicle is a procurement process using a request for proposal (RFP). Topics covered during the webinar include forming a strong project team, validating the feasibility of the distributed energy project at a site, acquisition planning, RFP development, procurement, proposal evaluation and contract award, and the construction and performance period. This webinar also provides an overview of the resources available in the ESPC ESA Toolkit, such as checklists and templates.

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

SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images

The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection with Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85% accuracy and +69.62% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All the code and models are availabe at: https://github.com/mvrl/SimLBR

Dhakal, Aayush [Washington University, St. Louis]↗
NASA NTRS2009

Estimating Transmitted-Signal Phase Variations for Uplink Array Antennas

A method of estimating phase drifts of microwave signals distributed to, and transmitted by, antennas in an array involves the use of the signals themselves as phase references. The method was conceived as part of the solution of the problem of maintaining precise phase calibration required for proper operation of an array of Deep Space Network (DSN) antennas on Earth used for communicating with distant spacecraft at frequencies between 7 and 8 GHz. The method could also be applied to purely terrestrial phased-array radar and other radio antenna array systems. In the DSN application, the electrical lengths (effective signal-propagation path lengths) of the various branches of the system for distributing the transmitted signals to the antennas are not precisely known, and they vary with time. The variations are attributable mostly to thermal expansion and contraction of fiber-optic and electrical signal cables and to a variety of causes associated with aging of signal-handling components. The variations are large enough to introduce large phase drifts at the signal frequency. It is necessary to measure and correct for these phase drifts in order to maintain phase calibration of the antennas. A prior method of measuring phase drifts involves the use of reference-frequency signals separate from the transmitted signals. A major impediment to accurate measurement of phase drifts over time by the prior method is the fact that although DSN reference-frequency sources separate from the transmitting signal sources are stable and accurate enough for most DSN purposes, they are not stable enough for use in maintaining phase calibrations, as required, to within a few degrees over times as long as days or possibly even weeks. By eliminating reliance on the reference-frequency subsystem, the present method overcomes this impediment. In a DSN array to which the present method applies (see figure), the microwave signals to be transmitted are generated by exciters in a signal-processing center, then distributed to the antennas via optical fibers. At each antenna, the signals are used to drive a microwave power-amplifier train, the output of which is coupled to the antenna for transmission. A small fraction of the power-amplifier-train output is sent back to the signal-processing center along another optical fiber that is part of the same fiber-optic cable used to distribute the transmitted signal to the antenna. In the signal-processing center, the signal thus returned from each antenna is detected and its phase is compared with the phase of the signal sampled directly from the corresponding exciter. It is known, from other measurements, that the signal-propagation path length from the power-amplifier-train output port to the phase center of each antenna is sufficiently stable and, hence, that sampling the signal at the power-amplifier-train output port suffices for the purpose of characterizing the phase drift of the transmitted signal at the phase center of the antenna

Paal, Leslie↗
NASA NTRS2005

Design of Gear Drives With High Gear Ratio

A three part paper to describe the results of several gear drive types with a high gear ratio is presented. A single stage planetary gear train with double helical gears is described with methods to reduce transmission errors and improve load distribution by regulating backlash during assembly. A new arrangement for face gear is also described. This new mechanism can perform rotations between axes that are collinear and intersected. Finally the design and simulation of an isostatic planetary gear train is presented. Conditions that can lead to noise and vibration of the planetary gear drive are described.

Litvin, Faydor L.↗
DOE OSTI2024

Bayesian analysis of (3 +1)⁢D relativistic nuclear dynamics with the RHIC beam energy scan data

This work presents a Bayesian inference study for relativistic heavy-ion collisions in the beam energy scan program at the BNL Relativistic Heavy-Ion Collider. The theoretical model simulates event-by-event (3+1)-dimensional [(3+1)⁢D] collision dynamics using hydrodynamics and hadronic transport theory. We analyze the model's 20-dimensional posterior distributions obtained using three model emulators with different accuracy and demonstrate the essential role of training an accurate model emulator in the Bayesian analysis. Our analysis provides robust constraints on the quark-gluon plasma's transport properties and various aspects of (3+1)⁢D relativistic nuclear dynamics. By running full model simulations with 100 parameter sets sampled from the posterior distribution, we make predictions for p T -differential observables and estimate their systematic theory uncertainty. Here, a sensitivity analysis is performed to elucidate how individual experimental observables respond to different model parameters, providing useful physics insights into the phenomenological model for heavy-ion collisions.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS2011

An Investigation of Interaction of Saharan Dust and Atlantic ITCZ Using Cloudsat-Calipso and A-Train Data

In this study, we investigate the radiative forcing of Saharan dust, its interactions with the Atlantic Intertropical Convergence Zone (ITCZ), through African easterly waves (AEW), African easterly jets (AEJ), and its impacts in short term numerical forecasts of tropical cyclogenesis using the GOCART-GEOS5 forecast system. Our approach is to develop and use an A-Train satellite simulator (ATSS) to constrain the observed aerosol index of refraction and particle size distribution by finding the values that simultaneously minimize the difference between observed CALIOP, CloudSat, OMI, and MODIS radiances and simulated radiances inverted from atmospheric model output using procedures and physical principles consistent with those used in corresponding retrieval algorithms. We use observations from the A-train and TRMM to determine relationships among the Saharan dust layer, transport by the AEW, and possible responses to dust radiative forcing in developing tropical cyclones in the A-ITCZ. Preliminary model results showing physical processes associated with the generation and transport of the Saharan dust layer, their interactions with the incipient moisture, clouds and rainfall in developing tropical cyclones will be presented. Also presented will be results of a case study of possible radiative impacts on AEW and AEJ during the NAMMA field campaign.

Lau, W.↗
NASA NTRS1989

Airline Crew Training

The discovery that human error has caused many more airline crashes than mechanical malfunctions led to an increased emphasis on teamwork and coordination in airline flight training programs. Human factors research at Ames Research Center has produced two crew training programs directed toward more effective operations. Cockpit Resource Management (CRM) defines areas like decision making, workload distribution, communication skills, etc. as essential in addressing human error problems. In 1979, a workshop led to the implementation of the CRM program by United Airlines, and later other airlines. In Line Oriented Flight Training (LOFT), crews fly missions in realistic simulators while instructors induce emergency situations requiring crew coordination. This is followed by a self critique. Ames Research Center continues its involvement with these programs.

Source record↗
NASA NTRS1993

Activity-induced regulation of myosin isoform distribution - Comparison of two contractile activity programs

This study examined the role of specific types of contractile activity in regulating myosin heavy chain (MHC) isoform expression in rodent soleus. A combination of hindlimb suspension (SN) and two programmed contractile training activity paradigms, either isometric contractile activity (ST-IM) or high-load slowly shortening isovelocity activity, were utilized. Both training paradigms increased muscle mass compared with SN alone. However, only ST-IM resulted in a partial prevention of the suspension-induced decrease in type I MHC. With the use of a fluorescently labeled antibody to type IIa MHC, the distribution of MHCs among fibers was examined immunohistochemically. In SN, the percentage of cells staining positive for type IIa MHC was increased but the staining intensity of the positively staining cells was unchanged compared with control cells. In the ST-IM soleus, the percentage of positively staining fibers was unchanged but the intensity of the positively staining cells was decreased compared with SN values. These results suggest that 1) isometric contractile activity is more effective than isovelocity activity in preventing suspension-induced shifts in soleus MHC distribution and 2) changes associated with both suspension and training occur in only a small number of fibers, with the majority of fibers apparently unresponsive to these interventions.

Diffee, Gary M.↗
DOE OSTI2023

Differentiable Earth mover’s distance for data compression at the high-luminosity LHC

Abstract The Earth mover’s distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms via gradient descent. In this paper, we train a convolutional neural network (CNN) to learn a differentiable, fast approximation of the EMD and demonstrate that it can be used as a substitute for computing-intensive EMD implementations. We apply this differentiable approximation in the training of an autoencoder-inspired neural network (encoder NN) for data compression at the high-luminosity LHC at CERN The goal of this encoder NN is to compress the data while preserving the information related to the distribution of energy deposits in particle detectors. We demonstrate that the performance of our encoder NN trained using the differentiable EMD CNN surpasses that of training with loss functions based on mean squared error.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2021

Mapping Global Forest Age from Forest Inventories, Biomass and Climate Data

Forest age can determine the capacity of a forest to uptake carbon from the atmosphere. However, a lack of global diagnostics that reflect the forest stage and associated disturbance regimes hampers the quantification of age-related differences in forest carbon dynamics. This study provides a new global distribution of forest age circa 2010, estimated using a machine learning approach trained with more than 40 000 plots using forest inventory, biomass and climate data. First, an evaluation against the plot-level measurements of forest age reveals that the data-driven method has a relatively good predictive capacity of classifying old-growth vs. non-old-growth (precision = 0.81 and 0.99 for old-growth and non-old-growth, respectively) forests and estimating corresponding forest age estimates (NSE = 0.6 – Nash–Sutcliffe efficiency – and RMSE = 50 years – root-mean-square error). However, there are systematic biases of overestimation in young- and underestimation in old-forest stands, respectively. Globally, we find a large variability in forest age with the old-growth forests in the tropical regions of Amazon and Congo, young forests in China, and intermediate stands in Europe. Furthermore, we find that the regions with high rates of deforestation or forest degradation (e.g. the arc of deforestation in the Amazon) are composed mainly of younger stands. Assessment of forest age in the climate space shows that the old forests are either in cold and dry regions or warm and wet regions, while young–intermediate forests span a large climatic gradient. Finally, comparing the presented forest age estimates with a series of regional products reveals differences rooted in different approaches and different in situ observations and global-scale products. Despite showing robustness in cross-validation results, additional methodological insights on further developments should as much as possible harmonize data across the different approaches. The forest age dataset presented here provides additional insights into the global distribution of forest age to better understand the global dynamics in the forest water and carbon cycles. The forest age datasets are openly available at https://doi.org/10.17871/ForestAgeBGI.2021 (Besnard et al., 2021).

Simon Besnard↗
DOE OSTI2025

A comparative analysis of YOLOv8 and U-Net image segmentation approaches for transmission electron micrographs of polycrystalline thin films

Metallic thin films offer a platform to experimentally study the dynamics of microstructural evolution, but the required transmission electron microscopy (TEM)-based imaging generates complex images that are challenging to segment and quantify. This work provides a comparative analysis of a new YOLOv8 model and an established U-Net model for bright-field TEM images of polycrystals, employing a framework leveraging physical observables to evaluate performance against two hand-traced benchmark datasets. This methodology obviates the comparison of large, diversely structured, and manually labeled datasets that are required to assess performance on a per-image/per-pixel basis. It is found that the YOLOv8 model, adapted for real-time instance segmentation, has up to 43× faster inferencing (NVIDIA GeForce RTX 4090) compared to U-Net and reconstructs hand-traced grain size distributions (GSDs) with excellent fidelity, finding mean diameter within 3% for grains near an optimal magnification; for grains that deviate from the optimal pixel-diameter, the size of small- (large)-diameter grains is systematically over- (under)-estimated. This is partially mitigated by including scale-aware augmentations during training. Moreover, when the bias is corrected post-inference by a rigid shift in distribution, the YOLOv8 model reproduces ground truth GSDs with exceptional fidelity, with statistical tests indicating <5% probability that the distributions are distinct. Based on ground truth data, calibration curves pertaining to this shift can be constructed for a given model. This issue is not present in the U-Net model’s results, indicating that for quantitative measurements where the true size of objects is of interest, special procedures must be implemented for YOLO-based models.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Deep Learning At Depth: Estimating subsurface parameters from geophysical monitoring data

Geophysical imaging techniques are a non-invasive way to image the subsurface and understand both subsurface solid (rock/soil) and fluid property distributions and their evolution in time. Inversions of the geophysical data, such as Electrical Resistance Tomography (ERT) data, are solved to estimate the subsurface property distributions, such as conductivity, and many inversion techniques smooth out sharp gradients in rock or fluid property distributions. Sharp gradients in subsurface properties tend to be present in situations with complex subsurface structures, which are common in many subsurface applications. We have successfully demonstrated that it is possible to inform, or constrain, inversions with neural networks trained on synthetic data with complex subsurface structures. Initial results suggest this process may be optimizable to yield property distributions that better represent the true property distributions than the same inversion process without the neural network constraint. Future work would optimize the neural network performance for this application and then apply the synthetic-data trained neural network to real data to understand the utility and performance of this technique for real data sets.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Convex Q-Learning in Continuous Time with Application to Dispatch of Distributed Energy Resources

Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure. This paper explores algorithm design in the continuous time domain, with a finite-horizon optimal control objective. The main contributions are (i) The new Q-ODE: a model-free characterization of the Hamilton-Jacobi-Bellman equation. (ii) A formulation of Convex Q-learning that avoids approximations appearing in prior work. The Bellman error used in the algorithm is defined by filtered measurements, which is necessary in the presence of measurement noise. (iii) Convex Q-learning with linear function approximation is a convex program. It is shown that the constraint region is bounded, subject to an exploration condition on the training input. (iv) The theory is illustrated in application to resource allocation for distributed energy resources, for which the theory is ideally suited.

Lu, Fan↗
NASA NTRS1993

A petabyte size electronic library using the N-Gram memory engine

A model library containing petabytes of data is proposed by Triada, Ltd., Ann Arbor, Michigan. The library uses the newly patented N-Gram Memory Engine (Neurex), for storage, compression, and retrieval. Neurex splits data into two parts: a hierarchical network of associative memories that store 'information' from data and a permutation operator that preserves sequence. Neurex is expected to offer four advantages in mass storage systems. Neurex representations are dense, fully reversible, hence less expensive to store. Neurex becomes exponentially more stable with increasing data flow; thus its contents and the inverting algorithm may be mass produced for low cost distribution. Only a small permutation operator would be recalled from the library to recover data. Neurex may be enhanced to recall patterns using a partial pattern. Neurex nodes are measures of their pattern. Researchers might use nodes in statistical models to avoid costly sorting and counting procedures. Neurex subsumes a theory of learning and memory that the author believes extends information theory. Its first axiom is a symmetry principle: learning creates memory and memory evidences learning. The theory treats an information store that evolves from a null state to stationarity. A Neurex extracts information data without a priori knowledge; i.e., unlike neural networks, neither feedback nor training is required. The model consists of an energetically conservative field of uniformly distributed events with variable spatial and temporal scale, and an observer walking randomly through this field. A bank of band limited transducers (an 'eye'), each transducer in a bank being tuned to a sub-band, outputs signals upon registering events. Output signals are 'observed' by another transducer bank (a mid-brain), except the band limit of the second bank is narrower than the band limit of the first bank. The banks are arrayed as n 'levels' or 'time domains, td.' The banks are the hierarchical network (a cortex) and transducers are (associative) memories. A model Neurex was built and studied. Data were 50 MB to 10 GB samples of text, data base, and images: black/white, grey scale, and high resolution in several spectral bands. Memories at td, S(m(sub td)), were plotted against outputs of memories at td-1. S(m(sub td)) was Boltzman distributed, and memory frequencies exhibited self-organized criticality (SOC); i.e., 'l/f(sup beta)' after long exposures to data. Whereas output signals from level n may be encoded with B(sub output) = O(-log(2)f(sup beta)) bits, and input data encoded with B(sub input) = O((S(td)/S(td-1))(sup n)), B(sup output)/B(sub input) is much less than 1 always, the Neurex determines a canonical code for data and it is a lossless data compressor. Further tests are underway to confirm these results with more data types and larger samples.

Bugajski, Joseph M.↗
DOE OSTI2024

The use of digital thread for reconstruction of local fiber orientation in a compression molded pin bracket via deep learning

A deep convolutional neural network (DCNN) was used for microstructure reconstruction using artificial intelligence (MR-AI) by predicting local average fiber orientation distributions (FOD) in a 3D prepreg platelet molded composite (PPMC) pin bracket. To train the MR-AI model, surface strain fields from residual stresses simulated in PPMC plates were used as the input to the DCNN. A training dataset included PPMC plates with various degrees of global fiber alignment, based on the information obtained from high-fidelity flow simulation of a pin bracket. Further, the MR-AI model was then deployed to analyze FOD in the 3D pin bracket by conducting thermo-elastic residual stress analysis. Initially, the MR-AI model was established entirely on the synthetic simulation data. Then, a μCT scan of a physically molded pin bracket was used to create a finite element model that provided data for additional validation of the DCNN model. For the μCT scan finite element pin bracket the MR-AI model predicted the distribution of fiber orientation tensor components with MAE of 0.10 indicating a global prediction error of 10%. For the flow simulated pin bracket, the MR-AI model predicted the distribution of fiber orientation tensor components with a global prediction error of 11%. The MR-AI model showed the ability to predict regions of varying alignment in the base and flange of the pin bracket. The proposed MR-AI methodology allows for rapid prediction of FOD in geometrically complex parts and offers a promising path to detecting unique fiber orientation states in molded components.

42 ENGINEERING↗
DOE OSTI2025

Solving high-dimensional inverse problems using amortized likelihood-free inference with noisy and incomplete data

Here, we present a likelihood-free probabilistic inversion method based on normalizing flows for high-dimensional inverse problems. The proposed method is composed of two complementary networks: a summary network for data compression and an inference network for parameter estimation. The summary network encodes raw observations into a fixed-size vector of summary features, while the inference network generates samples of the approximate posterior distribution of the model parameters based on these summary features. The posterior samples are produced in a deep generative fashion by sampling from a latent Gaussian distribution and passing these samples through an invertible transformation. We construct this invertible transformation by sequentially alternating conditional invertible neural network and conditional neural spline flow layers. The summary and inference networks are trained simultaneously. We apply the proposed method to an inversion problem in groundwater hydrology to estimate the posterior distribution of the log-conductivity field conditioned on spatially sparse time-series observations of the system’s hydraulic head responses. The conductivity field is represented with 706 degrees of freedom in the considered problem. Comparison with the likelihood-based iterative ensemble smoother PEST-IES method demonstrates that the proposed method accurately estimates the parameter posterior distribution and the observations’ predictive posterior distribution at a fraction of the inference time of PEST-IES.

conditional invertible neural network↗