SEARCH · Search NASA

Results for “neural network 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Reconstruction and Selection of Neutrino Interactions in MicroBooNE using Deep Convolutional Neural Networks

In this document, we describe a new reconstruction workflow developed for the MicroBooNE experiment. It features the use of Deep Convolutional Neural Networks trained to recognize key structures within the data sufficient for the 3D reconstruction of neutrino interactions within the detector. As a test of the reconstruction utility, the products of the reconstruction workflow are used to select inclusive charged-current (CC) $\nu_e$ and $\nu_\mu$ interactions in both simulated and real MicroBooNE data. In simulation, our $\nu_e$ and $\nu_\mu$ selections achieve an efficiency of 57% and 68\%, respectively, with a purity of 91% and 96%, respectively. We find that these selections are competitive with the inclusive selections used for the most recent MicroBooNE LEE searches. In particular, the CC-$\nu_e$ inclusive selection efficiency improves by over 20% while also improving sample purity. As a first step in quantifying potential bias, the data and Monte Carlo expectati ons are compared for both selections using the MicroBooNE open data. Within statistical and systematic uncertainties, both the electron and muon CC-inclusive event samples agree. A comparison of the real data events chosen by our work and another reconstruction framework shows that the two analyses each identify a sizeable fraction of events the other does not. This suggests that future analyses integrating the strengths of each could lead to combined gains. This work demonstrates, for the first time on real LArTPC data, state-of-the-art neutrino interaction reconstruction centered around deep learning algorithms.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Refining Fast Simulation Using Machine Learning

A growing reliance on the fast Monte Carlo (FastSim) will accompany the high luminosity and detector granularity expected in Phase 2. FastSim is roughly 10 times faster than equivalent GEANT4-based full simulation (FullSim). However, reduced accuracy of the FastSim affects some analysis variables and collections. To improve its accuracy, FastSim is refined using regression-based neural networks trained with ML. The status of FastSim refinement is presented. The results show improved agreement with the FullSim output and an improvement in correlations among output observables and external parameters.

Güngördü, Acelya Deniz↗

DOE OSTI2024

Open Call LDRD: Physically Informed Autoencoders for Galactic Redshift Regression

Physical constraints have been suggested to make neural network models more generalizable, act scientifically plausible, and be more data-efficient over unconstrained baselines. In this report, we present preliminary work on evaluating the effects of adding soft physical constraints to computer vision neural networks trained to estimate the conditional density of redshift on input galaxy images for the Sloan Digital Sky Survey. We introduce physically motivated soft constraint terms that are not implemented with differential or integral operators. We frame this work as a simple ablation study where the effect of including soft physical constraints is compared to an unconstrained baseline. We compare networks using standard point estimate metrics for photometric redshift estimation, as well as metrics to evaluate how faithful our conditional density estimate represents the probability over the ensemble of our test dataset. We find no evidence that the implemented soft physical constraints are more effective regularizers than augmentation.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Intracardiac Electrical Imaging using the 12-lead ECG: A Machine Learning Approach using Synthetic Data

Current state-of-the-art techniques for non-invasive imaging of cardiac electrical phenomena require voltage recordings from dozens of different torso locations and anatomical models built from expensive medical diagnostic imaging procedures. Here this study aimed to assess if recent machine learning advances could alternatively reconstruct electroanatomical maps at clinically relevant resolutions using only the standard 12-lead electrocardiogram (ECG) as input. To that end, a computational study was conducted to generate a dataset of over 16000 detailed cardiac simulations, which was then used to train neural network (NN) architectures designed to exploit both spatial and temporal correlations in the ECG signal. Analysis over a validation set showed average errors in activation map reconstruction below 1.7 msec over 75 intracardiac locations. Furthermore, phenotypical patterns of activation and the morphology of the activation potential were correctly reconstructed. The approach offers opportunities to stratify patients non-invasively, both retrospectively and prospectively, using metrics otherwise only available through invasive clinical procedures.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Methods and Comparisons Between Computer Vision and Radar Based Vehicle Location

Measuring vehicle locations relative to a driver's vehicle is a critical component in the analysis of driving data from both postanalysis (such as in naturalistic driving studies) or in autonomous vehicle navigation. In this work we describe a method to estimate vehicle positions from a forward-looking video camera using intrinsic camera calibration, estimates of extrinsic parameters, and a convolutional neural network trained to detect and locate vehicles in video data. We compare the measurements we achieve with this method with ground truth and with radar data available from a naturalistic driving study. We identify regions where video is preferred, where radar is preferred, and explore trade-offs between the two methods in regions where the preference is more ambiguous. We describe applications of these measurements for transportation analysis.

Aykac, Deniz↗

DOE OSTI2024

A Full-Stack Exploration of Language-Based Parallelism in Fortran 2023

This poster explores native parallel features in Fortran 2023 through the lens of supporting applications with libraries, compilers, and parallel runtimes. The language revision informally named Fortran 2008 introduced parallelism in the form of Single Program Multiple Data (SPMD) execution with two broad feature sets: (1) loop-level parallelism via do concurrent and (2) a Partitioned Global Address Space (PGAS) comprised of distributed “coarray” data structures. Fortran’s native parallelism has demonstrated high performance [1] and reduced the burden of inserting what sometimes amounts to more directives than code. Several compilers support both feature sets, typically by translating do concurrent into serial do loops annotated by parallel directives and by translating SPMD/PGAS features into direct calls to a communication library. Our research focuses primarily on two questions: (1) can the compiler’s parallel runtime library be developed in the language being compiled (Fortran) and (2) can we define an interface to the runtime that liberates compilers from being hardwired to one runtime and vice versa. We are answering these questions by developing the Parallel Runtime Interface for Fortran (PRIF) [2] and the Co-Array Fortran Framework of Efficient Interfaces to Network Environments (Caffeine) [3]. Caffeine is initially targeting adoption by LLVM Flang, a new open-source Fortran compiler developed by a broad community in industry, academia, and government labs. We are also exploring the use of these features in Inference-Engine, a deep learning library designed to facilitate neural network training and inference for high-performance computing applications written in modern Fortran.

Rasmussen, Katherine↗

DOE OSTI2022

Integrating Deep Learning and Hydrodynamic Modeling to Improve the Great Lakes Forecast

The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, trained with the limited data from hypothetical monitoring networks, can provide consistent and robust performance. The LSTM prediction captured the LST spatiotemporal variabilities across the five Great Lakes well, suggesting an effective and efficient way for monitoring network design in assisting the ML-based forecast. Furthermore, we employed an explainable artificial intelligence (XAI) technique named SHapley Additive exPlanations (SHAP) to uncover how the features impact the LSTM prediction. Our XAI analysis shows air temperature is the most influential feature for predicting LST in the trained LSTM. The relatively large bias in the LSTM prediction during the spring and fall was associated with substantial heterogeneity of air temperature during the two seasons. In contrast, the physics-based hydrodynamic model performed better in spring and fall yet exhibited relatively large biases during the summer stratification period. Finally, we developed a statistical integration of the hydrodynamic modeling and deep learning results based on the Best Linear Unbiased Estimator (BLUE). The integration further enhanced prediction accuracy, suggesting its potential for next-generation Great Lakes forecast systems.

Xue, Pengfei (ORCID:000000025702421X)↗

DOE OSTI2023

Oracle-Preserving Latent Flows

A fundamental task in data science is the discovery, description, and identification of any symmetries present in the data. We developed a deep learning methodology for the simultaneous discovery of multiple non-trivial continuous symmetries across an entire labeled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function, ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to invariant transformations with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset, where the oracle is provided by the 10-dimensional vector of logits of a trained classifier. We find classes of symmetries that transform each image from the dataset into new synthetic images while conserving the values of the logits. We illustrate these transformations as lines of equal probability (“flows”) in the reduced latent space. These results show that symmetries in the data can be successfully searched for and identified as interpretable non-trivial transformations in the equivalent latent space.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

The Roman View of Strong Gravitational Lenses

Galaxy–galaxy strong gravitational lenses can constrain dark matter models and the Lambda cold dark matter cosmological paradigm at subgalactic scales. Currently, there is a dearth of images of these rare systems with high signal-to-noise ratio (SNR) and angular resolution. The Nancy Grace Roman Space Telescope (hereafter Roman), scheduled for launch in late 2026, will play a transformative role in strong-lensing science with its planned wide-field surveys. With its remarkable 0.281 square degree field of view and diffraction-limited angular resolution of ~0$^{''}_.$1, Roman is uniquely suited to characterizing dark matter substructure from a robust population of strong lenses. We present a yield simulation of detectable strong lenses in Roman’s planned High Latitude Wide Area Survey (HLWAS). We simulate a population of galaxy–galaxy strong lenses across cosmic time with cold dark matter subhalo populations, select those detectable in the HLWAS, and generate simulated images accounting for realistic Wide Field Instrument detector effects. For a fiducial case of single 146 s exposures, we predict around 160,000 detectable strong lenses in the HLWAS, of which about 500 will have sufficient SNR to be amenable to detailed substructure characterization. We investigate the effect of variation of the point-spread function across Roman’s field of view on detecting individual subhalos and the suppression of the subhalo mass function at low masses. Our simulation products are available to support strong-lens science with Roman, such as training neural networks and validating dark matter substructure analysis pipelines.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2023

CLASS Survey Description: Coronal-line Needles in the SDSS Haystack

Coronal lines are a powerful, yet poorly understood, tool to identify and characterize active galactic nuclei. There have been few large-scale surveys of coronal lines in the general galaxy population in the literature so far. Using a novel preselection technique with a flux-to-rms ratio $\mathcal{F}$, followed by Markov Chain Monte Carlo fitting, we searched for the full suite of 20 coronal lines in the optical spectra of almost 1 million galaxies from the Sloan Digital Sky Survey Data Release 8. We present a catalog of the emission-line parameters for the resulting 258 galaxies with detections. The Coronal Line Activity Spectroscopic Survey includes line properties, host-galaxy properties, and selection criteria for all galaxies in which at least one line is detected. This comprehensive study reveals that a significant fraction of coronal-line activity is missed in past surveys based on a more limited set of coronal lines; ~60% of our sample do not display the more widely surveyed [Fe x] λ6374. In addition, we discover a strong correlation between coronal-line and Wide-field Infrared Survey Explorer W2 luminosities, suggesting that the mid-infrared flux can be used to predict coronal-line fluxes. For each line we also provide a confidence level that the line is present, generated by a novel neural network, trained on fully simulated data. We find that after training the network to detect individual lines using 100,000 simulated spectra, we achieve an overall true-positive rate of 75.49% and a false-positive rate of only 3.96%.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2024

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling

Recent advances in differentiable modeling, a genre of physics-informed machine learning that trains neural networks (NNs) together with process-based equations, have shown promise in enhancing hydrological models' accuracy, interpretability, and knowledge-discovery potential. Current differentiable models are efficient for NN-based parameter regionalization, but the simple explicit numerical schemes paired with sequential calculations (operator splitting) can incur numerical errors whose impacts on models' representation power and learned parameters are not clear. Implicit schemes, however, cannot rely on automatic differentiation to calculate gradients due to potential issues of gradient vanishing and memory demand. Here we propose a “discretize-then-optimize” adjoint method to enable differentiable implicit numerical schemes for the first time for large-scale hydrological modeling. The adjoint model demonstrates comprehensively improved performance, with Kling–Gupta efficiency coefficients, peak-flow and low-flow metrics, and evapotranspiration that moderately surpass the already-competitive explicit model. Therefore, the previous sequential-calculation approach had a detrimental impact on the model's ability to represent hydrological dynamics. Furthermore, with a structural update that describes capillary rise, the adjoint model can better describe baseflow in arid regions and also produce low flows that outperform even pure machine learning methods such as long short-term memory networks. The adjoint model rectified some parameter distortions but did not alter spatial parameter distributions, demonstrating the robustness of regionalized parameterization. Despite higher computational expenses and modest improvements, the adjoint model's success removes the barrier for complex implicit schemes to enrich differentiable modeling in hydrology.

58 GEOSCIENCES↗

DOE OSTI2022

Hyperspectral remote sensing-based plant community map for region around NGEE-Arctic intensive research watersheds at Seward Peninsula, Alaska, 2017-2019

Using airborne hyperspectral remote sensing data from NASA Airborne Visible-Infrared Imaging Spectrometer- Next Generation (AVIRIS-NG) platforms in a region near NGEE-Arctic intensive watersheds at Seward peninsula of Alaska, high resolution (5m) maps of plant community distribution were developed and included in this data collected. AVIRIS-NG data collected over 2017-2019 period were used to develop deep neural networks, trained using vegetation plot observations collected at NGEE-Arctic watersheds at Kougarok, Council and Teller. A hierarchical vegetation classification scheme consisting of six classes at Level I, and 16 classes at Level II contained in two .txt files were used to developed the plant community maps for the region. Two geospatial raster data files (.tif) at both thematic levels are shared in this data collection. Data files in this collection use Alaska Albers Equal Area projection. Readme files available in three formats (*.html, *.md, *.pdf) and one *.png visualization map.The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research.The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Sensitivity Analysis of Drivers Water Shortage in the Los Angeles Region During Drought

The code and detailed step-by-step instructions for generating the model output data, processing results, and analysis and plotting are provided at https://github.com/IMMM-SFA/Ferencz_et_al_2026_ER_Water. The PyArtes model is a python adaptation of the Artes model. PyArtes uses many of the same input data and optimization model architecture as Artes. Documentation for the PyArtes model is provided in the Supplement to the paper. The primary data product are simulated monthly water shortages for indoor and outdoor demand under a large ensemble of drought scenarios (>13,000). The droughts are hypothetical and are not based on historical time series data of supply sources - though historical data did help inform ranges explored for supply parameters. Demands are informed by recent 2017-2021 water supply data. Demands used for the model can be accessed at https://github.com/IMMM-SFA/Ferencz_et_al_2026_ER_Water. Simulations resolve demand for over 90 water providers in the study region. The results report 36 months of water shortage data for each indoor and outdoor demand node. The study also developed a multilayer perceptron (MLP) neural network trained on a subset of the simulated shortage ensemble to emulate worst annual water shortage for a given set of parameter multipliers -- provided the parameter values fall within the ranges sampled in the ensemble. Emulated water shortages for synthetic ensembles are in the MLP-generated shortages folder. The MLP model was used to generate larger ensembles to support Sobol analysis that would have been extremely computationally expensive to simulate. Datasets provided in this repository*: Simulated shortages. These results are used for the analysis for Figures 5, 8, and 9 in the paper, and also to train the MLP emulator. .zip file containing outputs for the 13,312 scenario ensemble. Separate .csv files for indoor and outdoor shortage for each scenario. Rows = demand ids (~100), Columns = months (36) Units = acre-feet/month of shortage (shortage = monthly demand - supply). 1 acft = 1233.48 m^3 .csv files of aggregated shortages derived from the 13,312 ensemble Rows = scenarios (13,312), Columns = demand ids (~100) Units = acre-feet/year (either worst annual shortage or total shortage over the 3-year drought) .csv file of the parameter multipliers scenarios for the ensemble .csv file of the parameter ranges and baseline values the multipliers were applied to MLP-generated shortages. These results are used for Figures 4, 6, and 7 in the paper. mwd higher folder: scenario ensembles, emulated worst year total shortages (acft), and Sobol results Emulated shortages. Rows = scenarios, columns = demand ids, units acft Sobol results. Rows = demand ids, columns Sobol (S1, ST, or 95% confidence interval) value for each parameter mwd lower folder: scenario ensembles, emulated worst year total shortages (acft), and Sobol results same organization as mwd higher MLP performance: performance metrics (R^2, RMSE, BIAS, MAPE) for the testing subset (20% or 2,662 scenarios) and simulated vs emulated worst year shortage (acre-feet/year) for every demand node, MWD wholesale regions, and the entire study region (LAC). Supporting data for figures. Figure plotting scripts in the associated GitHub repo. These files support analysis and visualization. Geospatial Data used for plotting simulated water shortages and Sobol results. Dictionary of full names for demand nodes in the model and estimates of water supply by source type informed by Artes input files and California Urban Water Management Planning data: https://water.ca.gov/Programs/Water-Use-And-Efficiency/Urban-Water-Use-Efficiency/Urban-Water-Management-Plans *Readme files provided for each folder.

drought↗

DOE OSTI2021

Simple biochemical features underlie transcriptional activation domain diversity and dynamic, fuzzy binding to Mediator

Gene activator proteins comprise distinct DNA-binding and transcriptional activation domains (ADs). Because few ADs have been described, we tested domains tiling all yeast transcription factors for activation in vivo and identified 150 ADs. By mRNA display, we showed that 73% of ADs bound the Med15 subunit of Mediator, and that binding strength was correlated with activation. AD-Mediator interaction in vitro was unaffected by a large excess of free activator protein, pointing to a dynamic mechanism of interaction. Structural modeling showed that ADs interact with Med15 without shape complementarity (‘fuzzy’ binding). ADs shared no sequence motifs, but mutagenesis revealed biochemical and structural constraints. Finally, a neural network trained on AD sequences accurately predicted ADs in human proteins and in other yeast proteins, including chromosomal proteins and chromatin remodeling complexes. These findings solve the longstanding enigma of AD structure and function and provide a rationale for their role in biology.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Systems and methods for real-time data processing and for emergency planning

Systems and methods are described herein for real-time data processing and for emergency planning. Scenario test data may be collected in real-time based on monitoring local or regional data to ascertain any anomaly phenomenon that may indicate an imminent danger or of concern. A computer-implemented method may include filtering a plurality of different test scenarios to identify a sub-set of test scenarios from the plurality of different test scenarios that may have similar behavior characteristics. A sub-set of test scenarios is provided to a trained neural network to identify one or more sub-set of test scenarios. The one or more identified sub-set of test scenarios may correspond to one or more anomaly test scenarios from the sub-set of test scenarios that is most likely to lead to an undesirable outcome. The neural network may be one of: a conventional neural network and a modular neural network.

Yilmaz, Alper↗

DOE OSTI2022

Progress on Machine Learning for the SNS High Voltage Converter Modulators

The High-Voltage Converter Modulators (HVCM) used to power the klystrons in the Spallation Neutron Source (SNS) linac were selected as one area to explore machine learning due to reliability issues in the past and the availability of large sets of archived waveforms. Progress in the past two years has resulted in generating a significant amount of simulated and measured data for training neural network models such as recurrent neural networks, convolutional neural networks, and variational autoencoders. Applications in anomaly detection, fault classification, and prognostics of capacitor degradation were pursued in collaboration with the Jefferson Laboratory, and early promising results were achieved. This paper will discuss the progress to date and present results from these efforts.

Pappas, Chris↗

DOE OSTI2022

Toward designing effective exascale scientific computing workflows: experiences and best practices

Many fields within scientific computing have embraced advances in big-data analysis and machine learning, which often requires the deployment of large, distributed and complicated workflows that may combine training neural networks, performing simulations, running inference, and performing database queries and data analysis in asynchronous, parallel and pipelined execution frameworks. Such a shift has brought into focus the need for scalable, efficient workflow management solutions with reproducibility, error and provenance handling, traceability, and checkpoint-restart capabilities, among other needs. Here, we discuss challenges and best-practices for deploying exascale-generation computational science workflows on resources at the Oak Ridge Leadership Computing Facility (OLCF). We present our experiences with large-scale deployment of distributed workflows on the Summit supercomputer, including for bioinformatics and computational biophysics, materials science, and deep learning model optimization. We also present problems and solutions created by working within a Python-centric software base on traditional HPC systems, and discuss steps that will be required before the convergence of HPC, AI, and data science can be fully realized. Our results point to a wealth of exciting new possibilities for harnessing this convergence to tackle new scientific challenges.

Coletti, Mark↗

DOE OSTI2023

Refining fast simulation using machine learning

At the CMS experiment, a growing reliance on the fast Monte Carlo application (FastSim) will accompany the high luminosity and detector granularity expected in Phase 2. The FastSim chain is roughly 10 times faster than the application based on the GEANT4 detector simulation and full reconstruction referred to as FullSim. However, this advantage comes at the price of decreased accuracy in some of the final analysis observables. In this contribution, a machine learning-based technique to refine those observables is presented. We employ a regression neural network trained with a sophisticated combination of multiple loss functions to provide post-hoc corrections to samples produced by the FastSim chain. The results show considerably improved agreement with the FullSim output and an improvement in correlations among output observables and external parameters. This technique is a promising replacement for existing correction factors, providing higher accuracy and thus contributing to the wider usage of FastSim.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗