Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep learning method”

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 937 records · Page 52

Improving galaxy clustering measurements with deep learning: analysis of the DECaLS DR7 data

ABSTRACT Robust measurements of cosmological parameters from galaxy surveys rely on our understanding of systematic effects that impact the observed galaxy density field. In this paper, we present, validate, and implement the idea of adopting the systematics mitigation method of artificial neural networks for modelling the relationship between the target galaxy density field and various observational realities including but not limited to Galactic extinction, seeing, and stellar density. Our method by construction allows a wide class of models and alleviates overtraining by performing k-fold cross-validation and dimensionality reduction via backward feature elimination. By permuting the choice of the training, validation, and test sets, we construct a selection mask for the entire footprint. We apply our method on the extended Baryon Oscillation Spectroscopic Survey (eBOSS) Emission Line Galaxies (ELGs) selection from the Dark Energy Camera Legacy Survey (DECaLS) Data Release 7 and show that the spurious large-scale contamination due to imaging systematics can be significantly reduced by up-weighting the observed galaxy density using the selection mask from the neural network and that our method is more effective than the conventional linear and quadratic polynomial functions. We perform extensive analyses on simulated mock data sets with and without systematic effects. Our analyses indicate that our methodology is more robust to overfitting compared to the conventional methods. This method can be utilized in the catalogue generation of future spectroscopic galaxy surveys such as eBOSS and Dark Energy Spectroscopic Instrument (DESI) to better mitigate observational systematics.

79 ASTRONOMY AND ASTROPHYSICS↗

Time-lapse seismic data inversion for estimating reservoir parameters using deep learning

Geologic carbon sequestration involves the injection of captured carbon dioxide ([Formula: see text]) into subsurface formations for long-term storage. The movement and fate of the injected [Formula: see text] plume is of great concern to regulators because monitoring helps to identify potential leakage zones and determines the possibility of safe long-term storage. To address this concern, we design a deep-learning framework for [Formula: see text] saturation monitoring to determine the geologic controls on the storage of the injected [Formula: see text]. We use different combinations of porosities and permeabilities for a given reservoir to generate saturation and velocity models. We train the deep-learning model with a few time-lapse seismic images and their corresponding changes in saturation values for a particular [Formula: see text] injection site. The deep-learning model learns the mapping from the change in the time-lapse seismic response to the change in [Formula: see text] saturation during the training phase. We then apply the trained model to data sets comprising different time-lapse seismic image slices (corresponding to different time instances) generated using different porosity and permeability distributions that are not part of the training to estimate the [Formula: see text] saturation values along with the plume extent. Our algorithm provides a deep-learning assisted framework for the direct estimation of [Formula: see text] saturation values and plume migration in heterogeneous formations using the time-lapse seismic data. Our method improves the efficiency of time-lapse inversion by streamlining the large number of intermediate steps in the conventional time-lapse inversion workflow. This method also helps to incorporate the geologic uncertainty for a given reservoir by accounting for the statistical distribution of porosity and permeability during the training phase. Tests on different examples verify the effectiveness of our approach.

Geochemistry & Geophysics↗

Utah FORGE: Optimization of a Plug-and-Perf Stimulation (Fervo Energy)

Information around the plug-and-perf treatment design at Utah FORGE by Fervo Energy. Objective and Purpose: - Develop a multistage hydraulic stimulation approach designed specifically to target the top three factors that control the technical and commercial viability of an EGS system: i) Achieving sufficient injectivity to support high cross-well flow rates ii) Distributing flow evenly across the wellbore and reservoir to maximize heat mining efficiency, ensure sustained heat transfer, and mitigate thermal breakthrough iii) Overcoming the effects of stress heterogeneity, stress shadowing, and variations in natural fracture properties during the stimulation treatment, leading to a more predictable stimulated reservoir volume and offset well placement - The following activities will be performed: i) Design, plan, and execute a multistage plug-and-perf stimulation treatment at a Fervo site with data acquisition and well testing activities aimed at addressing key technical aspects of the issues above ii) Perform data processing and interpretation of field results to translate the results form the Fervo site to a site-specific design at the Utah FORGE site iii) Design, plan, and execute a multistage plug-and-perf stimulation treatment design at the Utah FORGE site Methods and Approach: - Design a detailed data acquisition plan to maximize learning around: i) DFIT testing ii) Petrophysical logging, image logging iii) Permanent DAS/DTS fiber optic monitoring iv) Deep borehole microseismic monitoring v) Shallow borehole induced seismicity monitoring vi) Injection/production testing (RTA analysis, tracer testing) vii) Integrated numerical modeling and production forecasting

15 GEOTHERMAL ENERGY↗

A Search for Sterile-Neutrino-Based Muon Neutrino Disappearance Using the MicroBooNe Deep Learning Analysis

We describe a search for νµ disappearance using the MicroBooNE Deep Learning analysis 1µ1p selection. Presently, the unexplained MiniBooNE and LSND anomalies could be explained by a sterile neutrino impacting neutrino oscillations. Our analysis searches for the allowed parameter space that could describe such a sterile neutrino. We determine the allowed and excluded region of a 3+1 sterile-based muon neutrino disappearance model in MicroBooNE at 90% confidence. Our allowed region includes both the null model, and current global best fit model. Context for the underlying Deep Learning analysis is provided and several validation studies surrounding both the disappearance search, and originating 1µ1p selection are performed to strengthen confidence in the result. In addition, a next-generation deep learning tool for cosmic-ray-muon event discrimination is proposed and evaluated, demonstrating a removal of 70% of the remaining event background when added to current methods, under the cut criteria used.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Search for Sterile-Neutrino-Based Muon Neutrino Disappearance Using the MicroBooNe Deep Learning Analysis

We describe a search for νµ disappearance using the MicroBooNE Deep Learning analysis 1µ1p selection. Presently, the unexplained MiniBooNE and LSND anomalies could be explained by a sterile neutrino impacting neutrino oscillations. Our analysis searches for the allowed parameter space that could describe such a sterile neutrino. We determine the allowed and excluded region of a 3+1 sterile-based muon neutrino disappearance model in MicroBooNE at 90% confidence. Our allowed region includes both the null model, and current global best fit model. Context for the underlying Deep Learning analysis is provided and several validation studies surrounding both the disappearance search, and originating 1µ1p selection are performed to strengthen confidence in the result. In addition, a next-generation deep learning tool for cosmic-ray-muon event discrimination is proposed and evaluated, demonstrating a removal of 70% of the remaining event background when added to current methods, under the cut criteria used.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Suppressing simulation bias in multi-modal data using transfer learning

Abstract Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is multi-dimensional. Simulations, however, often suffer from an inherent bias. Estimation of this bias may be poorly constrained not only because of data sparsity, but also because traditional predictive models fit only one type of observed outputs, such as scalars or images, instead of all available output data modalities, which might have been acquired and simulated at great cost. To break this limitation and open up the path for multi-modal calibration, we propose to combine a novel, transfer learning technique for suppressing the bias with recent developments in deep learning, which allow building predictive models with multi-modal outputs. First, we train an initial neural network model on simulated data to learn important correlations between different output modalities and between simulation inputs and outputs. Then, the model is partially retrained, or transfer learned, to fit the experiments; a method that has never been implemented in this type of architecture. Using fewer than 10 inertial confinement fusion experiments for training, transfer learning systematically improves the simulation predictions while a simple output calibration, which we design as a baseline, makes the predictions worse. We also offer extensive cross-validation with real and carefully designed synthetic data. The method described in this paper can be applied to a wide range of problems that require transferring knowledge from simulations to the domain of experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

A machine learning decision criterion for reducing scan time for hyperspectral neutron computed tomography systems

We present the first machine learning-based autonomous hyperspectral neutron computed tomography experiment performed at the Spallation Neutron Source. Hyperspectral neutron computed tomography allows the characterization of samples by enabling the reconstruction of crystallographic information and elemental/isotopic composition of objects relevant to materials science. High quality reconstructions using traditional algorithms such as the filtered back projection require a high signal-to-noise ratio across a wide wavelength range combined with a large number of projections. This results in scan times of several days to acquire hundreds of hyperspectral projections, during which end users have minimal feedback. To address these challenges, a golden ratio scanning protocol combined with model-based image reconstruction algorithms have been proposed. This novel approach enables high quality real-time reconstructions from streaming experimental data, thus providing feedback to users, while requiring fewer yet a fixed number of projections compared to the filtered back projection method. In this paper, we propose a novel machine learning criterion that can terminate a streaming neutron tomography scan once sufficient information is obtained based on the current set of measurements. Our decision criterion uses a quality score which combines a reference-free image quality metric computed using a pre-trained deep neural network with a metric that measures differences between consecutive reconstructions. The results show that our method can reduce the measurement time by approximately a factor of five compared to a baseline method based on filtered back projection for the samples we studied while automatically terminating the scans.

97 MATHEMATICS AND COMPUTING↗

Active operator learning with predictive uncertainty quantification for partial differential equations

With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying reliable surrogate models in scientific applications. Existing uncertainty quantification (UQ) frameworks employ ensembles or Bayesian methods, which can incur substantial computational costs during both training and inference. Here, we propose a lightweight predictive UQ method tailored for Deep operator networks (DeepONets) that also generalizes to other operator networks. Numerical experiments on linear and nonlinear PDEs demonstrate that the framework’s uncertainty estimates are unbiased and provide accurate out-of-distribution uncertainty predictions with a sufficiently large training dataset. Our framework provides fast inference and uncertainty estimates that can efficiently drive outer-loop analyses that would be prohibitively expensive with conventional solvers. We demonstrate how predictive uncertainties can be used in the context of Bayesian optimization and active learning problems to yield improvements in accuracy and data-efficiency for outer-loop optimization procedures. In the active learning setup, we extend the framework to Fourier Neural Operators (FNO) and describe a generalized method for other operator networks. To enable real-time deployment, we introduce an inference strategy based on precomputed trunk outputs and a sparse placement matrix, reducing evaluation time by more than a factor of five. Our method provides a practical route to uncertainty-aware operator learning in time-sensitive settings.

97 MATHEMATICS AND COMPUTING↗

INITIAL STUDIES OF CAVITY FAULT PREDICTION AT JEFFERSON LABORATORY

The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Laboratory is a CW recirculating linac that utilizes over 400 superconducting radio-frequency (SRF) cavities to accelerate electrons up to 12 GeV through 5-passes. Recent work has shown that, given RF signals from a cavity during a fault as input, machine learning approaches can accurately classify the fault type. In this paper we report on initial results of predicting a fault onset using only data prior to the failure event. A data set was constructed using time-series data immediately before a fault (’unstable’) and 1.5 seconds prior to a fault (’stable’) gathered from over 5,000 saved fault events. The data was used to train a binary classifier. The results gave key insights into the behavior of several fault types and provided motivation to investigate whether data prior to a failure event could also predict the type of fault. We discuss our method using a sliding window approach and report on initial results. Recent modifications to the low-level RF control system will provide access to streaming signals and we outline a path forward for leveraging deep learning on streaming data

Vidyaratne, Lasitha↗

INITIAL STUDIES OF CAVITY FAULT PREDICTION AT JEFFERSON LABORATORY

The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Laboratory is a CW recirculating linac that utilizes over 400 superconducting radio-frequency (SRF) cavities to accelerate electrons up to 12 GeV through 5-passes. Recent work has shown that, given RF signals from a cavity during a fault as input, machine learning approaches can accurately classify the fault type. In this paper we report on initial results of predicting a fault onset using only data prior to the failure event. A data set was constructed using time-series data immediately before a fault (’unstable’) and 1.5 seconds prior to a fault (’stable’) gathered from over 5,000 saved fault events. The data was used to train a binary classifier. The results gave key insights into the behavior of several fault types and provided motivation to investigate whether data prior to a failure event could also predict the type of fault. We discuss our method using a sliding window approach and report on initial results. Recent modifications to the low-level RF control system will provide access to streaming signals and we outline a path forward for leveraging deep learning on streaming data

Vidyaratne, Lasitha↗

Experimental Observations of the Topology of Convolutional Neural Network Activations

Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture resulting in high-dimensional, difficult to interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper we apply cutting edge techniques from TDA with the goal of gaining insight towards interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers and discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight as to how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.

topological data analysis, deep learning↗

Predicting CO 2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network

Numerical simulation of flow and transport in heterogeneous formations has long been studied, especially for uncertainty quantification and risk assessment. The high computational cost associated with running large-scale numerical simulations in a Monte Carlo sense has motivated the development of surrogate models, which aim to capture the important input-output relations of physics-based models but require only a fraction of the cost of full model runs. In this work, we formulate a conditional deep convolutional generative adversarial network (cDC-GAN) surrogate model to learn the dynamic functional mappings in multiphase models. The cDC-GAN belongs to a class of semisupervised learning methods that can be used to learn the data generation processes. Like the original GAN, a main strength of the cDC-GAN is that it includes a self-training scheme for improving the quality of generative modeling in a game theoretic framework, without requiring extensive statistical knowledge and assumptions on input data distributions. In particular, our cDC-GAN model is designed to learn cross-domain mappings between high-dimensional input (e.g., permeability) and output (e.g., phase saturations) pairs, with the ability to incorporate conditioning information (e.g., prediction time). As a use case, we demonstrate the performance of cDC-GAN for predicting the migration of carbon dioxide (CO 2 ) plume in heterogeneous carbon storage reservoirs, which has both numerical and practical significance because of the safe storage requirements now mandated in many countries. Results show that cDC-GAN achieves high accuracy in predicting the spatial and temporal evolution patterns of the injected CO 2 plume, as compared to the original results obtained using a compositional reservoir simulator. The performance of cDC-GAN models, trained using the same number of training samples, stays relatively robust when the level of spatial heterogeneity is increased. Our cDC-GAN is pattern based and is not limited by the underlying physics. Thus, it provides a general framework for developing surrogate models, and for conducting uncertainty analyses for a wide range of physics-based models used in both groundwater and subsurface energy exploration applications.

54 ENVIRONMENTAL SCIENCES↗

Fast inference of deep neural networks in FPGAs for particle physics

Here, recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA (Field Programmable Gate Array) hardware has only just begun. FPGA-based trigger and data acquisition systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. A companion compiler package for this work is developed based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Transfer learning nonlinear plasma dynamic transitions in low dimensional embeddings via deep neural networks

Deep learning algorithms provide a new paradigm to study high-dimensional dynamical behaviors, such as those in fusion plasma systems. Development of novel, data-driven model reduction methods, coupled with detection of abnormal modes with plasma physics, opens a unique opportunity to identify plasma instabilities through automated construction of parsimonious models that can be tuned to balance accuracy and cost. Our fusion transfer learning (FTL) model demonstrates success in rapidly reconstructing nonlinear kink mode structures by learning from a limited amount of nonlinear simulation data. The knowledge transfer process leverages a pre-trained neural encoder–decoder network, initially trained on linear simulations, to effectively capture nonlinear dynamics. The low-dimensional embeddings extract the coherent structures of interest, while preserving the inherent dynamics of the complex system. Experimental results highlight FTL’s capacity to capture transitional behaviors and dynamical features in plasma dynamics—a task often challenging for conventional methods. The model developed in this study is generalizable and can be extended broadly through transfer learning to address various magnetohydrodynamics modes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Automated Threat Recognition For Aviation Security Applications

We have developed a framework for automated threat recognition (ATR) of explosive threat materials for both single-energy and dual-energy X-ray CT systems. Under this framework, two different types of ATR have been developed. The first type of ATR employs supervised machine learning with statistical characterization of target materials for threat identification training. The reliance only on statistical characterization information for threat training uniquely enables this style of ATR to adapt quickly to evolving threats. The second type of ATR employs deep learning through convolutional neural networks. Convolutional neural networks are attractive due to their human-like capacity for learning and strong ability to identify trends and patterns. Although this method is more powerful than the first type, it requires large amounts of training data and therefore is less agile. Each ATR performs threat characterization at the voxel neighborhood level. This approach avoids the use of threat shape as a detection criterion, which is prohibited by DHS and TSA guidelines.

97 MATHEMATICS AND COMPUTING↗

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

42 ENGINEERING↗

Identifying precursors of daily to seasonal hydrological extremes over the USA using deep learning techniques and climate model ensembles

Focal Area(s): We focus on two areas of crosscutting interest for DOE: 1) predictability of extreme precipitation and drought in the USA and 2) the integration of climate models with new AI tools, such as convolutional neural networks (CNN) and methods to understand their output (e.g. layer-wise relevance propagation; LRP). This project fits into focus area 3 of this call for white paper using AI to gain insight from complex data, including explainable AI tools. Science Challenge: Predicting hydrological extremes is important due to their impacts on people, agriculture and infrastructure. This prediction is difficult due to the infrequent occurrence of extremes and their complexity. However, extreme events can be related to more predictable conditions in the ocean, such as El Nino, long-term soil moisture or large scale modes of climate variability, such as the North Atlantic Oscillation (NAO).

54 ENVIRONMENTAL SCIENCES↗