Search NASA⌕ Search

SEARCH · Search NASA

Results for “fast machine learning”

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 397 records · Page 22

Machine Learning Based AFP Inspection: A Tool for Characterization and Integration

Automated Fiber Placement (AFP) has become a standard manufacturing technique in the creation of large scale composite structures due to its high production rates. However, the associated rapid layup that accompanies AFP manufacturing has a tendency to induce defects. We forward an inspection system that utilizes machine learning (ML) algorithms to locate and characterize defects from profilometry scans coupled with a data storage system and a user interface (UI) that allows for informed manufacturing. A Keyence LJ-7080 blue light profilometer is used for fast 2D height profiling. After scans are collected, they are process by ML algorithms, displayed to an operator through the UI, and stored in a database. The overall goal of the inspection system is to add an additional tool for AFP manufacturing. Traditional AFP inspection is done manually adding to manufacturing time and being subject to inspector errors or fatigue. For large parts, the inspection process can be cumbersome. The proposed inspection system has the capability of accelerating this process while still keeping a human inspector integrated and in control. This allows for the rapid capability of the automated inspection software and the robustness of a human checking for defects that the system either missed or misclassified.

Sacco, Christopher↗

Fast Learning for Immersive Engagement in Energy Simulations

The fast computation which is critical for immersive engagement with and learning from energy simulations would be furthered by developing a general method for creating rapidly computed simplified versions of NREL's computation-intensive energy simulations. Created using machine learning techniques, these 'reduced form' simulations can provide statistically sound estimates of the results of the full simulations at a fraction of the computational cost with response times - typically less than one minute of wall-clock time - suitable for real-time human-in-the-loop design and analysis. Additionally, uncertainty quantification techniques can document the accuracy of the approximate models and their domain of validity. Approximation methods are applicable to a wide range of computational models, including supply-chain models, electric power grid simulations, and building models. These reduced-form representations cannot replace or re-implement existing simulations, but instead supplement them by enabling rapid scenario design and quality assurance for large sets of simulations. We present an overview of the framework and methods we have implemented for developing these reduced-form representations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Machine-learning predictions of the shale wells’ performance

The ultra-low permeability nature of shale reservoirs leads to an extended linear flow and necessitates horizontal wells with multi-stage engineered fractures to efficiently extract hydrocarbons resources. These artificially-generated and naturally-occurring fractures form complex networks that create complex flow regimes which control oil production. These fractures are neither identical nor equally-spaced, which leads to a production profile with a masked onset of the boundary-dominated flow. The combination of the extended linear flow with the indeterminate onset of the boundary-dominated flow challenges the current deterministic analytic approaches to forecast the estimated ultimate recovery (EUR). In this work, we propose a novel machine-learning approach which overcomes these challenges and provides reliable EUR estimates based on field-wide analyses. We implement a novel unsupervised machine learning (ML) methodology, which allows for automatic identification of the optimal number of features (signals) present in the data based on non-negative matrix/tensor factorization coupled with k-means clustering incorporating regularization and physics constraints. In the presented analyses, the input data to the ML algorithm is the available (public) production history from the field collected at existing unconventional reservoirs. We validate our approach through hindcasting of the production data, where we achieved an excellent agreement. In addition, our approach is able to identify the poorly-performing wells, which could benefit from early refracing. Our approach provides fast and accurate estimations of the well performance without presumptions about the state of the well or the flow regime.

03 NATURAL GAS↗

Velocity Extraction Using Complete Time-Domain Waveform Data and Audio Machine Learning

We developed a new machine learning-based tool for extracting information from interferometry measurements: MIDWAZE (Modular Interferometry Direct Waveform AnalyZEr). This paper showcases MIDWAZE’s ability to extract an object’s velocity information from Photonic Doppler Velocimetry (PDV) data at near-human accuracy with little to no human intervention. MIDWAZE can extract velocities roughly 350 times as fast as a human analyst "rushing" to complete their extractions, with similar extraction accuracy. MIDWAZE’s most outstanding feature is that it operates directly in waveform/temporal space, freeing analysis from certain limitations imposed by traditional spectrogram-based approaches and opening the way to "phase aware" PDV analysis. MIDWAZE also has limited ability to discriminate between different solid objects, which we develop as a first step towards automated discrimination of different kinds of objects such as ejecta clouds.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Bragg Spot Finder (BSF): a new machine-learning-aided approach to deal with spot finding for rapidly filtering diffraction pattern images

Macromolecular crystallography contributes significantly to understanding diseases and, more importantly, how to treat them by providing atomic resolution 3D structures of proteins. This is achieved by collecting X-ray diffraction images of protein crystals from important biological pathways. Spotfinders are used to detect the presence of crystals with usable data, and the spots from such crystals are the primary data used to solve the relevant structures. Having fast and accurate spot finding is essential, but recent advances in synchrotron beamlines used to generate X-ray diffraction images have brought us to the limits of what the best existing spotfinders can do. This bottleneck must be removed so spotfinder software can keep pace with the X-ray beamline hardware improvements and be able to see the weak or diffuse spots required to solve the most challenging problems encountered when working with diffraction images. In this paper, we first present Bragg Spot Detection (BSD), a large benchmark Bragg spot image dataset that contains 304 images with more than 66 000 spots. We then discuss the open source extensible U-Net-based spotfinder Bragg Spot Finder (BSF), with image pre-processing, a U-Net segmentation backbone, and post-processing that includes artifact removal and watershed segmentation. Finally, we perform experiments on the BSD benchmark and obtain results that are (in terms of accuracy) comparable to or better than those obtained with two popular spotfinder software packages ( Dozor and DIALS ), demonstrating that this is an appropriate framework to support future extensions and improvements.

36 MATERIALS SCIENCE↗

Topological Machine Learning Methods for Power System Responses to Contingencies: Preprint

While deep learning tools, coupled with the emerging machinery of topological data analysis, are proven to deliver various performance gains in a broad range of applications, from image classification to biosurveillance to blockchain fraud detection, their utility in areas of high societal importance such as power system modeling and, particularly, resilience quantification in the energy sector yet remain untapped. To provide fast acting synthetic regulation and contingency reserve services to the grid while having minimal disruptions on customer quality of service, we propose a new topologybased system that depends on neural network architecture for impact metrics classification and prediction in power systems. This novel topology-based system allows one to evaluate the impact of three power system contingency types, namely, in conjunction with transmission lines, transformers, and transmission lines combined with transformers. We show that the proposed new neural network architecture equipped with local topological measures facilitates both more accurate classification of unserved load as well as the amount of unserved load. In addition, we are able to learn complex relationships between electrical properties and local topological measurements on the simulated response to contingencies for NREL-SIIP power system.

graph theory↗

Enabling real-time multi-messenger astrophysics discoveries with deep learning

Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and finally, the need to build a community of experts to realize the goals of multi-messenger astrophysics.

79 ASTRONOMY AND ASTROPHYSICS↗

Machine Learning for Scalable and Optimal Load Shedding Under Power System Contingency

Prompt and effective corrective actions in response to unexpected contingencies are crucial for improving power system resilience and preventing cascading blackouts. The optimal load shedding (OLS) accounting for network limits has the potential to address the diverse system-wide impacts of contingency scenarios as compared to traditional local schemes. However, due to the fast cascading propagation of initial contingencies, real-time OLS solutions are challenging to attain in large systems with high computation and communication needs. In this paper, we propose a decentralized design that leverages offline training of a neural network (NN) model for individual load centers to autonomously construct the OLS solutions from locally available measurements. Our learning-for-OLS approach can greatly reduce the computation and communication needs during online emergency responses, thus preventing the cascading propagation of contingencies for enhanced power grid resilience. Numerical studies on both the IEEE 118-bus system and a synthetic Texas 2000-bus system have demonstrated the efficiency and effectiveness of our scalable OLS learning design for timely power system emergency operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

An extensible perturbed parameter ensemble for the Community Atmosphere Model version 6

This paper documents the methodology and preliminary results from a perturbed parameter ensemble (PPE) technique, where multiple parameters are varied simultaneously and the parameter values are determined with Latin hypercube sampling. This is done with the Community Atmosphere Model version 6 (CAM6), the atmospheric component of the Community Earth System Model version 2 (CESM2). We apply the PPE method to CESM2–CAM6 to understand climate sensitivity to atmospheric physics parameters. The initial simulations vary 45 parameters in the microphysics, convection, turbulence and aerosol schemes with 263 ensemble members. These atmospheric parameters are typically the most uncertain in many climate models. Control simulations and targeted simulations to understand climate forcing due to aerosols and fast climate feedbacks are analyzed. The use of various emulators is explored in the multi-dimensional space mapping input parameters to output metrics. Parameter impacts on various model outputs, such as radiation, cloud and aerosol properties, are evaluated. Machine learning is also used to probe optimal parameter values against observations. Our findings show that PPE is a valuable tool for climate uncertainty analysis. Furthermore, by varying many parameters simultaneously, we find that many different combinations of parameter values can produce results consistent with observations, and thus careful analysis of tuning is important. The CESM2–CAM6 PPE is publicly available and extensible to other configurations to address questions of other model processes in the atmosphere and other model components (e.g., coupling to the land surface).

54 ENVIRONMENTAL SCIENCES↗

Enabling Real-time Multi-messenger Astrophysics Discoveries with Deep Learning

Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and the need to build a community of experts to realize the goals of multi-messenger astrophysics.

E A Huerta↗

Neural Networks for Modeling and Control of Particle Accelerators

Particle accelerators are host to myriad nonlinear and complex physical phenomena. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems, as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. The purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.

43 PARTICLE ACCELERATORS↗

CCUS 2024, Interpreting the strain tensor Larry Murdoch Interpreting strain tensor data to characterize and monitor reservoirs for CO2 storage and other applications

Recent advances in instrumentation have made it feasible to measure the transient strain tensor caused by small changes in fluid volume or pressure in the subsurface and this has opened the door to new opportunities for characterization and monitoring during CCUS. We have demonstrated this method by deploying strainmeters at shallow depths (30 to 40m) and then conducting injection well tests in an underlying reservoir at 530m depth. The resulting data indicated that the horizontal strain at shallow strainmeters was tensile and the vertical strain was compressive. The radial strain was less than the horizontal strain, and the strain rates decreased from 100 nanostrain/day to roughly 10 ne/d over a few days (1 nanostrain = 1 part per billion strain). We then used the strain data to estimate reservoir properties, geometry and pressure through inversion of poroelastic forward models using both numerical and novel analytical methods. The average horizontal strain in the caprock resembles the transient pressure in the underlying reservoir and classic type-curve methods from transient well testing can be used for preliminary interpretations of strain data. We have developed fast, closed-form analytical solutions to a pressurized poroelastic inclusion and inhomogeneity in a half-space. Numerical models developed using finite element methods allow more details of the subsurface to be included in the inversion, but they require much longer run times and this makes inversion cumbersome using standard methods. We have developed an inversion approach that uses a proxy model created using machine learning to do most of the forward calculations. This approach markedly reduces the computational requirements and makes it feasible to use Bayesian inversion with large numerical models. Bayesian inversion is important because it provides predictions with uncertainties, which makes the results useful for decision making. We have shown with field tests and simulations that the strain tensor in the caprock is sensitive to pressure in the reservoir, reservoir properties and boundaries, and pressure in the caprock caused by leaks. These results indicate that measuring and interpreting the shallow strain tensor could be a valuable tool for both initial reservoir characterization efforts and long-term monitoring during CCUS. Recent advances in instrumentation have made it feasible to measure the transient strain tensor caused by small changes in fluid volume or pressure in the subsurface and our objective was to evaluate opportunities for strain monitoring during characterization and monitoring for CCUS. Our approach was to deploy strainmeters at shallow depths (30 to 40m) and then conduct injection well tests in an underlying reservoir at 530m depth. The results indicate that the horizontal strain at shallow strainmeters was tensile and the vertical strain was compressive. The radial strain was less than the horizontal strain, and the strain rates decreased from 100 nanostrain/day to roughly 10 ne/d over a few days (1 nanostrain = 1 part per billion strain). We then used the strain data to estimate reservoir properties, geometry and pressure through inversion of poroelastic forward models using both numerical and novel analytical methods. The average horizontal strain in the caprock resembles the transient pressure in the underlying reservoir and classic type-curve methods from transient well testing can be used for preliminary interpretations of strain data. We have developed fast, closed-form analytical solutions to a pressurized poroelastic inclusion and inhomogeneity in a half-space. Numerical models developed using finite element methods allow more details of the subsurface to be included in the inversion, but they require much longer run times and this makes inversion cumbersome using standard methods. We have developed an inversion approach that uses a proxy model created using machine learning to do most of the forward calculations. This approach markedly reduces the computational requirements and makes it feasible to use Bayesian inversion with large numerical models. Bayesian inversion is important because it provides predictions with uncertainties, which makes the results useful for decision making. In conclusion, we have shown with field tests and simulations that the strain tensor in the caprock is sensitive to pressure in the reservoir, reservoir properties and boundaries, and pressure in the caprock caused by leaks. These results indicate that measuring and interpreting the shallow strain tensor could be a valuable tool for both initial reservoir characterization efforts and long-term monitoring during CCUS.

Murdoch, Larry↗

Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine-learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce-data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal-halides spanning 3 dimensionalities and 7 space-groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross-validated accuracies for dimensionality and space-group classification of 93% and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root-causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16° 2θ, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.

36 MATERIALS SCIENCE↗

A Deep Generative Deconvolutional Image Model

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic unpooling is employed to link consecutive layers in the model, yielding top-down image generation. A Bayesian support vector machine is linked to the top-layer features, yielding max-margin discrimination. Deep deconvolutional inference is employed when testing, to infer the latent features, and the top-layer features are connected with the max-margin classifier for discrimination tasks. The model is efficiently trained using a Monte Carlo expectation-maximization (MCEM) algorithm; the algorithm is implemented on graphical processor units (GPU) to enable large-scale learning, and fast testing. Excellent results are obtained on several benchmark datasets, including ImageNet, demonstrating that the proposed model achieves results that are highly competitive with similarly sized convolutional neural networks.

convolutional neural network↗

Plug & play directed evolution of proteins with gradient-based discrete MCMC

Abstract A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast Markov chain Monte Carlo sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650 M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

59 BASIC BIOLOGICAL SCIENCES↗

SU-F-T-450: The Investigation of Radiotherapy Quality Assurance and Automatic Treatment Planning Based On the Kernel Density Estimation Method

Purpose: To develop a fast automatic algorithm based on the two dimensional kernel density estimation (2D KDE) to predict the dose-volume histogram (DVH) which can be employed for the investigation of radiotherapy quality assurance and automatic treatment planning. Methods: We propose a machine learning method that uses previous treatment plans to predict the DVH. The key to the approach is the framing of DVH in a probabilistic setting. The training consists of estimating, from the patients in the training set, the joint probability distribution of the dose and the predictive features. The joint distribution provides an estimation of the conditional probability of the dose given the values of the predictive features. For the new patient, the prediction consists of estimating the distribution of the predictive features and marginalizing the conditional probability from the training over this. Integrating the resulting probability distribution for the dose yields an estimation of the DVH. The 2D KDE is implemented to predict the joint probability distribution of the training set and the distribution of the predictive features for the new patient. Two variables, including the signed minimal distance from each OAR (organs at risk) voxel to the target boundary and its opening angle with respect to the origin of voxel coordinate, are considered as the predictive features to represent the OAR-target spatial relationship. The feasibility of our method has been demonstrated with the rectum, breast and head-and-neck cancer cases by comparing the predicted DVHs with the planned ones. Results: The consistent result has been found between these two DVHs for each cancer and the average of relative point-wise differences is about 5% within the clinical acceptable extent. Conclusion: According to the result of this study, our method can be used to predict the clinical acceptable DVH and has ability to evaluate the quality and consistency of the treatment planning.

60 APPLIED LIFE SCIENCES↗

Need for advanced research reactors for the next-generation reactor physics, analysis tools, and technology

Full text of publication follows. There is an urgent need for design and deployment of advanced research and test reactors in support of design, licensing and operation of advanced power reactors and education of next generation nuclear workforce. Existing research reactors mostly were designed and constructed decades ago with the main objectives of training operators, performing reactor physics experiments, and educating nuclear engineers and scientists. There are already gaps and significant concern about future capabilities for the existing research reactor facilities to address modern instrumentation and/or flexible environments for: performing reactor physics studies for advanced designs which have significantly different core materials forms and compositions, reactor shapes and size; validation of advanced high-fidelity software; development of machine learning algorithms for enhancement of human-machine collaboration in support of reactor monitoring, operation and safeguards; and, effective education of the next-generation workforce. The authors will focus on the need for advanced research reactors to improve and validate fast and accurate simulation tools for high-fidelity modeling and analysis of nuclear reactors in support of their design, optimization, licensing, operation, and monitoring. In the past, simulation tools were limited to relatively coarse models using approximate methodologies that benefited from two main factors: i) allowance for large margins and tolerances; ii) ability to construct prototype (e.g., zero power) reactors for adjustment of approximate methodologies. The next generation reactors have to be designed mainly by using novel high-fidelity computational tools that are accurate and fast, and therefore can be used for parametric studies and uncertainty quantification. To sufficiently demonstrate the accuracy of these tools, advanced research reactors are needed. The authors argue the need for new computational paradigms such as the MRT (Multistage, Response- function Transport) methodology which has resulted in the development of the novel high-fidelity RAPID (Real-time Analysis for Particle-transport and In-situ Detection) code system. Such code systems have to be robust in modeling any complex system, and should be fast and accurate, henceforth their uncertainties can be quantified at reasonable costs. Again, advanced research reactors are needed for the validation of the fidelity and accuracy of new computational tools. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗