Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning operations”

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 1,477 records · Page 82

On the universality of S n -equivariant k -body gates

The importance of symmetries has recently been recognized in quantum machine learning from the simple motto: if a task exhibits a symmetry (given by a group $\mathfrak{G}$), the learning model should respect said symmetry. This can be instantiated via $\mathfrak{G}$-equivariant quantum neural networks (QNNs), i.e. parametrized quantum circuits whose gates are generated by operators commuting with a given representation of $\mathfrak{G}$. In practice, however, there might be additional restrictions to the types of gates one can use, such as being able to act on at most k qubits. In this work we study how the interplay between symmetry and k-bodyness in the QNN generators affect its expressiveness for the special case of $\mathfrak{G}=S_n$, the symmetric group. Our results show that if the QNN is generated by one- and two-body Sn-equivariant gates, the QNN is semi-universal but not universal. That is, the QNN can generate any arbitrary special unitary matrix in the invariant subspaces, but has no control over the relative phases between them. Then, we show that in order to reach universality one needs to include n-body generators (if n is even) or ($n-1$)-body generators (if n is odd). As such, our results brings us a step closer to better understanding the capabilities and limitations of equivariant QNNs.

97 MATHEMATICS AND COMPUTING↗

Machine Learning for Searching the Dark Energy Survey for Trans-Neptunian Objects

In this paper we investigate how implementing machine learning could improve the efficiency of the search for Trans-Neptunian Objects (TNOs) within Dark Energy Survey (DES) data when used alongside orbit fitting. The discovery of multiple TNOs that appear to show a similarity in their orbital parameters has led to the suggestion that one or more undetected planets, an as yet undiscovered “Planet 9”, may be present in the outer solar system. DES is well placed to detect such a planet and has already been used to discover many other TNOs. Here, we perform tests on eight different supervised machine learning algorithms, using a data set consisting of simulated TNOs buried within real DES noise data. We found that the best performing classifier was the Random Forest which, when optimized, performed well at detecting the rare objects. We achieve an area under the receiver operating characteristic (ROC) curve, (AUC) = 0.996 ± 0.001. After optimizing the decision threshold of the Random Forest, we achieve a recall of 0.96 while maintaining a precision of 0.80. Finally, by using the optimized classifier to pre-select objects, we are able to run the orbit-fitting stage of our detection pipeline five times faster.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Implementing two-qubit gates at the quantum speed limit

The speed of elementary quantum gates, particularly two-qubit gates, ultimately sets the limit on the speed at which quantum circuits can operate. In this work, we experimentally demonstrate commonly used two-qubit gates at nearly the fastest possible speed allowed by the physical interaction strength between two superconducting transmon qubits. We achieve this quantum speed limit by implementing experimental gates designed using a machine-learning-inspired optimal control method. Importantly, our method only requires the single-qubit drive strength to be moderately larger than the interaction strength to achieve an arbitrary two-qubit gate close to its analytical speed limit with high fidelity. Thus the method is applicable to a variety of platforms, including those with comparable single-qubit and two-qubit gate speeds, or those with always-on interactions. We expect our method to offer significant speedups for non-native two-qubit gates that are typically achieved with a long sequence of single-qubit and native two-qubit gates.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Machine Learning-based False Data Injection Attack Detection and Localization in Power Grids

Cyberattacks on critical infrastructures can be catastrophic and bring nations to their knees. Therefore, detecting these attacks is crucial and challenging. This paper presents a novel approach for detecting and locating cyberattacks affecting an electrical power system. The adversary employs a man-in-the-middle technique to inject false data into the communication between distributed energy resources (DER) and Microgrid Controller (MGC) with the goal of disrupting power delivery. The approach for detection and localization is based on integrating multiple machine learning-based anomaly detection models that combine network traffic data and grid measurements. Experiments are performed to assess the method's performance using a hardware-in-the-loop real-time simulation testbed which includes Modbus TCP/IP communication. Power system topology and operating conditions are based on actual topology and real-world data provided by the Holy Cross Energy utility network. Results confirm that the method can be successfully employed for detecting and localizing cyberattacks.

Leao, Bruno P.↗

GPU Direct I/O with HDF5

Exascale HPC systems are being designed with accelerators, such as GPUs, to accelerate parts of applications. In machine learning workloads as well as large-scale simulations that use GPUs as accelerators, the CPU (or host) memory is currently used as a buffer for data transfers between GPU (or device) memory and the file system. If the CPU does not need to operate on the data, then this is sub-optimal because it wastes host memory by reserving space for duplicated data. Furthermore, this “bounce buffer” approach wastes CPU cycles spent on transferring data. A new technique, NVIDIA GPUDirect Storage (GDS), can eliminate the need to use the host memory as a bounce buffer. Thereby, it becomes possible to transfer data directly between the device memory and the file system. This direct data path shortens latency by omitting the extra copy and enables higher-bandwidth. To take full advantage of GDS in existing applications, it is necessary to provide support with existing I/O libraries, such as HDF5 and MPI-IO, which are heavily used in applications. In this paper, we describe our effort of integrating GDS with HDF5, the top I/O library at NERSC and at DOE leadership computing facilities. We design and implement this integration using a HDF5 Virtual File Driver (VFD). The GDS VFD provides a file system abstraction to the application that allows HDF5 applications to perform I/O without the need to move data between CPUs and GPUs explicitly. We compare performance of the HDF5 GDS VFD with explicit data movement approaches and demonstrate superior performance with the GDS method.

Ravi, J↗

Predicting Metabolic Reaction Networks with Perturbation-Theory Machine Learning (PTML) Models

Background: Checking the connectivity (structure) of complex Metabolic Reaction Networks(MRNs) models proposed for new microorganisms with promising properties is an importantgoal for chemical biology. Objective: In principle, we can perform a hand-on checking (Manual Curation). However, this is achallenging task due to the high number of combinations of pairs of nodes (possible metabolic reactions). Results: The CPTML linear model obtained using the LDA algorithm is able to discriminate nodes(metabolites) with the correct assignation of reactions from incorrect nodes with values of accuracy,specificity, and sensitivity in the range of 85-100% in both training and external validation dataseries. Methods: In this work, we used Combinatorial Perturbation Theory and Machine Learning techniquesto seek a CPTML model for MRNs >40 organisms compiled by Barabasis’ group. First, wequantified the local structure of a very large set of nodes in each MRN using a new class of node indexcalled Markov linear indices fk. Next, we calculated CPT operators for 150000 combinationsof query and reference nodes of MRNs. Last, we used these CPT operators as inputs of differentML algorithms. Conclusion: Meanwhile, PTML models based on Bayesian network, J48-Decision Tree and RandomForest algorithms were identified as the three best non-linear models with accuracy greaterthan 97.5%. The present work opens the door to the study of MRNs of multiple organisms usingPTML models.

Pharmacology & Pharmacy↗

Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers

The Environmental Determinants of the Diabetes in the Young (TEDDY) study has prospectively followed, from birth, children at increased genetic risk of type 1 diabetes. We evaluated the potential of machine learning to identify new biomarkers that predict imminent (within 6 months) development of persistent islet autoantibodies to insulin, GAD or IA-2 in TEDDY participants through integration of time-invariant risk factors with time-varying metabolomics. The predictive modeling was initiated with over 220 potential biomarkers; through ensemble-based feature evaluation, the optimal model included 42 biomarkers, returning a cross-validated receiver operating characteristic area under the curve of 0.74. The model identified a principal set of 20 time-invariant markers, including 16 single nucleotide polymorphisms and two HLA-DR genotypes, gestational age, and exposure to a prebiotic formula. Integration of the metabolome identified 22 high-priority metabolites and lipids, including adipic acid and ceramide d42:0, that predicted development of islet autoantibodies, dependent upon the time horizon. The majority (86%) of metabolites that predicted development of islet autoantibodies belonged to 3 pathways: lipid oxidation, phospholipase A2 signaling, and pentose phosphate pathway. TEDDY data suggest that these metabolic processes may play a role in triggering islet autoimmunity.

59 BASIC BIOLOGICAL SCIENCES↗

INL Senior Project

What did my team set out to accomplish:? Can I put a custom Machine Learning Model on FPGA?? Can I analyze network traffic in real time?? Can a QSFP port be used with an FPGA?? Does a visual representation of the latent space enhance our understanding of network traffic?? What is QSFP QSFP (Quad Small Form-Factor Pluggable)? QSFP supports transfer speeds generally up to 100Gb/s? Runs 4 parallel lines running up to 28 Gb/s? Why the latent space is important to our project ?Latent space is the compressed mapping of data points in a non-linear fashion? Create an understanding of the relationship of data collected? Can represent that relationship of a single network packet in 3 points (X, Y, Z) Project Outline FPGA? Custom Xilinx Petalinux Image for the operating system? Python program to collect packets and run them through the DPU (Data Processing Unit)? The program then sends the information over a socket to a computer? Display Program? Python Program that collects the information sent from the FPGA and display it in a graph

99 GENERAL AND MISCELLANEOUS↗

Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning

Background: We developed machine-learning (ML) models to estimate a patient’s risk of cardiac death based on adenosine myocardial perfusion SPECT (MPS) and associated clinical data, and compared their performance to baseline logistic regression (LR). We demonstrated an approach to visually convey the reasoning behind a patient’s risk to provide insight to clinicians beyond that of a “black box.” Methods: We trained multiple models using 122 potential clinical predictors (features) for 8321 patients, including 551 cases of subsequent cardiac death. Accuracy was measured by area under the ROC curve (AUC), computed within a cross-validation framework. We developed a method to display the model’s rationale to facilitate clinical interpretation. Results: The baseline LR (AUC = 0.76; 14 features) was outperformed by all other methods. A least absolute shrinkage and selection operator (LASSO) model (AUC = 0.77; p = .045; 6 features) required the fewest features. A support vector machine (SVM) model (AUC = 0.83; p < .0001; 49 features) provided the highest accuracy. Conclusions: LASSO outperformed LR in both accuracy and simplicity (number of features), with SVM yielding best AUC for prediction of cardiac death in patients undergoing MPS. Combined with presenting the reasoning behind the risk scores, our results suggest that ML can be more effective than LR for this application.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Data optimization for large batch distributed training of deep neural networks

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and model accuracy deterioration with an increase in global batch size. Present solutions focus on improving message exchange efficiency as well as implementing techniques to tweak batch sizes and models in the training process. The loss of training accuracy typically happens because the loss function gets trapped in a local minima. We observe that the loss landscape minimization is shaped by both the model and training data and propose a data optimization approach that utilizes machine learning to implicitly smooth out the loss landscape resulting in fewer local minima. Our approach filters out data points which are less important to feature learning, enabling us to speed up the training of models on larger batch sizes to improved accuracy.

Gahlot, Shubhankar↗

Photovoltaic System Health-State Architecture for Data-Driven Failure Detection

The timely detection of photovoltaic (PV) system failures is important for maintaining optimal performance and lifetime reliability. A main challenge remains the lack of a unified health-state architecture for the uninterrupted monitoring and predictive performance of PV systems. To this end, existing failure detection models are strongly dependent on the availability and quality of site-specific historic data. The scope of this work is to address these fundamental challenges by presenting a health-state architecture for advanced PV system monitoring. The proposed architecture comprises of a machine learning model for PV performance modeling and accurate failure diagnosis. The predictive model is optimally trained on low amounts of on-site data using minimal features and coupled to functional routines for data quality verification, whereas the classifier is trained under an enhanced supervised learning regime. The results demonstrated high accuracies for the implemented predictive model, exhibiting normalized root mean square errors lower than 3.40% even when trained with low data shares. The classification results provided evidence that fault conditions can be detected with a sensitivity of 83.91% for synthetic power-loss events (power reduction of 5%) and of 97.99% for field-emulated failures in the test-bench PV system. Finally, this work provides insights on how to construct an accurate PV system with predictive and classification models for the timely detection of faults and uninterrupted monitoring of PV systems, regardless of historic data availability and quality. Such guidelines and insights on the development of accurate health-state architectures for PV plants can have positive implications in operation and maintenance and monitoring strategies, thus improving the system’s performance.

photovoltaics↗

Operator inference with roll outs for learning reduced models from scarce and low-quality data

Data-driven modeling has become a key building block in computational science and engineering. However, data that are available in science and engineering are typically scarce, often polluted with noise and affected by measurement errors and other perturbations, which makes learning the dynamics of systems challenging. Here, in this work, we propose to combine data-driven modeling via operator inference with the dynamic training via roll outs of neural ordinary differential equations. Operator inference with roll outs inherits interpretability, scalability, and structure preservation of traditional operator inference while leveraging the dynamic training via roll outs over multiple time steps to increase stability and robustness for learning from low-quality and noisy data. Numerical experiments with data describing shallow water waves and surface quasi-geostrophic dynamics demonstrate that operator inference with roll outs provides predictive models from training trajectories even if data are sampled sparsely in time and polluted with noise of up to 10%.

97 MATHEMATICS AND COMPUTING↗

Grooved electrodes for high-power-density fuel cells

Proton exchange membrane fuel cells (PEMFCs) are leading candidates to decarbonize the transport sector, but widespread deployment will require improvements in lifetime, fuel economy and cost. Here we present the grooved electrode, an alternative electrode structure that enhances PEMFC performance and durability by coupling high ionomer (ion-conducting binder) content for improved H + transport with grooves for rapid O 2 transport. Grooved electrodes provide up to 50% higher performance than state-of-the-art conventional electrodes under standard operating conditions. Fuel cell diagnostics combined with multiphysics modelling demonstrate that grooved electrodes provide facile O 2 transport despite their high ionomer content, enabling improved reaction rate uniformity. Grooved electrodes also provide improved durability, with less performance loss after carbon corrosion compared with baseline electrodes. Machine learning analysis demonstrates the potential to further optimize grooved structures for next-generation PEMFCs with enhanced performance and durability, enabling smaller and cheaper fuel cell stacks with higher fuel efficiency.

25 ENERGY STORAGE↗

Forecasting induced seismicity in Oklahoma using machine learning methods

Oklahoma earthquakes in the past decade have been mostly associated with wastewater injection. Here we use a machine learning technique—the Random Forest to forecast induced seismicity rate in Oklahoma based on injection-related parameters. We split the data into training (2011.01–2015.05) and test (2015.06–2020.12) periods. The model forecasts seismicity rate during the test period based on input features, including operational parameters (injection rate and pressure), geological information (depth to basement), and modeled pore pressure and poroelastic stress. The results show overall good match with observed seismicity rate (adjusted R 2 of 0.75). The model shows that pore pressure rate and poroelastic stressing rates are the two most important features in forecasting. The absolute values of pore pressure and poroelastic stress, and the injection rate itself, are less important than the stressing rates. These findings further emphasize that temporal changes of stressing rates would lead to significant changes in seismicity rates.

58 GEOSCIENCES↗

Nuclear Data Adjustment for Nonlinear Applications in the OECD/NEA WPNCS SG14 Benchmark—A Bayesian Inverse UQ-Based Approach for Data Assimilation

The Organisation for Economic Co-operation and Development Working Party on Nuclear Criticality Safety has proposed a benchmark exercise to assess the performance of current nuclear data adjustment techniques applied to nonlinear applications and experiments with low correlation to applications. This work introduces Bayesian inverse uncertainty quantification (IUQ) employing scientific machine learning surrogate models as a method for nuclear data adjustments in this benchmark, and compares IUQ to the more traditional methods of generalized linear least squares (GLLS) and Monte Carlo Bayes (MOCABA). Posterior predictions from IUQ showed agreement with GLLS and MOCABA for linear applications. Here, when comparing GLLS, MOCABA, and IUQ posterior predictions to computed model responses using adjusted parameters, we observe that the GLLS predictions failed to replicate the computed response distributions for nonlinear applications, while MOCABA showed near agreement, and IUQ used the computed model responses directly. We also discuss observations on why experiments with low correlation to applications can be informative to nuclear data adjustments and identify some properties useful in selecting experiments for inclusion in nuclear data adjustment. Performance in this benchmark indicates potential for Bayesian IUQ in nuclear data adjustments.

Bayesian calibration↗

Evolving Energy Efficient Convolutional Neural Networks

As deep neural networks have been deployed in more and more applications over the past half decade and are finding their way into an ever increasing number of operational systems, their energy consumption becomes a concern whether running in the datacenter or on edge devices. Hyperparameter optimization and automated network design for deep learning is a quickly growing field, but much of the focus has remained only on optimizing for the performance of the machine learning task. In this work, we demonstrate that the best performing networks created through this automated network design process have radically different computational characteristics (e.g. energy usage, model size, inference time), presenting the opportunity to utilize this optimization process to make deep learning networks more energy efficient and deployable to smaller devices. Optimizing for these computational characteristics is critical as the number of applications of deep learning continues to expand.

Young, Steven↗

A Combined Computer Vision and Deep Learning Approach for Rapid Drone-Based Optical Characterization of Parabolic Troughs

Optical accuracy is a primary driver of parabolic trough concentrating solar power (CSP) plant performance, but can be damaged by wind loads, gravity, error during installation, and regular plant operation. Collecting and analyzing optical measurements over an entire operating parabolic trough plant is difficult, given the large scale of typical installations. Distant Observer, a software tool developed at the National Renewable Energy Laboratory, uses images of the absorber tube reflected in the collector mirror to measure both surface slope in the parabolic mirror and offset of the absorber tube from the ideal focal point. This technology has been adapted for fast data collection using low-cost commercial drones, but until recently still required substantial human labor to process large amounts of data. A new method leveraging advanced deep learning and computer vision tools can drastically reduce the time required to process images. This new method addresses the primary analysis bottleneck, identifying featureless, reflective mirror corner points to a high degree of accuracy. Recent work has shown promising results using computer vision methods. The combined deep learning and computer vision approach presented here proved highly effective and has the potential to further automate data collection and analysis, making the tool more robust. The method presented in this paper automatically identified 74.3% of mirror corners within 2 pixels of their manually marked counterparts and 91.9% within 3 pixels. This level of accuracy is sufficient for practical Distant Observer analysis within a target uncertainty. A commercial drone collected video of over 100 parabolic trough modules at an operating CSP plant to demonstrate the deep learning and computer vision method's usefulness in processing large amounts of data. These troughs were successfully analyzed using Distant Observer, paired with the new deep learning and computer vision algorithm, and can provide plant operators and trough designers with valuable insight about plant performance, operating strategies, and plant-wide optical error trends.

computer vision↗

Hybrid Manufacturing of Conformal Cooling Channels for Tooling

Computer-aided manufacturing (CAM) techniques for hybrid manufacturing have led to new application areas in the manufacturing industry. In the tooling industry, cooling channels are used to enable specific heating and cooling cycles to improve the performance of the process. These internal cooling channels have been designed with limited manufacturing processes in mind, so, until recently, they were often straight in shape for cross-drilling operations and manufactured from a cast billet. To show a novel application of this common technology, a tool with integrated conformal cooling channels was manufactured using hybrid manufacturing (blown-powder DED and CNC machining) techniques. The computer-aided manufacturing strategy used, and the lessons learned are presented and discussed to enable future work in this industrial application space.

36 MATERIALS SCIENCE↗