Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Continual 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 559 records · Page 31

Assembly and Integrated Systems Testing for the Flow Boiling and Condensation Experiment (FBCE)

The Flow Boiling and Condensation Experiment (FBCE) is a flight experiment that is designed to operate in the Fluids Integrated Rack (FIR) on the International Space Station (ISS). The objective of the FBCE is to develop an integrated two-phase flow experiment that will serve as a primary platform for obtaining flow boiling and condensation heat transfer data in microgravity. This data will enable the design and analysis of two-phase thermal management systems for future NASA missions that require increased efficiency beyond the current single-phase systems. The FBCE consists of seven modules, each of which must link together mechanically, electrically, and fluidically upon final integration. Five of the modules provide the fluidic and electronic components required to bring the test fluid to the inlet conditions required by the test module, where the primary science is conducted. These inlet conditions encompass fluid quality ranging from a superheated vapor to a subcooled liquid at a variety of flow rates and pressures. The FBCE is currently manufacturing two test modules, each of which has its own separate test campaign with the five support modules. Each of the modules presents a unique challenge in its assembly and checkout, particularly related to ensuring the final hardware configuration can meet the fluid and thermal requirements levied upon them. Following assembly, a series of flight verification tests will be performed, including thermal testing, EMI testing, and final integration in a FIR Ground Integration Unit. This presentation discusses the status of the FBCE as it continues through final verification testing, including current test results and lessons learned throughout the assembly and integration phase of the project. In addition, future options for additional flight test sections will be explored that will benefit the broader NASA thermal and fluids community.

deFiebre, Jesse↗

Simultaneous Retrieval of Selected Optical Water Quality Indicators From Landsat-8, Sentinel-2, and Sentinel-3

Constructing multi-source satellite-derived water quality (WQ) products in inland and nearshore coastal waters from the past, present, and future missions is a long-standing challenge. Despite inherent differences in sensors’ spectral capability, spatial sampling, and radiometric performance, research efforts focused on formulating, implementing, and validating universal WQ algorithms continue to evolve. This research extends a recently developed machine-learning (ML) model, i.e., Mixture Density Networks (MDNs) (Pahlevan et al., 2020; Smith et al., 2021), to the inverse problem of simultaneously retrieving WQ indicators, including chlorophyll-a (Chla), Total Suspended Solids (TSS), and the absorption by Colored Dissolved Organic Matter at 440 nm (a cdom (440)), across a wide array of aquatic ecosystems. We use a database of in situ measurements to train and optimize MDN models developed for the relevant spectral measurements (400–800 nm) of the Operational Land Imager (OLI), MultiSpectral Instrument (MSI), and Ocean and Land Color Instrument (OLCI) aboard the Landsat-8, Sentinel-2, and Sentinel-3 missions, respectively. Our two performance assessment approaches, namely hold-out and leave-one-out, suggest significant, albeit varying degrees of improvements with respect to second-best algorithms, depending on the sensor and WQ indicator (e.g., 68%, 75%, 117% improvements based on the hold-out method for Chla, TSS, and a cdom (440), respectively from MSI-like spectra). Using these two assessment methods, we provide theoretical upper and lower bounds on model performance when evaluating similar and/or out-of-sample datasets. To evaluate multi-mission product consistency across broad spatial scales, map products are demonstrated for three near-concurrent OLI, MSI, and OLCI acquisitions. Overall, estimated TSS and a cdom (440) from these three missions are consistent within the uncertainty of the model, but Chla maps from MSI and OLCI achieve greater accuracy than those from OLI. By applying two different atmospheric correction processors to OLI and MSI images, we also conduct matchup analyses to quantify the sensitivity of the MDN model and best-practice algorithms to uncertainties in reflectance products. Our model is less or equally sensitive to these uncertainties compared to other algorithms. Recognizing their uncertainties, MDN models can be applied as a global algorithm to enable harmonized retrievals of Chla, TSS, and a cdom (440) in various aquatic ecosystems from multi-source satellite imagery. Local and/or regional ML models tuned with an apt data distribution (e.g., a subset of our dataset) should nevertheless be expected to outperform our global model.

Machine learning↗

Cyber Resiliency and the Implementation of a Host-Based Intrusion Detection System in an Urban Air Mobility Environment

With the growth in urban air mobility systems and the increasing reliance on interconnected technologies, ensuring the security of these complex infrastructures has become critical. As cities evolve into smart urban centers, the vulnerability to cyber threats escalates, possibly endangering citizens’ safety and the efficiency of transportation networks. In response to these challenges, this paper presents a study on implementing a Host-Based Intrusion Detection System (HIDS) tailored explicitly to urban mobility environments’ unique demands. This study explores the design, development, and deployment of the proposed HIDS, focusing on its adaptability to monitor the hybrid nature of the urban mobility environment. Leveraging machine learning algorithms and anomaly detection techniques, the HIDS is equipped to continuously monitor and analyze the behavior of individual host systems, vehicles, and devices, thereby providing a proactive approach to threat detection. Implementing a HIDS is a pivotal strategy for enhancing cyber resiliency, as it gives an organization granular visibility into internal system activities, enables rapid detection and response to anomalous behavior and cyber threats, and fortifies the organization’s overall cybersecurity posture. In conclusion, this paper highlights the significance of host-based intrusion detection in urban mobility environments and underscores the necessity of tailored security solutions to safeguard against emerging cyber threats.

UAM↗

Hydrogen milestone could help lower fossil fuel refining costs

Hydrogen researchers at the U.S. Department of Energy's Idaho National Laboratory have reached another milestone on the road to reducing carbon emissions and protecting the nation against the effects of peaking world oil production. Stephen Herring, laboratory fellow and technical director of the INL High Temperature Electrolysis team, today announced that the latest fuel cell modification has set a new mark in endurance. The group's Integrated Laboratory Scale experiment has now operated continuously for 2,583 hours at higher efficiencies than previously attained. Learn more about INL research at http://www.facebook.com/idahonationallaboratory.

08 HYDROGEN↗

The Waste Isolation Pilot Plant Deep Geological Repository: A Domestic and Global Blueprint for Safe Disposal of High-Level Radioactive Waste - 12081

At the end of 2011, the world's first used/spent nuclear fuel and other long-lived high-level radioactive waste (HLW) repository is projected to open in 2020, followed by two more in 2025. The related pre-opening periods will be at least 40 years, as it also would be if USA's candidate HLW-repository is resurrected by 2013. If abandoned, a new HLW-repository site would be needed. On 26 March 1999, USA began disposing long-lived radioactive waste in a deep geological repository in salt at the Waste Isolation Pilot Plant (WIPP) site. The related pre-opening period was less than 30 years. WIPP has since been re-certified twice. It thus stands to reason the WIPP repository is the global proof of principle for safe deep geological disposal of long-lived radioactive waste. It also stands to reason that the lessons learned since 1971 at the WIPP site provide a unique, continually-updated, blueprint for how the pre-opening period for a new HLW repository could be shortened both in the USA and abroad. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

CSA, the French LILW Disposal Facility: Taking Stock of the 30 years' Operating Experience - 20009

French Andra's currently operational LILW repository, Aube disposal facility, is almost 30 years old. From the beginning, the repository has benefited from the lessons learned from the first disposal facility, the CSM. It has nevertheless continued to evolve, to improve and to adapt, seeking to gain in efficiency, safety and cost optimization. This is a look at what has changed at the CSA since 1992 - and the effect these changes had on its operating practices, construction principles and the entire management organization. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Adaptive Stress Testing of Collision Avoidance Systems for Small UASs with Deep Reinforcement Learning

The next-generation Airborne Collision Avoidance System for smaller UASs (ACAS sXu) is currently being developed and tested by the Federal Aviation Administration (FAA) to provide detect-and-avoid capability for small unmanned aircraft operating beyond line-of-sight. Due to the complexity and safety-critical nature of the system, safety validation is important not only for the certification of the final system, but also for informing changes during the iterative development process. In this paper, we analyze a prototype of ACAS sXu in simulated aircraft encounters to discover scenarios of small near mid-air collisions (sNMACs), an important safety event in which two aircraft come closer than 50 feet horizontally and 15 feet vertically. Due to the size and complexity of the system as well as rarity of sNMAC events, traditional methods such as Monte Carlo testing often require informed setup and targeting to elicit failures. However, such a dependence on domain knowledge can be incompatible with the independent verification and validation (IV&V) process, the aim of which is to discover unforeseen issues. To address these challenges, we apply an accelerated validation method called adaptive stress testing (AST) to find the most likely sNMAC scenarios without reliance on system introspection. AST uses reinforcement learning to adapt the search towards the most promising areas of the search space as it progresses. We use a state-of-the-art deep reinforcement learning algorithm, proximate policy optimization, to more efficiently search the large and continuous state space. We find that this approach significantly improves the performance of AST compared to a prior approach based on Monte Carlo tree search. We perform experiments using AST to find sNMAC events under various encounter configurations, varying parameters pertaining to dynamics and coordination. Our experiments show AST to be very effective at finding sNMAC scenarios. We summarize our findings, presenting high-level categories of discovered sNMACs and specific examples of encounters in each category.

aircraft collision avoidance↗

Solid-State Lighting: Early Lessons Learned on the Way to Market

The purpose of this report is to document early challenges and lessons learned in the solid-state lighting (SSL) market development as part of the DOE’s SSL Program efforts to continually evaluate market progress in this area. This report summarizes early actions taken by DOE and others to avoid potential problems anticipated based on lessons learned from the market introduction of compact fluorescent lamps and identifies issues, challenges, and new lessons that have been learned in the early stages of the SSL market introduction. This study identifies and characterizes12 key lessons that have been distilled from DOE SSL program results.

CFLs↗

A Dynamic PCA and Machine Learning Tool for Automated Identification of Solar Wind Disturbances Impacting Earth’s Magnetosphere

Earth’s magnetosphere is continuously impacted by solar wind and interplanetary magnetic field (IMF) disturbances, such as shocks, discontinuities, magnetic clouds and more. Understanding how such disturbances propagate from the Sun and what is their impact on the different magnetospheric domains is key to understanding and forecasting energy transfer from the solar wind to Earth. The large number of overlapping solar wind and magnetospheric missions carrying magnetometers and the recent advances in communications and data storage technologies have enabled an unprecedented quantity of high-fidelity magnetic field data captured by in-situ spacecraft to be available at the click of a button. However, this massive quantity of available data can prove unwieldy for researchers, limiting the identification of interesting phenomena and disturbances to a relatively small percentage of the total dataset. Several techniques have been previously developed for automated identification of specific types of magnetic anomalies, but these methods are typically mission-specific and can be difficult to generalize. We present initial results for a generic method of automated anomaly detection in magnetic field measurements based on dimensionality reduction and unsupervised clustering via machine learning. The benefit of our technique is its high degree of generalizability and flexibility which make it a most useful data survey tool for a wide range of magnetic field datasets. This method can also be applied simultaneously to other observed time-series properties like plasma density, pressure, and velocity for more accurate event identification. Additionally, the application of this method to data captured by multiple spacecraft enables the simultaneous identification of disturbances and the determination of their propagation characteristics. Initial evaluation of this technique has been performed using data from Magnetospheric MultiScale (MMS) and THEMIS-ARTEMIS missions, providing a testbed scenario for the future Heliophysics Environmental and Radiation Measurement Experiment Suite (HERMES) platform instruments that will measure solar wind and IMF properties from lunar orbit onboard the Gateway station.

Miguel Martinez-Ledesma↗

A Dynamic PCA and Machine Learning Tool for Automated Identification of Solar Wind Disturbances Impacting Earth’s Magnetosphere

Earth’s magnetosphere is continuously impacted by solar wind and interplanetary magnetic field (IMF) disturbances, such as shocks, discontinuities, magnetic clouds and more. Understanding how such disturbances propagate from the Sun and what is their impact on the different magnetospheric domains is key to understanding and forecasting energy transfer from the solar wind to Earth. The large number of overlapping solar wind and magnetospheric missions carrying magnetometers and the recent advances in communications and data storage technologies have enabled an unprecedented quantity of high-fidelity magnetic field data captured by in-situ spacecraft to be available at the click of a button. However, this massive quantity of available data can prove unwieldy for researchers, limiting the identification of interesting phenomena and disturbances to a relatively small percentage of the total dataset. Several techniques have been previously developed for automated identification of specific types of magnetic anomalies, but these methods are typically mission-specific and can be difficult to generalize. We present initial results for a generic method of automated anomaly detection in magnetic field measurements based on dimensionality reduction and unsupervised clustering via machine learning. The benefit of our technique is its high degree of generalizability and flexibility which make it a most useful data survey tool for a wide range of magnetic field datasets. This method can also be applied simultaneously to other observed time-series properties like plasma density, pressure, and velocity for more accurate event identification. Additionally, the application of this method to data captured by multiple spacecraft enables the simultaneous identification of disturbances and the determination of their propagation characteristics. Initial evaluation of this technique has been performed using data from Magnetospheric MultiScale (MMS) and THEMIS-ARTEMIS missions, providing a testbed scenario for the future Heliophysics Environmental and Radiation Measurement Experiment Suite (HERMES) platform instruments that will measure solar wind and IMF properties from lunar orbit onboard the Gateway station.

Miguel Martinez-Ledesma↗

Mapping Glacier Basal Sliding Applying Machine Learning

During the RESOLVE project (“High-resolution imaging in subsurface geophysics: development of a multi-instrument platform for interdisciplinary research”), continuous surface displacement and seismic array observations were obtained on Glacier d’Argentière in the French Alps for 35 days in May 2018. The data set is used to perform a detailed study of targeted processes within the highly dynamic cryospheric environment. In particular, the physical processes controlling glacial basal motion are poorly understood and remain challenging to observe directly. Especially in the Alpine region for temperate based glaciers where the ice rapidly responds to changing climatic conditions and thus, processes are strongly intermittent in time and heterogeneous in space. Spatially dense seismic and Global Positioning System (GPS) measurements are analyzed applying machine learning to gain insight into the processes controlling glacial motions of Glacier d’Argentière. Using multiple bandpass-filtered copies of the continuous seismic waveforms, we compute energy-based features, develop a matched field beamforming catalog and include meteorological observations. Features describing the data are analyzed with a gradient boosting decision tree model to directly estimate the GPS displacements from the seismic noise. We posit that features of the seismic noise provide direct access to the dominant parameters that drive displacement on the highly variable and unsteady surface of the glacier. The machine learning model infers daily fluctuations and longer term trends. The results show on-ice displacement rates are strongly modulated by activity at the base of the glacier. The techniques presented provide a new approach to study glacial basal sliding and discover its full complexity.

58 GEOSCIENCES↗

Collective I/O Tuning Using Analytical and Machine-Learning Models

The ever larger demand of scientific applications for computation and data is currently driving a continuous increase in scale of parallel computers. The inherent complexity of scaling up a computing systems in terms of both hardware and software stack exposes an increasing number of factors impacting the performance and complicating the process of optimization. In particular, the optimization of parallel I/O has become increasingly challenging due to increasing storage hierarchy and well known performance variability of shared storage systems. This paper focuses on model-based autotuning of the two-phase collective I/O algorithm from a popular MPI distribution on the Blue Gene/Q architecture. We propose a novel hybrid model, constructed as a composition of analytical models for communication and storage operations and black-box models for the performance of the individual operations. We perform an in-depth study of the complexity involved in performance modeling including architecture, software stack and noise. In particular we address this challenges of modeling the performance of shared storage systems by building a benchmark that helps synthesizing factors such as topology, file caching, and noise. The experimental results show that the hybrid approach produces significantly better results than state-of-the-art machine learning approaches and shows a higher robustness to noise, at the cost of a higher modeling complexity

I/O performance modeling↗

Near-zero photon bioimaging by fusing deep learning and ultralow-light microscopy

Enhancing the reliability and reproducibility of optical microscopy by reducing specimen irradiance continues to be an important biotechnology target. As irradiance levels are reduced, however, the particle nature of light is heightened, giving rise to Poisson noise, or photon sparsity that restricts only a few (0.5%) image pixels to comprise a photon. Photon sparsity can be addressed by collecting approximately 200 photons per pixel; this, however, requires long acquisitions and, as such, suboptimal imaging rates. Here, we introduce near-zero photon bioimaging, a method that operates at kHz rates and 10,000-fold lower irradiance than standard microscopy. To achieve this level of performance, we uniquely combined a judiciously designed epifluorescence microscope enabling ultralow background levels and AI that learns to reconstruct biological images from as low as 0.01 photons per pixel. We demonstrate that near-zero photon bioimaging captures the structure of multicellular and subcellular features with high fidelity, including features represented by nearly zero photons. Beyond optical microscopy, the near-zero photon bioimaging paradigm can be applied in remote sensing, covert applications, and biomedical imaging that utilize damaging or quantum light.

AI↗

Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?

The Southern Photometric Local Universe Survey (S-PLUS) is a novel project that aims to map the Southern Hemisphere using a twelve filter system, comprising five broad-band SDSS-like filters and seven narrow-band filters optimized for important stellar features in the local universe. In this paper we use the photometry and morphological information from the first S-PLUS data release (S-PLUS DR1) cross-matched to unWISE data and spectroscopic redshifts from Sloan Digital Sky Survey DR15. We explore three different machine learning methods (Gaussian Processes with GPz and two Deep Learning models made with TensorFlow) and compare them with the currently used template-fitting method in the S-PLUS DR1 to address whether machine learning methods can take advantage of the twelve filter system for photometric redshift prediction. Using tests for accuracy for both single-point estimates such as the calculation of the scatter, bias, and outlier fraction, and probability distribution functions (PDFs) such as the Probability Integral Transform (PIT), the Continuous Ranked Probability Score (CRPS) and the Odds distribution, we conclude that a deep-learning method using a combination of a Bayesian Neural Network and a Mixture Density Network offers the most accurate photometric redshifts for the current test sample. In conclusion, it achieves single-point photometric redshifts with scatter (σ NMAD ) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r_auto magnitudes between 16 and 21.

79 ASTRONOMY AND ASTROPHYSICS↗

Dust Machine Learning Probability and Assessment

- NASA SPoRT introduced the "Dust RGB" via NASA satellites to demonstrate GOES-R ABI capabilities and then evaluated the impact in operations (Fuell et al. 2016) - The Dust RGB allows for continued dust detection at night, but the cooling ground surface limits the effectiveness as night progresses. - SPoRT has developed a 'Machine Learning' (ML) model using a physically-based approach which can correctly label 85% of dust pixels and 99% of no-dust pixels

Dust↗

Exploring Applications of Machine Learning for Wildfire Monitoring and Detection using Unmanned Aerial Vehicles

Wildfires are increasing in frequency and severity around the world, including the United States. The losses caused by wildfires could be mitigated if high-risk areas, hotspots, and flare-ups could be monitored continuously, such as through the use of Unmanned Aerial Vehicles (UAVs). This paper documents exploratory efforts using machine learning to determine efficient flight paths for UAVs and to detect wildfires using image classification. On path planning, three machine learning techniques—Genetic Algorithm, Simulated Annealing, and Dynamic Programming—were explored. Genetic Algorithm was found to be an effective approach for path planning for wildfire monitoring and surveillance by UAVs. For a scenario of 25 locations in a circular arrangement, the algorithm was able to return the optimal path. The accuracy and execution time was found to be sensitive to the algorithm hyperparameters selected, which was especially evident in scenarios with hundreds or thousands of locations. Simulated Annealing was also found to be an effective approach for UAV path planning, with a major benefit of avoiding getting trapped in local minima and being straightforward to implement. Like Genetic Algorithm, the performance of Simulated Annealing was also found to be sensitive to the algorithm hyperparameters selected. By comparison, Dynamic Programming guarantees optimality for any number of locations, but it was found to be less practical in terms of execution time for scenarios with more than about a couple dozen locations. On wildfire detection, image classification using deep learning with a convolutional neural network was explored. Transfer learning was found to be a useful technique to efficiently train deep learning models. Also, it was determined that GPU processing can increase training speed by an order of magnitude, which enables significantly faster development. For a validation test set of 500 images, there were only two false negatives and zero false positives. These results demonstrate that detecting wildfires in static cameras using machine learning is feasible and establish a baseline for using images captured by UAVs in flight for wildfire detection.

Wildfire management↗

Uncertainty Aware Deep Learning for Fault Prediction Using Multivariate Time Series Signals

The superconducting radio-frequency cavities are a crucial component of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. When a cavity faults, beam delivery to experimental end users is disrupted. Prediction of cavity faults prior to onset is essential to reduce operation and maintenance costs. In this work, a parallel long short-term memory (LSTM)-convolution neural network (CNN)-based deep learning (DL) model is proposed to predict impending faults using pre-fault signals. Further, we introduce an uncertainty quantification approach using Monte Carlo dropout with the LSTM-CNN model to ascertain confidence in the prediction. The model was tested using multivariate time series signals from stable cavity operations and before faults. Initial results show that on the test dataset, the model can identify impending faults before their onset with an average 10-fold cross validation accuracy of 97.39% and a standard deviation of 0.12% using a 100-ms time window. It is also observed that the model performs better as the prediction time moves closer to the fault onset. For additional context, we compare the performance of the model with three machine-learning-based (ML) fault prediction models. Our proposed parallel LSTM-CNN-based DL method shows better performance than the ML-based methods.

Rahman, Md Monibor↗

Processed Lab Data for Neural Network-Based Shear Stress Level Prediction

Machine learning can be used to predict fault properties such as shear stress, friction, and time to failure using continuous records of fault zone acoustic emissions. The files are extracted features and labels from lab data (experiment p4679). The features are extracted with a non-overlapping window from the original acoustic data. The first column is the time of the window. The second and third columns are the mean and the variance of the acoustic data in this window, respectively. The 4th-11th column is the the power spectrum density ranging from low to high frequency. And the last column is the corresponding label (shear stress level). The name of the file means which driving velocity the sequence is generated from. Data were generated from laboratory friction experiments conducted with a biaxial shear apparatus. Experiments were conducted in the double direct shear configuration in which two fault zones are sheared between three rigid forcing blocks. Our samples consisted of two 5-mm-thick layers of simulated fault gouge with a nominal contact area of 10 by 10 cm^2. Gouge material consisted of soda-lime glass beads with initial particle size between 105 and 149 micrometers. Prior to shearing, we impose a constant fault normal stress of 2 MPa using a servo-controlled load-feedback mechanism and allow the sample to compact. Once the sample has reached a constant layer thickness, the central block is driven down at constant rate of 10 micrometers per second. In tandem, we collect an AE signal continuously at 4 MHz from a piezoceramic sensor embedded in a steel forcing block about 22 mm from the gouge layer The data from this experiment can be used with the deep learning algorithm to train it for future fault property prediction.

15 GEOTHERMAL ENERGY↗