Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Neural Networks”

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 973 records · Page 54

Chasing Accreted Structures within Gaia DR2 Using Deep Learning

In previous work, we developed a deep neural network classifier that only relies on phase-space information to obtain a catalog of accreted stars based on the second data release of Gaia (DR2). In this paper, we apply two clustering algorithms to identify velocity substructure within this catalog. We focus on the subset of stars with line-of-sight velocity measurements that fall in the range of Galactocentric radii $r\in [6.5,9.5]\,{\rm{kpc}}$ and vertical distances $| z| \lt 3\,{\rm{kpc}}$. Known structures such as Gaia Enceladus and the Helmi stream are identified. The largest previously unknown structure, Nyx, is a vast stream consisting of at least 200 stars in the region of interest. This study displays the power of the machine-learning approach by not only successfully identifying known features but also discovering new kinematic structures that may shed light on the merger history of the Milky Way.

Astronomy & Astrophysics↗

DeepZipper: A Novel Deep-learning Architecture for Lensed Supernovae Identification

Large-scale astronomical surveys have the potential to capture data on large numbers of strongly gravitationally lensed supernovae (LSNe). To facilitate timely analysis and spectroscopic follow-up before the supernova fades, an LSN needs to be identified soon after it begins. To quickly identify LSNe in optical survey data sets, we designed ZipperNet, a multibranch deep neural network that combines convolutional layers (traditionally used for images) with long short-term memory layers (traditionally used for time series). We tested ZipperNet on the task of classifying objects from four categories—no lens, galaxy-galaxy lens, lensed Type-Ia supernova, lensed core-collapse supernova—within high-fidelity simulations of three cosmic survey data sets: the Dark Energy Survey, Rubin Observatory’s Legacy Survey of Space and Time (LSST), and a Dark Energy Spectroscopic Instrument (DESI) imaging survey. Among our results, we find that for the LSST-like data set, ZipperNet classifies LSNe with a receiver operating characteristic area under the curve of 0.97, predicts the spectroscopic type of the lensed supernovae with 79% accuracy, and demonstrates similarly high performance for LSNe 1–2 epochs after first detection. We anticipate that a model like ZipperNet, which simultaneously incorporates spatial and temporal information, can play a significant role in the rapid identification of lensed transient systems in cosmic survey experiments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Artificial Intelligence Assisted Inversion (AIAI): Quantifying the Spectral Features of 56 Ni of Type Ia Supernovae

Abstract Following our previous study of Artificial Intelligence Assisted Inversion (AIAI) of supernova analyses, we train a set of deep neural networks based on the 1D radiative transfer code TARDIS to simulate the optical spectra of Type Ia supernovae (SNe Ia) between 10 and 40 days after the explosion. The neural networks are applied to derive the mass of 56 Ni in velocity ranges above the photosphere for a sample of 124 well-observed SNe Ia in the TARDIS model context. A subset of the SNe have multi-epoch observations for which the decay of the radioactive 56 Ni can be used to test the AIAI quantitatively. The 56 Ni mass derived from AIAI using the observed spectra as inputs for this subset agrees with the radioactive decay rate of 56 Ni. AIAI reveals that a spectral signature near 3890 Å is related to the Niii4067Å line, and the 56 Ni mass deduced from AIAI is found to be correlated with the light-curve shapes of SNe Ia, with SNe Ia with broader light curves showing larger 56 Ni mass in the envelope above the photosphere. AIAI enables spectral data of SNe to be quantitatively analyzed under theoretical frameworks based on well-defined physical assumptions.

Astronomy & Astrophysics↗

Comparing theory based and higher-order reduced models for fusion simulation data

We consider using regression to fit a theory-based log-linear ansatz, as well as higher order approximations, for the thermal energy confinement of a Tokamak as a function of device features. We use general linear models based on total order polynomials, as well as deep neural networks. The results indicate that the theory-based model fits the data almost as well as the more sophisticated machines, within the support of the data set. The conclusion we arrive at is that only negligible improvements can be made to the theoretical model, for input data of this type.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Technical note: Deep learning for creating surrogate models of precipitation in Earth system models

Abstract. We investigate techniques for using deep neural networks to produce surrogatemodels for short-term climate forecasts. A convolutional neural network istrained on 97 years of monthly precipitation output from the 1pctCO2 run (theCO 2 concentration increases by 1 % per year) simulated by the second-generation Canadian Earth System Model (CanESM2). The neural network clearly outperforms a persistence forecast anddoes not show substantially degraded performance even when the forecast lengthis extended to 120 months. The model is prone to underpredicting precipitationin areas characterized by intense precipitation events. Scheduled sampling(forcing the model to gradually use its own past predictions rather than groundtruth) is essential for avoiding amplification of early forecasting errors.However, the use of scheduled sampling also necessitates preforecasting(generating forecasts prior to the first forecast date) to obtain adequateperformance for the first few prediction time steps. We document the trainingprocedures and hyperparameter optimization process for researchers who wish toextend the use of neural networks in developing surrogate models.

54 ENVIRONMENTAL SCIENCES↗

Building a machine learning surrogate model for wildfire activities within a global Earth system model

Abstract. Wildfire is an important ecosystem process, influencing land biogeophysical and biogeochemical dynamics and atmospheric composition. Fire-driven loss of vegetation cover, for example, directly modifies the surface energy budget as a consequence of changing albedo, surface roughness, and partitioning of sensible and latent heat fluxes. Carbon dioxide and methane emitted by fires contribute to a positive atmospheric forcing, whereas emissions of carbonaceous aerosols may contribute to surface cooling. Process-based modeling of wildfires in Earth system land models is challenging due to limited understanding of human, climate, and ecosystem controls on fire counts, fire size, and burned area. Integration of mechanistic wildfire models within Earth system models requires careful parameter calibration, which is computationally expensive and subject to equifinality. To explore alternative approaches, we present a deep neural network (DNN) scheme that surrogates the process-based wildfire model with the Energy Exascale Earth System Model (E3SM) interface. The DNN wildfire model accurately simulates observed burned area with over 90 % higher accuracy with a large reduction in parameterization time compared with the current process-based wildfire model. The surrogate wildfire model successfully captured the observed monthly regional burned area during validation period 2011 to 2015 (coefficient of determination, R2=0.93). Since the DNN wildfire model has the same input and output requirements as the E3SM process-based wildfire model, our results demonstrate the applicability of machine learning for high accuracy and efficient large-scale land model development and predictions.

58 GEOSCIENCES↗

Knowledge-informed deep learning for hydrological model calibration: an application to Coal Creek Watershed in Colorado

Abstract. Deep learning (DL)-assisted inverse mapping has shown promise in hydrological model calibration by directly estimating parameters from observations. However, the increasing computational demand for running the state-of-the-art hydrological model limits sufficient ensemble runs for its calibration. In this work, we present a novel knowledge-informed deep learning method that can efficiently conduct the calibration using a few hundred realizations. The method involves two steps. First, we determine decisive model parameters from a complete parameter set based on the mutual information (MI) between model responses and each parameter computed by a limited number of realizations (∼50). Second, we perform more ensemble runs (e.g., several hundred) to generate the training sets for the inverse mapping, which selects informative model responses for estimating each parameter using MI-based parameter sensitivity. We applied this new DL-based method to calibrate a process-based integrated hydrological model, the Advanced Terrestrial Simulator (ATS), at Coal Creek Watershed, CO. The calibration is performed against observed stream discharge (Q) and remotely sensed evapotranspiration (ET) from the water year 2017 to 2019. Preliminary MI analysis on 50 realizations resulted in a down-selection of 7 out of 14 ATS model parameters. Then, we performed a complete MI analysis on 396 realizations and constructed the inverse mapping from informative responses to each of the selected parameters using a deep neural network. Compared with calibration using observations covering all time steps, the new inverse mapping improves parameter estimations, thus enhancing the performance of ATS forward model runs. The Nash–Sutcliffe efficiency (NSE) of streamflow predictions increases from 0.53 to 0.8 when calibrating against Q alone. Using ET observations, on the other hand, does not show much improvement on the performance of ATS modeling mainly due to both the uncertainty of the remotely sensed product and the insufficient coverage of the model ET ensemble in capturing the observation. By using observed Q only, we further performed a multiyear analysis and show that Q is best simulated (NSE > 0.8) by including in the calibration the dry-year flow dynamics that show more sensitivity to subsurface characteristics than the other wet years. Moreover, when continuing the forward runs till the end of 2021, the calibrated models show similar simulation performances during this evaluation period as the calibration period, demonstrating the ability of the estimated parameters in capturing climate sensitivity. Our success highlights the importance of leveraging data-driven knowledge in DL-assisted hydrological model calibration.

54 ENVIRONMENTAL SCIENCES↗

Informed Feature Selection for Data Clustering of CSP Plant Production

To make concentrating solar power (CSP) more cost competitive, rigourous optimizations must be run to improve plant design and operations. However, these optimizaitons rely on time consuming annual simulations that solve an electricity dispatch scheduling problem to maximize plant revenue. To reduce the runtime of annual dispatch simulations of CSP plants, a data clustering approach is utilized. This approach assumes that like days of revenue and electricity generation can be identified using weather and price data. Although weather and price are important factors for electricity production, this work investigates how thermal energy storage (TES) inventory at the beginning of a day, denoted as Si, can be used as a supplemental feature to group like days. A framework for creating and training a deep neural network to predict Si is proposed. This model is validated and assessed using eleven sets of testing data that were not used during training. Then, the data clustering approach is performed three seperate times with features of weather and price along with either Si from the neural network, Si from the full annual simulation, or no Si. Ultimately, the results suggest that using Si as an additional clustering feature improves the data clustering simulation accuracy by 1.4%.

Tuman, Matthew J. (ORCID:000900038772051X)↗

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

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

54 ENVIRONMENTAL SCIENCES↗

Future of Big Earth Data Analytics

The state of the art of Big Earth Data Analytics can be expected to evolve rapidly in the coming years. The forces driving evolution come from both growth in the data and advancement in the field of data analytics. In the data area, advances in sensor instrumentation and platform miniaturization are increasing both data resolution and coverage, resulting in enormous growth in data Volume. Increases in temporal resolution in particular also generate demands for higher data Velocity. At the same time, the proliferation of instruments and the platforms on which they reside is increasing the Variety of datasets. The Variety increase in turn leads to questions about the Veracity of the data. In the algorithm area, powerful machine learning methods are coming to the fore, particularly Deep Neural Networks. These are powerful at detecting interesting features in the data, integrating many different measurements (i.e., data fusion), and classification problems. However, they are still challenging when seeking explanations of how natural or socio-economic phenomena work using Earth Observations. Thus, classical analysis techniques will remain relevant when the emphasis is on forming or testing explanations, as well as to support interactive data exploration.

Lynnes, Christopher↗

Automatically Finding Ship-Tracks to Enable Large-Scale Analysis of Aerosol-Cloud Interactions

Ship tracks appear as long winding linear features in satellite images and are produced by aerosols from ship exhausts changing low cloud properties. They are one of the best examples of aerosol‐cloud interaction experiments. However, manually finding ship tracks from satellite data on a large scale is prohibitively costly while a large number of samples are required to improve our understanding. Here we train a deep neural network to automate finding ship tracks. The neural network model generalizes well as it not only finds ship tracks labeled by human experts but also detects those that are occasionally missed by humans. It finds more ship tracks than all previous studies combined and produces a map of ship track distributions off the California coast that matches well with known shipping traffic. Our technique will enable studying aerosol effects on low clouds using ship tracks on a large scale, which will potentially narrow the uncertainty of the aerosol‐cloud interactions.

aerosol cloud interactions↗

Are we ready for the first EASA guidance on the use of ML in Aviation?

NASA has been working for the past 12 years on software tools for the assurance of software in Aviation critical systems. For now two years, NASA has focused more on the use of AI-based techniques in Aviation than the traditional software systems used in the past. The primary focus has been on machine learning (ML), and more specifically, on supervised off-line learning ML systems. NSA’s research has been driven by case studies such as a vision-based centerline tracking system (implemented using deep neural networks) and the new generation of collision avoidance systems developed under the FAA guidance, i.e., the family of ACAS-X products. Since EASA has recently released its first usable guidance for Level 1 machine learning applications, it is opportunity to see how the research done at NASA is mapping to this first guidance for ML. In this talk I will use the EASA guidance document as a guide to present the past, present, and future tools and techniques being developed at NASA. The intent is to not only provide an overview of the research effort at NASA but also to see how this effort is addressing the concerns listed in the EASA first usable guidance for ML.

Guillaume Brat↗

Statistical learning framework for safety and failure analysis of a DNN-based autonomous aircraft system

Deep Neural Networks (DNNs) and Machine Learning technology is increasingly used for safety-critical applications in the Aerospace domain. To ensure safe operations, the DNN and the system must undergo rigorous verification and validation, including advanced statistical analyses. Performance and safety of the DNN and system behavior must not only be analyzed for the nominal case, but under numerous off-nominal and failure cases. In this paper we will describe how our statistical learning framework SYSAI can efficiently perform such analyses using the tool’s unique combination of advanced learning modeling and statistical analysis techniques. SYSAI can effectively explore the high-dimensional state and failure space of the system under test; geometrical shape detection of safety regions and boundaries support explainability of the results to the designer. In this paper, we report experiments and results obtained with a vision-based DNN control system (ACT) that is capable of autonomously steering an aircraft down a runway.

Yuning He↗

Toward Design Assurance of Machine-Learning Airborne Systems

In recent years, Artificial Intelligence (AI) systems, enabled by Machine Learning (ML)technology, have demonstrated impressive progress and provides historic opportunities for the aviation industry. However, several key aspects of ML technology are not compatible with existing design assurance standards and make certification problematic. In this paper, we present a case study of a visual system with a Deep Neural Network (DNN) intended to detect and identify airport runway signs. Different use cases and variants of this system exhibit different levels of criticality ranging from design assurance level (DAL) D to B. We use the case study to illustrate the challenges of certification according to the current standards, such asDO-178C. We present the system design, data generation, training, and verification in detail and describe how the design assurance objectives can be met for a DAL D variant of the system. We also discuss gaps and potential approaches for the higher design assurance levels.

Avionics↗

Machine-Learning for Safety Critical Airborne Applications Part II: Case Study

The exceptional progress in the field of Artificial Intelligence (AI) systems, enabled by Machine Learning (ML) technology in recent years provides historic opportunities for the aviation industry. Current certification standards for avionics were developed prior to the ML renaissance and have several fundamental incompatibilities with the ML technology. WG-114 is working hard to release a new standard as soon as possible but for now there is no recognized means of compliance for ML based systems even of low criticality. In this talk, we present the custom ML workflow that can be used comply with all objectives of the current certification standards for a low-criticality (DAL D and C) ML-based system. To illustrate the practical application of the custom ML workflow we present a case study of a system based on a Deep Neural Network (DNN) intended to detect and identify airport runway signs. We present the system design, data generation, training, and verification in detail and describe how the design assurance objectives can be met for a DAL D and DAL C systems.

Johann Schumann↗

Super-Resolution from Space: Using MERRA-2 and MAIAC Satellite Imagery to Produce Daily Continuous 1 km PM2.5 Estimates

PM2.5 measurements from ground stations are the gold standard when available, but the expense and coverage of such stations limits widespread monitoring. Having accurate PM2.5 estimates outside the range of these stations is important for monitoring this crucial aspect of air quality. The goal of this project is to produce daily 1 km continuous PM2.5 estimates for the contiguous US relying primarily on satellite-derived data sources. This is important because models based on such data can be more easily expanded outside the study area and produce global estimates as well. The temporal availability of such data products is often weekly/daily, unlike land-use products with are often available at a yearly or worse temporal resolution. To achieve our goal, we use a couple of different deep neural network architectures to produce PM2.5 measurements at 10 km and 1 km resolution. We use two model architectures, a UNET-like model and a GAN-based model. We train both models using MERRA-2 data and MAIAC AOD data scaled to 10 km and 1 km for the two different prediction resolutions. MERRA-2 imagery is data rich with a wide range of geospatial variables at 50 km and has long historical availability (beginning in 1980). We’re also using higher spatial resolution MAIAC data at 1 km to provide finer resolution spatial context. This essentially leverages the spatial resolution of MAIAC data and the “wider” information of MERRA-2 data to predict PM2.5. For the target data we’re using a modeled 1 km PM2.5 dataset produced by Harvard to pre-train our models and then fine-tune our models using ground station measurements. Not only are our results comparable with the performance of the Harvard dataset, but can be generalized to any area or time where MERRA-2 and MAIAC data is available.

satellite imagery↗

Radiation Tolerance and Mitigation for Neuromorphic Processors

Neuromorphic processors are designed to execute Deep Neural Networks (DNNs) at very high speed using only a fraction of the electrical power needed to run a DNN on a traditional CPU or GPU. This unique capability makes Neuromorphic processors a prime candidate for space systems, where advanced computational tasks like image analysis, depth map reconstruction, or rover control need to be executed in a power-starved environment. In contrast to the growing number of applications of Neuromorphic processors in smart phones, the automotive and robotics domain, the space environment is unforgiving because of extreme temperatures and high levels of radiation. Any space system, operating beyond LEO requires computing hardware that is resilient against radiation effects. However, Neuromorphic processors have not yet been designed or tested for their radiation tolerance. In this report, we consider traditional methods of detection of radiation events and mitigation via redundancy and gauge their effectiveness on DNNs. In contrast to traditional flight software, however, neural networks represent a statistical algorithm, which might affect its resilience against radiation events. We will focus on the analysis of the tolerance of DNNs with respect to radiation events and discuss techniques to detect radiation hits using on-chip triple modular redundancy (TMR) on an Intel Loihi neuromorphic processor and to mitigate radiation damage. We describe an architecture for on-chip TMR for the Intel Loihi and present results of initial experiments.

Neural Networks↗

Machine-Learned Committor Functions for Reactive Molecular Dynamics

Reactive molecular dynamics (MD) is a powerful tool for atomistic-scale modeling of a diverse range of chemical processes. However, scaling these simulations to large systems and long times scales remains a challenge because of the complexity of the potential energy function required. The authors previously developed a heuristic approach, called REACTER, that incorporates reactivity in MD simulations in a less general but much more computationally efficient manner. REACTER uses standard, fixed valence force fields as the underlying potentialenergy surface for describing all interatomic interactions but adds a procedure for enforcing user-defined reactions that occur when certain geometric constraints on relative atomic positions are satisfied. Further, these bonding changes can be accepted or rejected with a probability related tothe local thermal energy. This work seeks to generalize this approach by replacing the set of user defined geometric constraints and energetic criteria with a committor function that specifies the probability of a reaction occurring on the basis of the local atomic configuration. The committor function is a useful mathematical tool for modeling rare events but, unfortunately, is very difficult to compute for realistic systems in a general way. This work describes a method for approximating the committor function using a machine learning approach, specifically a deep neural network trained with data from reactive MD and DFT-based dynamics simulations. This network is coupled to the existing REACTER protocol, as implemented in the LAMMPS MD package, and used to make on-the-fly predictions of reaction probabilities without the more extensive user input previously required. The new method is demonstrated using the polymerization of polystyrene as a case study. Although very dependent on the quality and quantity of training data, machine-learned committor functions show promise as a method for incorporating reaction probability from higher level calculations into highly scalable MD simulations.

polymer simulations↗