SEARCH · Engineering Papers

Results for “Principal Component Analysis”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 523 records · Page 29

All sources NASA NTRS DOE OSTI

DOE OSTI2022

raogroupuiuc/lipo11557_growth

Project: Systems analysis of Lipomyces starkeyi during growth on various plant-based sugars Authors: Anshu Deewan*, Jing-Jing Liu*, Sujit Sadashiv Jagtap, Eun Ju Yun, Hanna E Walukiewicz, Yong-Su Jin, Christopher V Rao (* - co-authors) Abstract : Oleaginous yeasts have received significant attention due to their substantial lipids storage capability. The accumulated lipids can be utilized directly or processed into various bioproducts and biofuels. Lipomyces starkeyi is an oleaginous yeast capable of using multiple plant-based sugars, such as glucose, xylose, and cellobiose. It is, however, a relatively unexplored yeast due to limited knowledge about its physiology. In this study, we have evaluated the growth of L. starkeyi on different sugars and performed transcriptomic and metabolomic analyses to understand the underlying mechanisms of sugar metabolism. Principal component analysis showed clear differences resulting from growth on different sugars. We have further reported various metabolic pathways activated during growth on these sugars. We also observed non-specific regulation in L. starkeyi and have updated the gene annotations for the NRRL Y-11557 strain. This analysis provides a foundation for understanding the metabolism of these plant-based sugars and potentially valuable information to guide the metabolic engineering of L. starkeyi to produce bioproducts and biofuels.

Deewan, Anshu↗

DOE OSTI2018

Recurrent Neural Network Language Models for Open Vocabulary Event-Level Cyber Anomaly Detection

Automated analysis methods are crucial aids for monitoring and defending a network to protect the sensitive or confidential data it hosts. This work introduces a flexible, powerful, and unsupervised approach to detecting anomalous behavior in computer and network logs; one that largely eliminates domain-dependent feature engineering employed by existing methods. By treating system logs as threads of interleaved ``sentences'' (event log lines) to train online unsupervised neural network language models, our approach provides an adaptive model of normal network behavior. We compare the effectiveness of both standard and bidirectional recurrent neural network language models at detecting malicious activity within network log data. Extending these models, we introduce a tiered recurrent architecture, which provides context by modeling sequences of users' actions over time. Compared to isolation forests and Principal Components Analysis (PCA), two popular anomaly detection algorithms, we observe superior performance on the Los Alamos National Laboratory Cyber Security dataset. For log-line-level predictions, our best performing character-based model provides test set anomaly scores ranking red team events in the 98th percentile on average, and yields 0.97 area under the receiver operator characteristic curve, demonstrating the strong fine-grained anomaly detection performance of this approach on open vocabulary logging sources.

Cyber Analysis, Deep Learning, language analysis, ↗

DOE OSTI2024

Machine Learning-Driven Reliability Estimation of PV Inverters Considering Alert-Ambient Variability

Weather-induced spatio-temporal degradation limits outdoor PV inverter lifetime and reliability, necessitating advanced data analysis. This study employs a top-down, data-driven approach utilizing multiple machine learning (ML) algorithms to estimate inverter reliability in a 1.4 MW PV power plant, considering factors such as irradiance, humidity, temperature, time of day, and weather conditions. An extensive alert dataset from 17 identical inverters, including alert types, propagation, and frequency, reveals significant correlations with environmental factors and inverter output power, enabling the construction of a performance reliability model. Dual-stage supervised-ML models are evaluated for accuracy, with the ‘classification-regression’ model by an artificial neural network (ANN) tested on the averaged “Alert-Ambient” dataset, which is outperformed by ‘clustering-regression’ models using random forest (RF) and K-Nearest Neighbors (KNN) on individual inverter datasets. K-means clustering applies principal component analysis to reduce dimensions, achieving improved accuracy beyond the 80% achieved by ANN on the averaged dataset. Second-stage regression estimates inverter reliability with a mean square error of 0.0195 on the averaged dataset and as low as 0.002 on individual inverter datasets using RF. Furthermore, these findings highlight the method's suitability for estimating PV inverter output reliability under ambient conditions, essential for digital twin development and related applications.

14 SOLAR ENERGY↗

NASA NTRS1982

An initial analysis of LANDSAT 4 Thematic Mapper data for the classification of agricultural, forested wetland, and urban land covers

An initial analysis of LANDSAT 4 thematic mapper (TM) data for the delineation and classification of agricultural, forested wetland, and urban land covers was conducted. A study area in Poinsett County, Arkansas was used to evaluate a classification of agricultural lands derived from multitemporal LANDSAT multispectral scanner (MSS) data in comparison with a classification of TM data for the same area. Data over Reelfoot Lake in northwestern Tennessee were utilized to evaluate the TM for delineating forested wetland species. A classification of the study area was assessed for accuracy in discriminating five forested wetland categories. Finally, the TM data were used to identify urban features within a small city. A computer generated classification of Union City, Tennessee was analyzed for accuracy in delineating urban land covers. An evaluation of digitally enhanced TM data using principal components analysis to facilitate photointerpretation of urban features was also performed.

Quattrochi, D. A.↗

DOE OSTI2024

New Measurements of the Lyα Forest Continuum and Effective Optical Depth with LyCAN and DESI Y1 Data

Abstract We present the Ly α Continuum Analysis Network (LyCAN), a convolutional neural network that predicts the unabsorbed quasar continuum within the rest-frame wavelength range of 1040–1600 Å based on the red side of the Ly α emission line (1216–1600 Å). We developed synthetic spectra based on a Gaussian mixture model representation of nonnegative matrix factorization (NMF) coefficients. These coefficients were derived from high-resolution, low-redshift ( z < 0.2) Hubble Space Telescope/Cosmic Origins Spectrograph (COS) quasar spectra. We supplemented this COS-based synthetic sample with an equal number of DESI Year 5 mock spectra. LyCAN performs extremely well on testing sets, achieving a median error in the forest region of 1.5% on the DESI mock sample, 2.0% on the COS-based synthetic sample, and 4.1% on the original COS spectra. LyCAN outperforms principal component analysis (PCA) and NMF-based prediction methods using the same training set by 40% or more. We predict the intrinsic continua of 83,635 DESI Year 1 spectra in the redshift range of 2.1 ≤ z ≤ 4.2 and perform an absolute measurement of the evolution of the effective optical depth. This is the largest sample employed to measure the optical depth evolution to date. We fit a power law of the form τ ( z ) = τ 0 ( 1 + z ) γ to our measurements and find τ 0 = (2.46 ± 0.14) × 10 −3 and γ = 3.62 ± 0.04. Our results show particular agreement with high-resolution, ground-based observations around z = 2, indicating that LyCAN is able to predict the quasar continuum in the forest region with only spectral information outside the forest.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2017

Accurate force field for molybdenum by machine learning large materials data

In this work, we present a highly accurate spectral neighbor analysis potential (SNAP) model for molybdenum (Mo) developed through the rigorous application of machine learning techniques on large materials data sets. Despite Mo's importance as a structural metal, existing force fields for Mo based on the embedded atom and modified embedded atom methods still do not provide satisfactory accuracy on many properties. We will show that by fitting to the energies, forces and stress tensors of a large density functional theory (DFT)-computed dataset on a diverse set of Mo structures, a Mo SNAP model can be developed that achieves close to DFT accuracy in the prediction of a broad range of properties, including energies, forces, stresses, elastic constants, melting point, phonon spectra, surface energies, grain boundary energies, etc. We will outline a systematic model development process, which includes a rigorous approach to structural selection based on principal component analysis, as well as a differential evolution algorithm for optimizing the hyperparameters in the model fitting so that both the model error and the property prediction error can be simultaneously lowered. We expect that this newly developed Mo SNAP model will find broad applications in large-scale, long-time scale simulations.

36 MATERIALS SCIENCE↗

NASA NTRS2015

Extension and Statistical Analysis of the GACP Aerosol Optical Thickness Record.

The primary product of the Global Aerosol Climatology Project (GACP) is a continuous record of the aerosol optical thickness (AOT) over the oceans. It is based on channel-1 and -2 radiance data from the Advanced Very High Resolution Radiometer (AVHRR) instruments flown on successive National Oceanic and Atmospheric Administration (NOAA) platforms. We extend the previous GACP dataset by four years through the end of 2009 using NOAA-17 and -18 AVHRR radiances recalibrated against MODerate resolution Imaging Spectroradiometer (MODIS) radiance data, thereby making the GACP record almost three decades long. The temporal overlap of over three years of the new NOAA-17 and the previous NOAA-16 record reveals an excellent agreement of the corresponding global monthly mean AOT values, thereby confirming the robustness of the vicarious radiance calibration used in the original GACP product. The temporal overlap of the NOAA-17 and -18 instruments is used to introduce a small additive adjustment to the channel-2 calibration of the latter resulting in a consistent record with increased data density. The Principal Component Analysis (PCA) of the newly extended GACP record shows that most of the volcanic AOT variability can be isolated into one mode responsible for ~12% of the total variance. This conclusion is confirmed by a combined PCA analysis of the GACP, MODIS, andMulti-angle Imaging SpectroRadiometer (MISR) AOTs during the volcano-free period fromFebruary 2000 to December 2009.We show that the modes responsible for the tropospheric AOT variability in the three datasets agree well in terms of correlation and spatial patterns. A previously identified negative AOT trend which started in the late 1980s and continued into the early 2000s is confirmed. Its magnitude and duration indicate that it was caused by changes in tropospheric aerosols. The latest multi-satellite segment of the GACP record shows that this trend tapered off, with no noticeable AOT change after 2002. This result is consistent with the MODIS andMISR AOT records as well as with the recent gradual reversal frombrightening to dimming revealed by surface flux measurements in many aerosol producing regions. Thus the robustness of the GACP record is confirmed, increasing our confidence in the validity of the negative trend. Although the nominal negative GACP AOT trend could partially be an artifact of increasing aerosol absorption, we argue that the time dependence of the GACP record, including the latest flat period, is more consistent with the actual decrease in the tropospheric AOT.

aerosols↗

DOE OSTI2024

Exploring Geothermal Potential of Great Basin Sub-Regions: Preprint

The INnovative Geothermal Exploration through Novel Investigations Of Undiscovered Systems (INGENIOUS) project aims to discover new, economically viable hidden geothermal systems in the Great Basin region by building on previous work in play fairway analysis and machine learning. A key objective of this project is to develop an exploration workflow to reduce geothermal exploration risks for hidden geothermal systems. A single preliminary play fairway workflow was developed from the assessment of the regional INGENIOUS geological, geophysical, and geochemical datasets. This workflow provided new preliminary predictive geothermal fairway maps for the INGENIOUS study area, which encompasses most of Nevada, western Utah, southern Idaho, southeastern Oregon, and easternmost California. However, a recent study (incorporating machine learning techniques) of a portion of Nevada identified four geologic domains and determined that the relative importance of individual datasets or features as indicators of geothermal potential may differ across these domains. The INGENIOUS study area includes a much larger and more geologically diverse region; therefore, additional geologic domains or sub-regions are expected. To assess the sub-regions in the INGENIOUS study area, principal component analysis and k-means clustering were applied. Preliminary results indicate that the INGENIOUS regional data cluster into groups that relate to different geologic domains in the Great Basin region. These include domains such as the Walker Lane, extensional western Great Basin region, broad lower strain region in the eastern Great Basin of western Utah and eastern Nevada, Quaternary volcanic fields, and the area adjacent to the Snake River Plain. These clusters are assessed to determine the key geologic drivers of the identified clusters. Understanding this variability can provide key insights for the exploration and characterization of hidden geothermal systems in the Great Basin region and could indicate the need to develop multiple geothermal conceptual models and play fairway workflows for the INGENIOUS study area.

GEOTHERMAL ENERGY↗

DOE OSTI2025

Exploring Geothermal Potential of Great Basin Sub-Regions

exploration↗

DOE OSTI2019

Chemical composition of ultrafine aerosol particles in central Amazonia during the wet season

Central Amazonia serves as an ideal location to study atmospheric particle formation, since it often represents nearly natural, pre-industrial conditions but can also experience periods of anthropogenic influence due to the presence of emissions from large metropolitan areas like Manaus, Brazil. Ultrafine (sub-100 nm diameter) particles are often observed in this region, although new particle formation events seldom occur near the ground despite being readily observed in other forested regions with similar emissions of volatile organic compounds (VOCs). This study focuses on identifying the chemical composition of ultrafine particles as a means of determining the chemical species and mechanisms that may be responsible for new particle formation and growth in the region. These measurements were performed during the wet season as part of the Observations and Modeling of the Green Ocean Amazon (GoAmazon2014/5) field campaign at a site located 70 km southwest of Manaus. A thermal desorption chemicalionization mass spectrometer (TDCIMS) characterized the most abundant compounds detected in ultrafine particles. Two time periods representing distinct influences on aerosol composition, which we label as “anthropogenic” and “background” periods, were studied as part of a larger 10 d period of analysis. Higher particle number concentrations were measured during the anthropogenic period, and modeled back-trajectory frequencies indicate transport of emissions from the Manaus metropolitan area. During the background period there were much lower number concentrations, and back-trajectory frequencies showed that air masses arrived at the site predominantly from the forested regions to the north and northeast. TDCIMS-measured constituents also show distinct differences between the two observational periods. Although bisulfate was detected in particles throughout the 10 d period, the anthropogenic period had higher levels of particulate bisulfate overall. Ammonium and trimethyl ammonium were positively correlated with bisulfate. The background period had distinct diurnal patterns of particulate cyanate and acetate, while oxalate remained relatively constant during the 10 d period. 3-Methylfuran, a thermal decomposition product of a particulate-phase isoprene epoxy diol(IEPOX), was the dominant species measured in the positive-ion mode. Principal component analysis (PCA) was performed on the TDCIMS-measured ion abundance and aerosol mass spectrometer (AMS) mass concentration data. Two different hierarchical clusters representing unique influences arise: one comprising ultrafine particulate acetate, hydrogen oxalate, cyanate, trimethyl ammonium and 3-methylfuran and another made up of ultra fine particulate bisulfate, chloride, ammonium and potassium. A third cluster separated AMS-measured species from the two TDCIMS-derived clusters, indicating different sources or processes in ultrafine aerosol particle formation compared to larger submicron-sized particles.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Improved precision in As speciation analysis with HERFD-XANES at the As K -edge: the case of As speciation in mine waste

High-energy-resolution fluorescence-detected (HERFD) X-ray absorption near-edge spectroscopy (XANES) is a spectroscopic method that allows for increased spectral feature resolution, and greater selectivity to decrease complex matrix effects compared with conventional XANES. XANES is an ideal tool for speciation of elements in solid-phase environmental samples. Accurate speciation of As in mine waste materials is important for understanding the mobility and toxicity of As in near-surface environments. In this study, linear combination fitting (LCF) was performed on synthetic spectra generated from mixtures of eight measured reference compounds for both HERFD-XANES and transmission-detected XANES to evaluate the improvement in quantitative speciation with HERFD-XANES spectra. The reference compounds arsenolite (As 2 O 3 ), orpiment (As 2 S 3 ), getchellite (AsSbS 3 ), arsenopyrite (FeAsS), kaňkite (FeAsO 4 ·3.5H 2 O), scorodite (FeAsO 4 ·2H 2 O), sodium arsenate (Na 3 AsO 4 ), and realgar (As 4 S 4 ) were selected for their importance in mine waste systems. Statistical methods of principal component analysis and target transformation were employed to determine whether HERFD improves identification of the components in a dataset of mixtures of reference compounds. LCF was performed on HERFD- and total fluorescence yield (TFY)-XANES spectra collected from mine waste samples. Arsenopyrite, arsenolite, orpiment, and sodium arsenate were more accurately identified in the synthetic HERFD-XANES spectra compared with the transmission-XANES spectra. In mine waste samples containing arsenopyrite and either scorodite or kaňkite, LCF with HERFD-XANES measurements resulted in fits with smaller R -factors than concurrently collected TFY measurements. The improved accuracy of HERFD-XANES analysis may provide enhanced delineation of As phases controlling biogeochemical reactions in mine wastes, contaminated soils, and remediation systems.

58 GEOSCIENCES↗

DOE OSTI2017

A Piecewise Local Partial Least Squares (PLS) Method for the Quantitative Analysis of Plutonium Nitrate Solutions

We have developed a piecewise local (PL) partial least squares (PLS) analysis method for total plutonium measurements by absorption spectroscopy in nitric acid-based nuclear material processing streams. Instead of using a single PLS model that covers all expected solution conditions, the method selects one of several local models based on an assessment of solution absorbance, acidity, and Pu oxidation state distribution. The local models match the global model for accuracy against the calibration set, but were observed in several instances to be more robust to variations associated with measurements in the process. The improvements are attributed to the relative parsimony of the local models. Not all of the sources of spectral variation are uniformly present at each part of the calibration range. Thus, the global model is locally overfitting and susceptible to increased variance when presented with new samples. A second set of models quantifies the relative concentrations of Pu(III), (IV), and (VI). Standards containing a mixture of these species were not at equilibrium due to a disproportionation reaction. Therefore, a separate principal component analysis is used to estimate of the concentrations of the individual oxidation states in these standards in the absence of independent confirmatory analysis. The PL analysis approach is generalizable to other systems where the analysis of chemically complicated systems can be aided by rational division of the overall range of solution conditions into simpler sub-regions.

47 OTHER INSTRUMENTATION↗

DOE OSTI2020

Temporal Analysis and Scene Change Detection in Multispectral Overhead Imagery

Scene change detection can be a tedious and time consuming process especially when concerning large geographical areas, and the process can be even more cumbersome when analyzing changes in an area over large spans of time. Developing a useful way to help analysts recognize at what points in time significant changes to a scene have occurred can allow them to better focus their efforts in characterizing events. Applications include: Facility monitoring, Construction chronology, Monitoring of vehicle/aircraft activity, Characterization of larger sequences of events. In large areas exceeding hundreds to thousands of square kilometers in size, it can be difficult localizing when scene changes have occurred. Analysts can spend hours going through imagery to try to identify new construction, monitor facility activities, monitor vehicle movement, etc. where the object of interest may only be a few square meters. Our goal is to help cut down this time by giving analysts change maps with hot spots of change, allowing them to focus on regions that have experienced actual change in time frames they're interested in. Additionally, by combining these change maps into layers within a data cube, analysts can examine the change maps from a temporal perspective, allowing events to be characterized over spans of time. By opening the data cube in an imaging software capable of separating the layers, we can analyze the change maps sequentially, allowing us to examine scene changes occurring over time. As an example, we examined overhead imagery from Planet Labs of what appears to be a parking lot on Fort Irwin over the course of a year using ENVI, a geospatial satellite imagery analysis software. Using ENVI, we generate a graph of changes over time, and notice a particular segment near the end of our analysis window where no changes are detected. Examination of the actual satellite imagery reveals that during this time span, the parking lot was empty. This could be due to facility shutdown for maintenance or upgrades, or possibly even total workforce/vehicle fleet movement. Information like this could help analysts better characterize events, as well as to help create clearer timelines in larger sequences of events. Workflow steps: - Collect multiple maps of the same AOI (Area of Interest) during a time span of interest; - Generate change maps from AOI maps; - Generate data cube from change maps. An analyst can use the data cube to help inspect an AOI for activities within a time span of interest. If an event of interest is discovered, the analyst can then refer to the maps corresponding to the appropriate dates and times in the data cube to see precisely what is transpiring. The biggest objective being worked on is improving the change detection methodology employed. We currently use PCA-EM (Principal Component Analysis with Expectation Maximization), but we are currently focusing on implementing IR-MAD (Iteratively Reweighted Multivariate Alteration Detection) to be used in conjunction with PCA-EM in an effort to decrease false positivity and noise in the change maps we generate.

42 ENGINEERING↗

DOE OSTI2025

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗

DOE OSTI2015

The Phylogenetic Signature Underlying ATP Synthase c-Ring Compliance

The proton-driven ATP synthase (F O F 1 ) is comprised of two rotary, stepping motors (F O and F 1 ) coupled by an elastic power transmission. The elastic compliance resides in the rotor module that includes the membrane-embedded F O c-ring. Proton transport by F O is firmly coupled to the rotation of the c-ring relative to other F O subunits (ab 2 ). It drives ATP synthesis. We used a computational method to investigate the contribution of the c-ring to the total elastic compliance. We performed principal component analysis of conformational ensembles built using distance constraints from the bovine mitochondrial c-ring x-ray structure. Angular rotary twist, the dominant ring motion, was estimated to show that the c-ring accounted in part for the measured compliance. Ring rotation was entrained to rotation of the external helix within each hairpin-shaped c-subunit in the ring. Ensembles of monomer and dimers extracted from complete c-rings showed that the coupling between collective ring and the individual subunit motions was independent of the size of the c-ring, which varies between organisms. Molecular determinants were identified by covariance analysis of residue coevolution and structural-alphabet-based local dynamics correlations. The residue coevolution gave a readout of subunit architecture. The dynamic couplings revealed that the hinge for both ring and subunit helix rotations was constructed from the proton-binding site and the adjacent glycine motif (IB-GGGG) in the midmembrane plane. IB-GGGG motifs were linked by long-range couplings across the ring, while intrasubunit couplings connected the motif to the conserved cytoplasmic loop and adjacent segments. The correlation with principal collective motions shows that the couplings underlie both ring rotary and bending motions. Noncontact couplings between IB-GGGG motifs matched the coevolution signal as well as contact couplings. The residue coevolution reflects the physiological importance of the dynamics that may link proton transfer to ring compliance.

36 MATERIALS SCIENCE↗

NASA NTRS2004

Neural network uncertainty assessment using Bayesian statistics: a remote sensing application

Neural network (NN) techniques have proved successful for many regression problems, in particular for remote sensing; however, uncertainty estimates are rarely provided. In this article, a Bayesian technique to evaluate uncertainties of the NN parameters (i.e., synaptic weights) is first presented. In contrast to more traditional approaches based on point estimation of the NN weights, we assess uncertainties on such estimates to monitor the robustness of the NN model. These theoretical developments are illustrated by applying them to the problem of retrieving surface skin temperature, microwave surface emissivities, and integrated water vapor content from a combined analysis of satellite microwave and infrared observations over land. The weight uncertainty estimates are then used to compute analytically the uncertainties in the network outputs (i.e., error bars and correlation structure of these errors). Such quantities are very important for evaluating any application of an NN model. The uncertainties on the NN Jacobians are then considered in the third part of this article. Used for regression fitting, NN models can be used effectively to represent highly nonlinear, multivariate functions. In this situation, most emphasis is put on estimating the output errors, but almost no attention has been given to errors associated with the internal structure of the regression model. The complex structure of dependency inside the NN is the essence of the model, and assessing its quality, coherency, and physical character makes all the difference between a blackbox model with small output errors and a reliable, robust, and physically coherent model. Such dependency structures are described to the first order by the NN Jacobians: they indicate the sensitivity of one output with respect to the inputs of the model for given input data. We use a Monte Carlo integration procedure to estimate the robustness of the NN Jacobians. A regularization strategy based on principal component analysis is proposed to suppress the multicollinearities in order to make these Jacobians robust and physically meaningful.

Neural Networks (Computer)↗

NASA NTRS1994

Passive microwave observations of the Wedell Sea during austral winter and early spring

The results of multispectral passive microwave observations (6.7 to 90-GHz) are presented from the cruises of the FS Polarstern in the Weddell Sea from July to December 1986. This paper includes primarily the analysis of radiometric observations taken at ice station sites. Averaged emissivity spectra for first-year (FY) ice were relatively constant throughout the experiment and were not statistically different from FY ice signatures in the Arctic. Detailed ice characterization was carried out at each site to compare the microwave signatures of the ice with the physical properties. Absorption optical depths of FY ice were found to be sufficiently high that only the structure in the upper portions of the ice contributed significantly to interstation emissivity variations. The emissivities at 90-GHz, e(90), had the greatest variance. Both e(90) at vertical polarization and GR(sub e)(90, 18.7)(defined as (e(sub V)(90)-e(sub V)(18.7))/e(sub V)(90 + e(sub V)(18.7)) depended on the scattering optical depth which is a function of the snow grain diameter and layer thickness. The variance showed a latitude dependence and is probably due to an increase in the strength of snow metamorphism nearer the northern edge of the ice pack. The contribution of variations of near-surface brine volume to the emissivity was not significant over the range of values encountered at the station sites. Emissivity spectra are presented for a range of thin ice types. Unsupervised principal component analysis produced three significant eigenvectors and showed a separation among four different surface types: open water, thin ice, FY ice, and FY ice with a thick snow cover. A comparison with SMMR satellite data showed that average ice concentrations derived from the ship's ice watch log were consistent with the satellite concentrations. The surface based emissivities for FY ice were also compared with emissivities calculated from scanning multichannel microwave radiometer (SMMR) satellite radiances. Best agreement was found at 6.7 and 10-GHz, while at 18 and 37-GHz, SMMR emissivities were slightly lower than surface based results. For the three lower frequencies agreement was found within a confidence limit of 95% and for 37-GHz within about 90%.

Grenfell, T. C.↗

NASA NTRSDate not supplied

Predicting the Seawater Chemistry of an Ocean World Using Machine Learning on Isotopic Measurements of Volatile CO2

Introduction: Given the long time intervals required for data transmission to and from ocean worlds targets, low bandwidth for data transmission, time required for data processing and analysis, and potentially extreme radiation environments (e.g., Europa), it is clear that ocean worlds missions will need more autonomous flight instruments and software in order to achieve established science goals. Protracted time intervals for data analysis (e.g., Europa Lander) strongly motivates the development of rapid, consistent and streamlined methods for interpreting data from flight mass spectrometers to e.g., determine how mass spectra from a plume or surface liquid/ice relates to the surface/subsurface. Since mass spectrometry also has the potential to correctly identify biosignatures[1], it is imperative that such methods for interpreting data are consistent and accurate. We used 848 isotope ratio mass spectra from laboratory analyses of CO2 that interacted with ocean worlds-relevant seawaters as a ‘training’ dataset for ‘unsupervised’ machine learning. In unsupervised learning, characteristics of the data are not labeled or linked, and any similarities found only result from the neural network. CO2 isotopologues analyzed for this dataset mimic the remote measurements of CO2 by a flight mass spectrometer, and are detailed in Theiling [2]. From this dataset, we used measured features of the spectra, such as retention time, intensity, and (isotopologue) mass ratios as inputs for our autoencoder neural network. Our neural network was trained to find similarities in these and other spectral features for seawaters of a particular composition and amount of initial CO2. Successful training then created an output of these similarities for various seawaters, which included MgSO4, Na2SO4, NaCl, MgCl2, KCl, and NaHCO3, and combinations of these salts. We then applied dimensionality reduction techniques such as Principal Component Analysis (PCA), T-Distributed Stochastic Neighbor Embedding (TSNE), and Uniform Manifold Approximation and Projection (UMAP) to demonstrate latent data features as a two-dimensional projection in a unitless, high-dimensional space. In this projection, a data point represents the combined effect of spectral features such as intensity, retention time, and isotope ratio. Our initial UMAP demonstrates data clustering (organization of the data by the neural network) based on the amount of CO2 that had initially interacted with each seawater. Further training using more ‘supervised’ learning techniques demonstrate strong clustering of preliminary data based on initial CO2 concentration, seawater chemical composition, and ionic strength (salinity). Our preliminary work therefore suggests that machine learning has the potential to identify compositional variants of an ocean world seawater based on mass spectra from volatile CO2 measurements. Acknowledgments: This work was funded through a Strategic Task Group at NASA Goddard Space Flight Center. The training dataset was collected through funding from the Oklahoma Space Grant Consortium. References: [1] Pappalardo, R. et al. (2013) Astrobiology, 13, 740–773. [2] Theiling (2020) Icarus, 114216.

Europa↗