Search NASA⌕ Search

SEARCH · Search NASA

Results for “multiple regression”

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 703 records · Page 39

Differentiation of pancreatic neuroendocrine tumors from pancreas renal cell carcinoma metastases on CT using qualitative and quantitative features

Purpose: To assess qualitative and quantitative imaging features on enhanced CT that may differentiate pancreatic neuroendocrine tumors (PNETs) from pancreatic renal cell carcinoma (RCC) metastases. Methods: This IRB-approved multi-center retrospective case–control study compared 43 resected PNETs and 28 resected RCC metastases with pre-operative enhanced CT identified consecutively between 2003 and 2017. Two blinded radiologists (R1/R2) independently assessed tumor location, attenuation (relative to pancreas), composition (solid/cystic/mixed), homogeneity (homogeneous/heterogeneous), calcification, multiplicity, and for main pancreatic duct (MPD) dilation. Tumors were segmented for quantitative texture analysis. Data were analyzed with Chi square, logistic regression, and receiver operating characteristic (ROC). Inter-observer agreement was assessed (Cohen’s kappa). Results: There was no difference in age, gender, location, attenuation, or composition (P > 0.05) between groups. PNETs were larger than RCC metastases (37 ± 23 mm vs. 26 ± 21 mm, P = 0.038), more frequently solitary (P < 0.001), subjectively more heterogeneous (P = 0.033/0.144, R1/R2), and associated with calcification (P = 0.002/0.004) and MPD dilation (P = 0.025/0.006). Agreement for subjective features was moderate-to-almost perfect (K = 0.4879–0.9481). Quantitative texture analysis showed higher entropy in PNETs (6.32 ± 0.49 versus 5.96 ± 0.53; P = 0.004) with no difference in other features studied (P > 0.05). Entropy had ROC area under the curve for diagnosis of PNET of 0.77 ± 0.06, with optimal sensitivity/specificity of 71.4/79.1%. Conclusions: Compared to pancreatic RCC metastases, PNETs are larger, more frequently solitary, contain calcification, show MPD dilation, and are subjectively and quantitatively more heterogeneous tumors.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

A review of lunar chronology revealing a preponderance of 4.34-4.37 Ga ages

In this study, data obtained from Sm-Nd and Rb-Sr isotopic measurements of lunar highlands’ samples are renormalized to common standard values and then used to define ages with a common isochron regression algorithm. The reliability of these ages is evaluated using five criteria that include whether: (1) the ages are defined by multiple isotopic systems, (2) the data demonstrate limited scatter outside uncertainty, (3) initial isotopic compositions are consistent with the petrogenesis of the samples, (4) the ages are defined by an isotopic system that is resistant to disturbance by impact metamorphism, and (5) the rare-earth element abundances determined by isotope dilution of bulk of mineral fractions match those measured by in situ analyses. From this analysis, it is apparent that the oldest highlands’ rock ages are some of the least reliable, and that there is little support for crustal ages older than ~4.40 Ga. A model age for ur-KREEP formation calculated using the most reliable Mg-suite Sm-Nd isotopic systematics, in conjunction with Sm-Nd analyses of KREEP basalts, is 4389 ± 45 Ma. This age is a good match to the Lu-Hf model age of 4353 ± 37 Ma determined using a subset of this sample suite, the average model age of 4353 ± 25 Ma determined on mare basalts with the 146 Sm- 142 Nd isotopic system, with a peak in Pb-Pb ages observed in lunar zircons of ~4340 ± 20 Ma, and the oldest terrestrial zircon age of 4374 ± 6 Ma. The preponderance of ages between 4.34 and 4.37 Ga reflect either primordial solidification of a lunar magma ocean or a widespread secondary magmatic event on the lunar nearside. The first scenario is not consistent with the oldest ages reported for lunar zircons, whereas the second scenario does not account for concordance between ages of crustal rocks and mantle reservoirs.

79 ASTRONOMY AND ASTROPHYSICS↗

Robust Mosaicking of Stereo Digital Elevation Models from the Ames Stereo Pipeline

Robust estimation method is proposed to combine multiple observations and create consistent, accurate, dense Digital Elevation Models (DEMs) from lunar orbital imagery. The NASA Ames Intelligent Robotics Group (IRG) aims to produce higher-quality terrain reconstructions of the Moon from Apollo Metric Camera (AMC) data than is currently possible. In particular, IRG makes use of a stereo vision process, the Ames Stereo Pipeline (ASP), to automatically generate DEMs from consecutive AMC image pairs. However, the DEMs currently produced by the ASP often contain errors and inconsistencies due to image noise, shadows, etc. The proposed method addresses this problem by making use of multiple observations and by considering their goodness of fit to improve both the accuracy and robustness of the estimate. The stepwise regression method is applied to estimate the relaxed weight of each observation.

Kim, Tae Min↗

Comparison of Aircraft Conceptual Design Weight Estimation Methods to the Flight Optimization System

Weight estimation is critical in the aircraft conceptual design process. The Flight Optimization System (FLOPS) is an aircraft conceptual design tool that has been the primary aircraft synthesis software used by the Systems Analysis and Concepts Directorate at NASA Langley Research Center. FLOPS includes multiple modules that represent aircraft design disciplines. The FLOPS weight module includes estimation methods that are similar in nature to other regression based aircraft preliminary weight estimation methods, however the FLOPS methods were created to use a minimum number of input parameters to limit the effort required by the designer to apply it. As FLOPS has recently been made publically available, this work compares the FLOPS weight estimation methods with several similar methods with the goal of explaining the differences in FLOPS, providing conceptual designers with a brief introduction to the method before attempting to apply it, and providing a reference to inform the development of future weight estimating relationships. In this paper, the Boeing 737-200 is used as a test case to highlight to differences and similarities in the methods.

Horvath, Bryce L.↗

Emissions Relationships in Western Forest Fire Plumes: I. Reducing the Effect of Mixing Errors on Emission Factors

Studies of emission factors from biomass burning using aircraft data complement the results of lab studies and extend them to conditions of immense hot conflagrations. We illustrate and discuss emission relationships for 422 individual samples from many forest-fire plumes in the Western US. The samples are from two NASA investigations: ARCTAS (Arctic Research of the Composition of the Troposphere from Aircraft and Satellites) and SEAC4RS (Studies of Emissions and Atmospheric Composition, Clouds, and Climate Coupling by Regional Surveys). This work provides sample-by-sample enhancement ratios (EnRs) for 23 gases and particulate properties. Many EnRs provide candidates for emission ratios (ERs, corresponding to the EnR at the source) when the origin and degree of transformation is understood and appropriate. From these, emission factors (EFs) can be estimated when the fuel dry mass consumed is known or can be estimated using the carbon mass budget approach. This analysis requires understanding the interplay of mixing of the plume with surrounding air. Some initial examples emphasize that measured C(tot) = CO2 + CO in a fire plume does not necessarily describe the emissions of the total carbon liberated in the flames, C(burn). Rather, it represents C(tot) = C(burn) + C(bkgd), which includes possibly varying background concentrations for entrained air. Consequently, we present a simple theoretical description for plume entrainment for multiple tracers from flame to hundreds of kilometers downwind and illustrate some intrinsic linear behaviors. The analysis suggests a Mixed Effects Regression Emission Technique (MERET), which can eliminate occasional strong biases associated with the commonly used normalized excess mixing ratio (NEMR) method. MERET splits C(tot) to reveal C(burn) by exploiting the fact that C(burn) and all tracers respond linearly to dilution, while each tracer has consistent EnR behavior (slope of tracer concentration with respect to C(burn)). The two effects are separable. Two or three or preferably more emission indicators are required as a minimum; here we used ten. Limited variations in the EnRs for each tracer can be incorporated and the variations and co-variations analyzed. The percentage CO yield (or the modified combustion efficiency) plays some role. Other co-relationships involving nitrogen and organic classes are more prominent; these have strong relationships to the C(burn) to O3 emission relationship. In summary, MERET allows fine spatial resolution (EnRs for individual observations) and comparison of similar plumes distant in time and space. Alkene ratios provide us with an approximate photochemical timescale. This allows discrimination and definition, by fire situation, of ERs, allowing us to estimate emission factors.

Chatfield, Robert B.↗

Use of Continuous Integration Tools for Application Performance Monitoring

High performance computing systems are becom- ing increasingly complex, both in node architecture and in the multiple layers of software stack required to compile and run applications. As a consequence, the likelihood is increasing for application performance regressions to occur as a result of routine upgrades of system software components which interact in complex ways. The purpose of this study is to evaluate the effectiveness of continuous integration tools for application performance monitoring on HPC systems. In addition, this paper also describes a prototype system for application perfor- mance monitoring based on Jenkins, a Java-based continuous integration tool. The monitoring system described leverages several features in Jenkins to track application performance results over time. Preliminary results and lessons learned from monitoring applications on Cray systems at the Oak Ridge Leadership Computing Facility are presented.

Vergara Larrea, Veronica G↗

Stochastic AC optimal power flow: A data-driven approach

There is an emerging need for efficient solutions to stochastic AC Optimal Power Flow (AC-OPF) to ensure optimal and reliable grid operations in the presence of increasing demand and generation uncertainty. Herein this paper presents a highly scalable data-driven algorithm for stochastic AC-OPF that has extremely low sample requirement. The novelty behind the algorithm’s performance involves an iterative scenario design approach that merges information regarding constraint violations in the system with data-driven sparse regression. Compared to conventional methods with random scenario sampling, our approach is able to provide feasible operating points for realistic systems with much lower sample requirements. Furthermore, multiple sub-tasks in our approach can be easily paralleled and based on historical data to enhance its performance and application. We demonstrate the computational improvements of our approach through simulations on different test cases in the IEEE PES PGLib-OPF benchmark library.

42 ENGINEERING↗

Poisson-response Tensor-on-Tensor Regression and Applications

We introduce Poisson-response tensor-on-tensor regression (PToTR), a novel regression framework designed to handle tensor responses composed element-wise of random Poisson-distributed counts. Tensors, or multi-dimensional arrays, composed of counts are common data in fields such as inter national relations, social networks, epidemiology, and medical imaging, where events occur across multiple dimensions like time, location, and dyads. PToTR accommodates such tensor responses alongside tensor covariates, providing a versatile tool for multi dimensional data analysis. We propose algorithms for maximum likelihood estimation under a canonical polyadic (CP) structure on the regression coefficient tensor that satisfy the positivity of Poisson parameters and then provide an initial theoretical error analysis for PToTR estimators. We also demonstrate the utility of PToTR through three concrete applications: longitudinal data analysis of the Integrated Crisis Early Warning System database, positron emission tomography (PET) image reconstruction, and change-point detection of communication patterns in longitudinal dyadic data. These applications highlight the versatility of PToTR in addressing complex, structured count data across various domains.

97 MATHEMATICS AND COMPUTING↗

A Deep Multimodal Representation Learning Framework for Accurate Molecular Properties Prediction

Drug discovery is a complex and challenging process, requiring the optimization of candidate compounds to identify those with the potential to become safe and effective drugs. Predicting molecular properties is an indispensable step in the drug discovery pipeline. Traditionally, this process is costly and time-intensive, involving multiple rounds of experiments and clinical trials, rendering it impractical for every candidate compound. Deep learning techniques have emerged as a promising approach to drug discovery to reduce the cost and time required to identify novel drugs. However, prevalent research in deep learning models focused on predicting molecular properties has primarily fixated on single-modal models, which utilize a single modality of data, neglecting the potential benefits of combining different data modalities. To overcome this limitation, we introduce MRL-Mol: a deep \textbf{M}ultimodal \textbf{R}epresentation \textbf{L}earning framework for accurate \textbf{Mol}ecular properties prediction. MRL-Mol harnesses three data modalities: sequence, graph, and image, augmenting the depth of comprehension. Leveraging a large-scale unlabeled dataset~($\sim$1M unique molecules), we pretrain MRL-Mol to extract inter- and intra-modal information. Our study demonstrates the superior performance of MRL-Mol in predicting molecular properties across six benchmark datasets, including both classification and regression tasks. Notably, MRL-Mol outperforms other state-of-the-art molecular properties prediction models. These findings suggest that by combining information from multiple data modalities, MRL-Mol can comprehend molecules better than single-modal deep learning models and identify molecular properties with better accuracy.

Yang, Yuxin↗

Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-informed Deep Generative Models

Here, we propose a new method for inferring the governing stochastic ordinary differential equations (SODEs) by observing particle ensembles at discrete and sparse time instants, i.e., multiple “snapshots.” Particle coordinates at a single time instant, possibly noisy or truncated, are recorded in each snapshot but are unpaired across the snapshots. By training a physics-informed generative model that generates “fake” sample paths, we aim to fit the observed particle ensemble distributions with a curve in the probability measure space, which is induced from the inferred particle dynamics. We employ different metrics to quantify the differences between distributions, e.g., the sliced Wasserstein distances and the adversarial losses in generative adversarial networks. We refer to this method as generative “ensemble-regression” (GER), in analogy to the classic “point-regression,” where we infer the dynamics by performing regression in the Euclidean space. We illustrate the GER by learning the drift and diffusion terms of particle ensembles governed by SODEs with Brownian motions and Lévy processes up to 100 dimensions. We also discuss how to treat cases with noisy or truncated observations. Apart from systems consisting of independent particles, we also tackle nonlocal interacting particle systems with unknown interaction potential parameters by constructing a physics-informed loss function. Finally, we investigate scenarios of paired observations and discuss how to reduce the dimensionality in such cases by proving a convergence theorem that provides theoretical support.

97 MATHEMATICS AND COMPUTING↗

Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Revenue estimation for integrated renewable energy and energy storage systems is important to support plant owners or operators’ decisions in battery sizing selection that leads to maximized financial performances. A common approach to optimizing revenues of a hybrid hydro and energy storage system is using mixed-integer linear programming (MILP). Although MILP models can provide accurate production cost estimations, they are typically very computationally expensive. To provide a fast yet accurate first-step information to hydropower plant owners or operators who consider integrating energy storage systems, we propose an innovative approach to predicting optimal revenues of an integrated energy generation and storage system. In this study, we examined the performance of two prediction techniques: Generalized Additive Models (GAMs) and machine learning (ML) models developed based on artificial neural networks (ANN). Predictive equations and models are generated based on optimized solutions from a market participation optimization model, the Conventional Hydropower Energy and Environmental Resource System (CHEERS) model. The two predicting techniques reduce the computational time to evaluate annual revenue for one set of battery configurations from 3 h to 1 to 4 min per run while also being implementable with significantly less data. The model validation prediction errors of developed GAMs and ML models are generally below 5%; for model testing predictions, the ML models consistently outperform the regression equations in terms of root mean square errors. This new approach allows plant owners, operators, or potential investors to quickly access multiple battery configurations under different energy generation and market scenarios. This new revenue prediction method will therefore help reduce the barriers, and thereby promoting the deployment of battery hybridization with existing renewable energy sources.

13 HYDRO ENERGY↗

Deep learning the properties of inorganic perovskites

We report the ability to accurately and quickly predict the stability of materials and their structural and electronic properties remains a grand challenge in materials science. Density functional theory is widely used as a means of predicting these material properties, but is known to be computationally expensive and scales as the cube of the number of electrons in the material’s unit cell. In this article, for a previously published dataset of inorganic perovskites, we show that a single neural network model using only the elemental properties of the compounds’ constituents can predict lattice constants to within 0.1 Å, heat of formation to within 0.2 eV, and band gaps to within 0.7 eV RMSE. We also compare the performance of the trained network to two widely used regression techniques, namely random forest and Kernel ridge regression, and find that the neural network’s predictions are more accurate for each of the properties. The simultaneous accurate prediction of multiple key properties of technologically relevant materials is promising for rational design and optimization in known and novel chemical spaces.

36 MATERIALS SCIENCE↗

Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

Purpose: Given the paucity of available data concerning radiotherapy-induced urinary toxicity, it is important to ensure derivation of the most robust models with superior predictive performance. This work explores multiple statistical-learning strategies for prediction of urinary symptoms following external beam radiotherapy of the prostate. Methods: The performance of logistic regression, elastic-net, support-vector machine, random forest, neural network, and multivariate adaptive regression splines (MARS) to predict urinary symptoms was analyzed using data from 754 participants accrued by TROG03.04-RADAR. Predictive features included dose-surface data, comorbidities, and medication-intake. Four symptoms were analyzed: dysuria, haematuria, incontinence, and frequency, each with three definitions (grade ≥ 1, grade ≥ 2 and longitudinal) with event rate between 2.3% and 76.1%. Repeated cross-validations producing matched models were implemented. A synthetic minority oversampling technique was utilized in endpoints with rare events. Parameter optimization was performed on the training data. Area under the receiver operating characteristic curve (AUROC) was used to compare performance using sample size to detect differences of ≥0.05 at the 95% confidence level. Results: Logistic regression, elastic-net, random forest, MARS, and support-vector machine were the highest-performing statistical-learning strategies in 3, 3, 3, 2, and 1 endpoints, respectively. Logistic regression, MARS, elastic-net, random forest, neural network, and support-vector machine were the best, or were not significantly worse than the best, in 7, 7, 5, 5, 3, and 1 endpoints. The best-performing statistical model was for dysuria grade ≥ 1 with AUROC ± standard deviation of 0.649 ± 0.074 using MARS. For longitudinal frequency and dysuria grade ≥ 1, all strategies produced AUROC>0.6 while all haematuria endpoints and longitudinal incontinence models produced AUROC<0.6. Conclusions: Logistic regression and MARS were most likely to be the best-performing strategy for the prediction of urinary symptoms with elastic-net and random forest producing competitive results. The predictive power of the models was modest and endpoint-dependent. New features, including spatial dose maps, may be necessary to achieve better models.

60 APPLIED LIFE SCIENCES↗

Optimal selection of passes

Preliminary numerical results obtained from the application of a linear feature selection technique to the determination of combinations of passes which best discriminate between a given set of crops in a given area of interest, are reported. The results obtained are not purported to hold in a general situation, but only for the given set of crops and the given, but unknown, levels of several factors-such as soil type, and fertilizer practice, holding in the area of interest. However, by identifying the various factors affecting the spectral signatures, and by formulating a regression model one could use the feature selection technique to determine the regression coefficients for predicting optimal passes for a given set of crops. Another use of the feature selection technique as applied to multiple pass registered data is the generation of enhanced grey scale displays by using a single linear combination of all channels of all designated passes as opposed to a single channel within a single pass.

Guseman, L. F., Jr.↗

Automation of Flight Software Regression Testing

NASA is developing the Space Launch System (SLS) to be a heavy lift launch vehicle supporting human and scientific exploration beyond earth orbit. SLS will have a common core stage, an upper stage, and different permutations of boosters and fairings to perform various crewed or cargo missions. Marshall Space Flight Center (MSFC) is writing the Flight Software (FSW) that will operate the SLS launch vehicle. The FSW is developed in an incremental manner based on "Agile" software techniques. As the FSW is incrementally developed, testing the functionality of the code needs to be performed continually to ensure that the integrity of the software is maintained. Manually testing the functionality on an ever-growing set of requirements and features is not an efficient solution and therefore needs to be done automatically to ensure testing is comprehensive. To support test automation, a framework for a regression test harness has been developed and used on SLS FSW. The test harness provides a modular design approach that can compile or read in the required information specified by the developer of the test. The modularity provides independence between groups of tests and the ability to add and remove tests without disturbing others. This provides the SLS FSW team a time saving feature that is essential to meeting SLS Program technical and programmatic requirements. During development of SLS FSW, this technique has proved to be a useful tool to ensure all requirements have been tested, and that desired functionality is maintained, as changes occur. It also provides a mechanism for developers to check functionality of the code that they have developed. With this system, automation of regression testing is accomplished through a scheduling tool and/or commit hooks. Key advantages of this test harness capability includes execution support for multiple independent test cases, the ability for developers to specify precisely what they are testing and how, the ability to add automation, and the ability of the harness and cases to be executed continually. This test concept is an approach that can be adapted to support other projects.

Tashakkor, Scott B.↗

A Critical Examination of Figure of Merit (FOM). Assessing the Goodness-of-Fit in Gamma/X-ray Peak Analysis

In this paper we develop and investigate several criteria for assessing how well a proposed spectral form fits observed spectra. We consider the classical improved figure of merit (FOM) along with several modifications, as well as criteria motivated by Poisson regression from the statistical literature. We also develop a new FOM that is based on the statistical idea of the bootstrap. A spectral simulator has been developed to assess the performance of these different criteria under multiple data configurations.

97 MATHEMATICS AND COMPUTING↗

Experimental Investigations of Non-Stationary Properties In Radiometer Receivers Using Measurements of Multiple Calibration References

Radiometers must be periodically calibrated because the receiver response fluctuates. Many techniques exist to correct for the time varying response of a radiometer receiver. An analytical technique has been developed that uses generalized least squares regression (LSR) to predict the performance of a wide variety of calibration algorithms. The total measurement uncertainty including the uncertainty of the calibration can be computed using LSR. The uncertainties of the calibration samples used in the regression are based upon treating the receiver fluctuations as non-stationary processes. Signals originating from the different sources of emission are treated as simultaneously existing random processes. Thus, the radiometer output is a series of samples obtained from these random processes. The samples are treated as random variables but because the underlying processes are non-stationary the statistics of the samples are treated as non-stationary. The statistics of the calibration samples depend upon the time for which the samples are to be applied. The statistics of the random variables are equated to the mean statistics of the non-stationary processes over the interval defined by the time of calibration sample and when it is applied. This analysis opens the opportunity for experimental investigation into the underlying properties of receiver non stationarity through the use of multiple calibration references. In this presentation we will discuss the application of LSR to the analysis of various calibration algorithms, requirements for experimental verification of the theory, and preliminary results from analyzing experiment measurements.

Racette, Paul↗

Materials representation and transfer learning for multi-property prediction

The adoption of machine learning in materials science has rapidly transformed materials property prediction. Hurdles limiting full capitalization of recent advancements in machine learning include the limited development of methods to learn the underlying interactions of multiple elements as well as the relationships among multiple properties to facilitate property prediction in new composition spaces. To address these issues, we introduce the Hierarchical Correlation Learning for Multi-property Prediction (H-CLMP) framework that seamlessly integrates: (i) prediction using only a material's composition, (ii) learning and exploitation of correlations among target properties in multi-target regression, and (iii) leveraging training data from tangential domains via generative transfer learning. The model is demonstrated for prediction of spectral optical absorption of complex metal oxides spanning 69 three-cation metal oxide composition spaces. H-CLMP accurately predicts non-linear composition-property relationships in composition spaces for which no training data are available, which broadens the purview of machine learning to the discovery of materials with exceptional properties. This achievement results from the principled integration of latent embedding learning, property correlation learning, generative transfer learning, and attention models. The best performance is obtained using H-CLMP with transfer learning [H-CLMP(T)] wherein a generative adversarial network is trained on computational density of states data and deployed in the target domain to augment prediction of optical absorption from composition. H-CLMP(T) aggregates multiple knowledge sources with a framework that is well suited for multi-target regression across the physical sciences.

36 MATERIALS SCIENCE↗