Search NASA⌕ Search

SEARCH · Search NASA

Results for “discriminant 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.

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

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

Graphical methods for the sensitivity analysis in discriminant analysis

Similar to regression, many measures to detect influential data points in discriminant analysis have been developed. Many follow similar principles as the diagnostic measures used in linear regression in the context of discriminant analysis. Here we focus on the impact on the predicted classification posterior probability when a data point is omitted. The new method is intuitive and easily interpretative compared to existing methods. We also propose a graphical display to show the individual movement of the posterior probability of other data points when a specific data point is omitted. This enables the summaries to capture the overall pattern of the change.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Multiblock Discriminant Analysis of Integrative 18F-FDG-PET/CT Radiomics for Predicting Circulating Tumor Cells in Early-Stage Non-small Cell Lung Cancer Treated With Stereotactic Body Radiation Therapy

The main objective of the present study was to integrate {sup 18}F-FDG-PET/CT radiomics with multiblock discriminant analysis for predicting circulating tumor cells (CTCs) in early-stage non-small cell lung cancer (ES-NSCLC) treated with stereotactic body radiation therapy (SBRT).

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2024

Yet Another Discriminant Analysis (YADA): A Probabilistic Model for Machine Learning Applications

This paper presents a probabilistic model for various machine learning (ML) applications. While deep learning (DL) has produced state-of-the-art results in many domains, DL models are complex and over-parameterized, which leads to high uncertainty about what the model has learned, as well as its decision process. Further, DL models are not probabilistic, making reasoning about their output challenging. In contrast, the proposed model, referred to as Yet Another Discriminate Analysis(YADA), is less complex than other methods, is based on a mathematically rigorous foundation, and can be utilized for a wide variety of ML tasks including classification, explainability, and uncertainty quantification. YADA is thus competitive in most cases with many state-of-the-art DL models. Ideally, a probabilistic model would represent the full joint probability distribution of its features, but doing so is often computationally expensive and intractable. Hence, many probabilistic models assume that the features are either normally distributed, mutually independent, or both, which can severely limit their performance. YADA is an intermediate model that (1) captures the marginal distributions of each variable and the pairwise correlations between variables and (2) explicitly maps features to the space of multivariate Gaussian variables. Numerous mathematical properties of the YADA model can be derived, thereby improving the theoretic underpinnings of ML. Validation of the model can be statistically verified on new or held-out data using native properties of YADA. However, there are some engineering and practical challenges that we enumerate to make YADA more useful.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis

Introduction Recent studies in human brain connectomics with multimodal magnetic resonance imaging (MRI) data have widely reported abnormalities in brain structure, function and connectivity associated with schizophrenia (SZ). However, most previous discriminative studies of SZ patients were based on MRI features of brain regions, ignoring the complex relationships within brain networks. Methods We applied a graph convolutional network (GCN) to discriminating SZ patients using the features of brain region and connectivity derived from a combined multimodal MRI and connectomics analysis. Structural magnetic resonance imaging (sMRI) and resting-state functional magnetic resonance imaging (rs-fMRI) data were acquired from 140 SZ patients and 205 normal controls. Eighteen types of brain graphs were constructed for each subject using 3 types of node features, 3 types of edge features, and 2 brain atlases. We investigated the performance of 18 brain graphs and used the TopK pooling layers to highlight salient brain regions (nodes in the graph). Results The GCN model, which used functional connectivity as edge features and multimodal features (sMRI + fMRI) of brain regions as node features, obtained the highest average accuracy of 95.8%, and outperformed other existing classification studies in SZ patients. In the explainability analysis, we reported that the top 10 salient brain regions, predominantly distributed in the prefrontal and occipital cortices, were mainly involved in the systems of emotion and visual processing. Discussion Our findings demonstrated that GCN with a combined multimodal MRI and connectomics analysis can effectively improve the classification of SZ at an individual level, indicating a promising direction for the diagnosis of SZ patients. The code is available at https://github.com/CXY-scut/GCN-SZ.git .

Chen, Xiaoyi↗
DOE OSTI2019

Guide for Atomic Force Microscopy Image Analysis To Discriminate Heteroatoms in Aromatic Molecules [A Guide for AFM Image Analysis To Discriminate Heteroatoms in Aromatic Molecules]

Heteroatoms are essential for functional groups in organic structures and are complementary to hydrocarbon molecules in reactivities and properties. However, it is still a challenge to quickly identify heteroatoms with only non-contact atomic force microscopy (nc-AFM) to resolve chemical structures in complex unknown mixtures. This study aimed to understand the effect of elemental types on the contrast of atomic force microscopy (AFM) images using a few selected model heterocycles, including dibenzothiophene (DBT), acridine (ACR), and carbazole (CBZ). We identified several features that can be used to find common heteroatoms (S and N) and discriminated them from carbon atoms (C) using nc-AFM images alone. The mechanism of the atom and bond contrast was studied with image simulations and was found to be mostly correlated to van der Waals radii, but other factors, such as bonding geometry, electron density, and substrate interaction, need to be considered. As a result, this work will allow for rapid identification of these common heteroatoms in petroleum with AFM.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Multivariate regression modelling for gender prediction using volatile organic compounds from hand odor profiles via HS-SPME-GC-MS

The efficacy of using human volatile organic compounds (VOCs) as a form of forensic evidence has been well demonstrated with canines for crime scene response, suspect identification, and location checking. Although the use of human scent evidence in the field is well established, the laboratory evaluation of human VOC profiles has been limited. This study used Headspace-Solid Phase Microextraction-Gas Chromatography-Mass Spectrometry (HS-SPME-GC-MS) to analyze human hand odor samples collected from 60 individuals (30 Females and 30 Males). The human volatiles collected from the palm surfaces of each subject were interpreted for classification and prediction of gender. The volatile organic compound (VOC) signatures from subjects’ hand odor profiles were evaluated with supervised dimensional reduction techniques: Partial Least Squares-Discriminant Analysis (PLS-DA), Orthogonal-Projections to Latent Structures Discriminant Analysis (OPLS-DA), and Linear Discriminant Analysis (LDA). The PLS-DA 2D model demonstrated clustering amongst male and female subjects. The addition of a third component to the PLS-DA model revealed clustering and minimal separation of male and female subjects in the 3D PLS-DA model. The OPLS-DA model displayed discrimination and clustering amongst gender groups with leave one out cross validation (LOOCV) and 95% confidence regions surrounding clustered groups without overlap. The LDA had a 96.67% accuracy rate for female and male subjects. The culminating knowledge establishes a working model for the prediction of donor class characteristics using human scent hand odor profiles.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Bolide Light-curve Analysis and Discrimination Explorer (BLADE)

SAND2025-09601O Bolide Light-curve Analysis and Discrimination Explorer (BLADE) is a robust, high-fidelity framework designed to analyze the light curves of bolides—objects detected from space. It automates the identification of fragmentation events and energy release modes, using advanced techniques like Savitzky-Golay filtering, prominence-based peak detection, and gradient analysis. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Silber, Elizabeth [Sandia National Lab. (SNL-CA), ↗
DOE OSTI2025

Linear Discriminant Analysis-Based Machine Learning and All-Atom Molecular Dynamics Simulations for Probing Electro-Osmotic Transport in Cationic-Polyelectrolyte-Brush-Grafted Nanochannels

Deciphering the correct mechanisms governing certain phenomena in polyelectrolyte (PE) brush grafted systems, revealed through atomistic simulations, is an extremely challenging problem. In a recent study, our all-atom molecular dynamics (MD) simulations revealed a non-linearly large electroosmotic (EOS) flow (in the presence of an applied electric field) in nanochannels grafted with PMETAC [Poly(2-(methacryloyloxy)ethyl trimethylammonium chloride] brushes. Given the lack of any formal procedure that would have directed us to identify the correct factors responsible for such an occurrence, we needed to spend several months and devote significant analyses to unravel the involved mechanisms. In this paper, we propose a Linear Discriminant Analysis (LDA) based Machine Learning (ML) approach to address this gap. At first, we obtain data on certain basic features from the all-atom MD data. These basic features represent the number of atoms of certain species around one atom of another (or same) species. Here, we obtain such data on basic features for a reference case (case of an EOS flow in PMETAC-brush-grafted nanochannels with a smaller electric field) and a perturbed case (case of an EOS flow in PMETAC-brush-grafted nanochannels with a larger electric field) in bins in which the nanochannel half height has been divided into. These datasets are high-dimensional dataset, to which the LDA is applied. This leads to the projection of the data (between the reference and the perturbed states) in a highly separated form on a 1D line. From such LDA calculations, we are able to identify the relative importance of the different basic features in ensuring this separation of the data (between the reference and the perturbed states) on the 1D line. This relative importance of the different basic features is quantified as “importance scores” for the different features, which in turn tell us what to study and where to study. Such knowledge enables us to rapidly identify the key factors responsible for the non-linearly large EOS transport in PMETAC-brush-grafted nanochannels.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2018

Solvent effects on differentiation of mouse brain tissue using laser microdissection ‘cut and drop’ sampling with direct mass spectral analysis

Rationale: Laser microdissection-liquid vortex capture/electrospray ionization mass spectrometry (LMD-LVC/ESI-MS) has potential for on-line classification of tissue but an investigation into what analytical conditions provide best spectral differentiation has not been conducted. The effects of solvent, ionization polarity, and spectral acquisition parameters on differentiation of mouse brain tissue regions are described.Methods: Individual 40 × 40 μm microdissections from cortex, white, grey, granular, and nucleus regions of mouse brain tissue were analyzed using different capture/ESI solvents, in positive and negative ion mode ESI, using time-of-flight (TOF)-MS and sequential window acquisitions of all theoretical spectra (SWATH)-MS (a permutation of tandem-MS), and combinations thereof. Principal component analysis-linear discriminant analysis (PCA-LDA), applied to each mass spectral dataset, was used to determine the accuracy of differentiation of mouse brain tissue regions. Results: Mass spectral differences associated with capture/ESI solvent composition manifested as altered relative distributions of ions rather than the presence or absence of unique ions. In negative ion mode ESI, 80/20 (v/v) methanol/water yielded spectra with low signal/noise ratios relative to other solvents. PCA-LDA models acquired using 90/10 (v/v) methanol/chloroform differentiated tissue regions with 100% accuracy while data collected using methanol misclassified some samples. The combination of SWATH-MS and TOF-MS data improved differentiation accuracy.Conclusions: Combined TOF-MS and SWATH-MS data differentiated white, grey, granular, and nucleus mouse tissue regions with greater accuracy than when solely using TOF-MS data. Using 90/10 (v/v) methanol/chloroform, tissue regions were perfectly differentiated. Lastly, these results will guide future studies looking to utilize the potential of LMD-LVC/ESI-MS for tissue and disease differentiation.

47 OTHER INSTRUMENTATION↗
DOE OSTI2015

MALDI-Mass Spectrometric Imaging Revealing Hypoxia-Driven Lipids and Proteins in a Breast Tumor Model

Hypoxic areas are a common feature of rapidly growing malignant tumors and their metastases, and are typically spatially heterogeneous. Hypoxia has a strong impact on tumor cell biology and contributes to tumor progression in multiple ways. To date, only a few molecular key players in tumor hypoxia, such as for example hypoxia-inducible factor-1 (HIF-1), have been discovered. The distribution of biomolecules is frequently heterogeneous in the tumor volume, and may be driven by hypoxia and HIF-1α. Understanding the spatially heterogeneous hypoxic response of tumors is critical. Mass spectrometric imaging (MSI) provides a unique way of imaging biomolecular distributions in tissue sections with high spectral and spatial resolution. In this paper, breast tumor xenografts grown from MDA-MB-231-HRE-tdTomato cells, with a red fluorescent tdTomato protein construct under the control of a hypoxia response element (HRE)-containing promoter driven by HIF-1α, were used to detect the spatial distribution of hypoxic regions. We elucidated the 3D spatial relationship between hypoxic regions and the localization of small molecules, metabolites, lipids, and proteins by using principal component analysis – linear discriminant analysis (PCA-LDA) on 3D rendered MSI volume data from MDA-MB-231-HRE-tdTomato breast tumor xenografts. In this study we identified hypoxia-regulated proteins active in several distinct pathways such as glucose metabolism, regulation of actin cytoskeleton, protein folding, translation/ribosome, splicesome, the PI3K-Akt signaling pathway, hemoglobin chaperone, protein processing in endoplasmic reticulum, detoxification of reactive oxygen species, aurora B signaling/apoptotic execution phase, the RAS signaling pathway, the FAS signaling pathway/caspase cascade in apoptosis and telomere stress induced senescence. In parallel we also identified co-localization of hypoxic regions and various lipid species such as PC(16:0/18:1), PC(16:0/18:2), PC(18:0/18:1), PC(18:1/18:1), PC(18:1/18:2), PC(16:1/18:4), PC(18:0/20:3), PC(16:0/22:1), among others. Lastly, our findings shed light on the biomolecular composition of hypoxic tumor regions, which may be responsible for a given tumor’s resistance to radiation or chemotherapy.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

Towards intelligent diagnostic system employing integration of mathematical and engineering model

The development of medical diagnostic system has been one of the main research fields during years. The goal of the medical diagnostic system is to place a nosological system that could ease the diagnostic evaluation normally performed by scientists and doctors. Efficient diagnostic evaluation is essentials and requires broad knowledge in order to improve conventional diagnostic system. Several approaches on developing the medical diagnostic system have been designed and tested since the earliest 60s. Attempts on improving their performance have been made which utilizes the fields of artificial intelligence, statistical analyses, mathematical model and engineering theories. With the availability of the microcomputer and software development as well as the promising aforementioned fields, medical diagnostic prototypes could be developed. In general, the medical diagnostic system consists of several stages, namely the 1) data acquisition, 2) feature extraction, 3) feature selection, and 4) classifications stages. Data acquisition stage plays an important role in converting the inputs measured from the real world physical conditions to the digital numeric values that can be manipulated by the computer system. One of the common medical inputs could be medical microscopic images, radiographic images, magnetic resonance image (MRI) as well as medical signals such as electrocardiogram (ECG) and electroencephalogram (EEG). Normally, the scientist or doctors have to deal with myriad of data and redundant to be processed. In order to reduce the complexity of the diagnosis process, only the significant features of the raw data such as peak value of the ECG signal or size of lesion in the mammogram images will be extracted and considered in the subsequent stages. Mathematical models and statistical analyses will be performed to select the most significant features to be classified. The statistical analyses such as principal component analysis and discriminant analysis as well as mathematical model of clustering technique have been widely used in developing the medical diagnostic systems. The selected features will be classified using mathematical models that embedded engineering theory such as artificial intelligence, support vector machine, neural network and fuzzy-neuro system. These classifiers will provide the diagnostic results without human intervention. Among many publishable researches, several prototypes have been developed namely NeuralPap, Neural Mammo, and Cervix Kit. The former system (NeuralPap) is an automatic intelligent diagnostic system for classifying and distinguishing between the normal and cervical cancerous cells. Meanwhile, the Cervix Kit is a portable Field-programmable gate array (FPGA)-based cervical diagnostic kit that could automatically diagnose the cancerous cell based on the images obtained during sampling test. Besides the cervical diagnostic system, the Neural Mammo system is developed to specifically aid the diagnosis of breast cancer using a fine needle aspiration image.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2017

Hydroacoustic Assessment of Behavioral Responses by Fish Passing Near an Operating Tidal Turbine in the East River, New York

An important environmental issue facing the marine and hydrokinetic energy industry is whether fish that encounter underwater energy devices are likely to be struck and injured by moving components, primarily rotating turbine blades. The automated analysis of nearly 3 weeks of multibeam hydroacoustics data identified about 35,000 tracks of fish passing a tidal turbine in the East River, New York. These tracks included both individual fish and schools during periods with the turbine absent, the turbine present and operating, and the turbine present but not operating. The density of fish in the sampled area when the turbine was absent was roughly twice the density observed when the turbine was in place, particularly when the turbine was operating. This suggests that some avoidance occurred before fish were close enough to the turbine to be observed by the hydroacoustics system. Various measures of swimming behavior (direction, velocity, and linearity) were calculated for each track and evaluated for indication of behavioral responses to turbine presence and operation. Fish tracks were grouped based on tidal cycle, current velocity, and swimming direction and were evaluated with respect to turbine presence and operation and with respect to distance from the turbine. Nonparametric tests (Kolmogorov–Smirnov test) and multivariate analysis (canonical discriminant analysis) found significant differences among groups with respect to turbine presence and operation, suggesting that some fish responded to the turbine by adjusting swimming behavior, such as making small adjustments to swimming direction and velocity as they passed near the turbine. We found no evidence that fish were being struck by rotating blades, but there did appear to be large-scale avoidance initiated out of the range of the hydroacoustics detection system. Furthermore, more study is needed to determine whether such avoidance behavior has significant ramifications for normal fish movement patterns, bioenergetics, seasonal migrations, and predator exposure.

13 HYDRO ENERGY↗
DOE OSTI2018

Automated Optically Guided System for Chemical Analysis of Single Plant and Algae Cells Using Laser Microdissection/Liquid Vortex Capture/Mass Spectrometry

Current analytical methods are not capable of providing rapid, sensitive, and comprehensive chemical analysis of a wide range of cellular constitutes of single cells (e.g., lipids, metabolites, proteins, etc.) from dispersed cell suspensions and thin tissues. This capability is important for a number of critical applications, including discovery of cellular mechanisms for coping with chemical or environmental stress and cellular response to drug treatment, to name a few. Here we introduce an optically guided platform and methodology for rapid, automated recognition, sampling, and chemical analysis of surface confined individual cells utilizing a novel hybrid laser capture microdissection/liquid vortex capture/mass spectrometry system. The system enabled automated analysis of single cells by reliably detecting and sampling them either through laser ablation from a glass microscope slide or by cutting the entire cell out of a poly(ethylene naphthalate)-coated membrane substrate that the cellular sample is deposited on. Proof of principle experiments were performed using thin tissues of Allium cepa and cultured Euglena gracilis and Phacus cell suspensions as model systems for single cell analysis using the developed method. Reliable, hands-off laser ablation sampling coupled to liquid vortex capture/mass spectrometry analysis was conducted for hundreds of individual Allium cepa cells in connected tissue. In addition, more than 300 individual Euglena gracilis and Phacus cells were analyzed automatically and sampled using laser microdissection sampling with the same liquid vortex capture/mass spectrometry analysis system. Principal component analysis-linear discriminant analysis, applied to each mass spectral dataset, was used to determine the accuracy of differentiation of the different algae cell lines.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Detection of the Metabolic Response to Drought Stress Using Hyperspectral Reflectance

Drought is the most important limitation on crop yield. Understanding and detecting drought stress in crops is vital for improving water use efficiency through effective breeding and management. Leaf reflectance spectroscopy offers a rapid, non-destructive alternative to traditional techniques for measuring plant traits involved in a drought response. We measured drought stress in six glasshouse-grown agronomic species using physiological, biochemical and spectral data. In contrast to physiological traits, leaf metabolite concentrations revealed drought stress before it was visible to the naked eye. We used full-spectrum leaf reflectance data to predict metabolite concentrations using partial least-squares regression, with validation R2 values of 0.49 to 0.87. We show for the first time that spectroscopy may be used for the quantitative estimation of proline and abscisic acid, demonstrating the first use of hyperspectral data to detect a phytohormone. We used linear discriminant analysis and partial least squares discriminant analysis to differentiate between droughted and watered plants based on measured traits (accuracy: 71%) and raw spectral data (66%). Finally, we validated our glasshouse-developed models in an independent field trial. We demonstrate that spectroscopy can detect drought stress via underlying biochemical changes, before visual differences occur, representing a powerful advance for measuring limitations on yield.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Data-driven analysis of relight variability of jet fuels induced by turbulence

For safety purposes, reliable reignition of aircraft engines in the event of flame blow-out is a critical requirement. Typically, an external ignition source in the form of a spark is used to achieve a stable flame in the combustor. However, such forced turbulent ignition may not always successfully relight the combustor, mainly because the state of the combustor cannot be precisely determined. Uncertainty in the turbulent flow inside the combustor, inflow conditions, and spark discharge characteristics can lead to variability in sparking outcomes even for nominally identical operating conditions. Prior studies have shown that of all the uncertain parameters, turbulence is often dominant and can drastically alter ignition behavior. For instance, even when different fuels have similar ignition delay times, their ignition behavior in practical systems can be completely different. In practical operating conditions, it is challenging to understand why ignition fails and how much variation in outcomes can be expected. The focus of this work is to understand relight variability induced by turbulence for two different aircraft fuels, namely Jet-A and a variant named C1. A detailed, previously developed simulation approach is used to generate a large number of successful and failed ignition events. Using this data, the cause of misfire is evaluated based on a discriminant analysis that delineates the difference between turbulent initial conditions that lead to ignition or failure. From the discriminant analysis, a compressed sensing algorithm is then applied to help pinpoint the locations of relevant turbulent features. Findings from the discriminant analysis are confirmed with the time history of near kernel properties. Next, a clustering strategy is used to identify ignition and misfire modes. With this approach, it was determined that the cause of ignition failure is different for the two fuels. While it was found that Jet-A is influenced by fuel entrainment, C1 was found to be more sensitive to small scale turbulence features. Finally, a larger variability is found in the ignition modes of C1, which can be subject to extreme events induced by kernel breakdown.

42 ENGINEERING↗
DOE OSTI2021

Structural Polymorphism of Chitin and Chitosan in Fungal Cell Walls From Solid-State NMR and Principal Component Analysis

Chitin is a major carbohydrate component of the fungal cell wall and a promising target for novel antifungal agents. However, it is technically challenging to characterize the structure of this polymer in native cell walls. Here, we recorded and compared 13 C chemical shifts of chitin using isotopically enriched cells of six Aspergillus, Rhizopus, and Candida strains, with data interpretation assisted by principal component analysis (PCA) and linear discriminant analysis (LDA) methods. The structure of chitin is found to be intrinsically heterogeneous, with peak multiplicity detected in each sample and distinct fingerprints observed across fungal species. Fungal chitin exhibits partial similarity to the model structures of α- and γ-allomorphs; therefore, chitin structure is not significantly affected by interactions with other cell wall components. Addition of antifungal drugs and salts did not significantly perturb the chemical shifts, revealing the structural resistance of chitin to external stress. In addition, the structure of the deacetylated form, chitosan, was found to resemble a relaxed two-fold helix conformation. This study provides high-resolution information on the structure of chitin and chitosan in their cellular contexts. The method is applicable to the analysis of other complex carbohydrates and polymer composites.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2016

Mapping Cheatgrass Across the Range of the Greater Sage-Grouse: Linking Biophysical, Climate and Remote Sensing Data to Predict Cheatgrass Occurrence

Increasing spread of invasive annual grasses, such as Bromus tectorum (cheatgrass), can contribute to increased fire frequency and hinder the reestablishment of native sagebrush, forbs, and grasses in subsequent years. Knowledge of the current distribution of cheatgrass on the landscape is a key component in planning and executing strategies to protect sagebrush ecosystems and sensitive wildlife species such as the Greater sage-grouse (Centrocercus urophasianus). Pacific Northwest National Laboratory (PNNL) worked with US Fish and Wildlife Service (FWS) to assemble and derive information to map cheatgrass occurrence across the historic range of sage-grouse. The information and map products described in this report can help land managers prioritize conservation efforts at the species’ range scale. We constructed an ecological model based on a suite of climatic and biophysical variables and satellite measures of peak NDVI (normalized difference vegetation index) – an index of vegetation greenness – to predict cheatgrass occurrence across the historic range of sage-grouse in the United States. More than 24,000 field measurements of cheatgrass cover across the study area were acquired from various agencies and research groups and reviewed for use in the modeling efforts. A subset of 6650 field measurement points were identified and verified for use in statistical analyses. For each measurement location we derived a suite of 50 biophysical and NDVI variables correlated with cheatgrass occurrence. Pairwise correlation of variables was examined to remove highly-correlated variables from the model. A total of 13 variables were retained for use in forward-stepping discriminant analysis and modeling. Discriminant scores were used to determine probability of cheatgrass occurrence, which was broken into two relative cover classes: 0% to 2% cover and > 2% cheatgrass cover. This report describes the data and methods used to develop the model and the cheatgrass occurrence map. We provide a brief discussion of the accuracy of classification, and describe the appropriate scale of use for map results. The range-wide map of occurrence will be made available online for FWS and partner agencies.

54 ENVIRONMENTAL SCIENCES↗