Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Modal Testing”

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 397 records · Page 22

SU-F-J-172: Hybrid MR/CT Compatible Phantom for MR-Only Based Radiotherapy

Purpose: Development of hybrid MR/CT compatible phantom was introduced to fully establish MR image only radiation treatment and this suggested technique using in-house developed hybrid MR/CT compatible phantom image would utilize to generate radiation treatment planning and perform dose calculation without multi-modal registration process or generation of pseudo CT. Methods: Fundamental characteristics for “hybrid MR/CT compatible phantom” was established: Relaxation times equivalent to human tissue, dielectric properties, homogeneous relaxation times, sufficient strength to fabricate a torso, ease of handling, a wide variety of density material for calibration, chemical and physical stability over an extended time. For this requirements, chemical component in each tested plug which would be tissue equivalent to human tissue on MR and CT image and production of phantom body and plug was performed. Chemical component has described below: Agaros, GdCl{sub 3}, NaN{sub 3}, NaCl, K{sub 2}Co{sub 3}, deionized-distilled water. Various mixture of chemical component to simulate human tissue on both MR and CT image was tested by measuring T1, T2 relaxation time and signal intensity (SI) on MR image and Hounsfield unit (HU) on CT and each value was compared. The hybrid MR/CT compatible phantom with 14 plugs was designed and has made. Total height and external diameter was decided by internal size of 32 channel MR head-coil. Results: Tissue-equivalent chemical component materials and hybrid MR/CT compatible phantom was developed. The range of T1, T2 relaxation time and SI on MR image, HU on CT was acquired and could be adjusted to correspond to simulated human tissue. Conclusion: Current result shows its possibility for MR-only based radiotherapy and the best mixing rate of chemical component for tissue-equivalent image on MR and CT was founded. However, additional technical issues remain to be overcome. Conversion of SI on MR image into HU and dose calculation based on converted MRI will be progressing.

60 APPLIED LIFE SCIENCES↗

Validating and improving CT ventilation imaging by correlating with ventilation 4D-PET/CT using {sup 68}Ga-labeled nanoparticles

Purpose: CT ventilation imaging is a novel functional lung imaging modality based on deformable image registration. The authors present the first validation study of CT ventilation using positron emission tomography with{sup 68}Ga-labeled nanoparticles (PET-Galligas). The authors quantify this agreement for different CT ventilation metrics and PET reconstruction parameters. Methods: PET-Galligas ventilation scans were acquired for 12 lung cancer patients using a four-dimensional (4D) PET/CT scanner. CT ventilation images were then produced by applying B-spline deformable image registration between the respiratory correlated phases of the 4D-CT. The authors test four ventilation metrics, two existing and two modified. The two existing metrics model mechanical ventilation (alveolar air-flow) based on Hounsfield unit (HU) change (V{sub HU}) or Jacobian determinant of deformation (V{sub Jac}). The two modified metrics incorporate a voxel-wise tissue-density scaling (ρV{sub HU} and ρV{sub Jac}) and were hypothesized to better model the physiological ventilation. In order to assess the impact of PET image quality, comparisons were performed using both standard and respiratory-gated PET images with the former exhibiting better signal. Different median filtering kernels (σ{sub m} = 0 or 3 mm) were also applied to all images. As in previous studies, similarity metrics included the Spearman correlation coefficient r within the segmented lung volumes, and Dice coefficient d{sub 20} for the (0 − 20)th functional percentile volumes. Results: The best agreement between CT and PET ventilation was obtained comparing standard PET images to the density-scaled HU metric (ρV{sub HU}) with σ{sub m} = 3 mm. This leads to correlation values in the ranges 0.22 ⩽ r ⩽ 0.76 and 0.38 ⩽ d{sub 20} ⩽ 0.68, with r{sup ¯}=0.42±0.16 and d{sup ¯}{sub 20}=0.52±0.09 averaged over the 12 patients. Compared to Jacobian-based metrics, HU-based metrics lead to statistically significant improvements in r{sup ¯} and d{sup ¯}{sub 20} (p < 0.05), with density scaled metrics also showing higher r{sup ¯} than for unscaled versions (p < 0.02). r{sup ¯} and d{sup ¯}{sub 20} were also sensitive to image quality, with statistically significant improvements using standard (as opposed to gated) PET images and with application of median filtering. Conclusions: The use of modified CT ventilation metrics, in conjunction with PET-Galligas and careful application of image filtering has resulted in improved correlation compared to earlier studies using nuclear medicine ventilation. However, CT ventilation and PET-Galligas do not always provide the same functional information. The authors have demonstrated that the agreement can improve for CT ventilation metrics incorporating a tissue density scaling, and also with increasing PET image quality. CT ventilation imaging has clear potential for imaging regional air volume change in the lung, and further development is warranted.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

A Cyber Threat Mitigation Approach For Wide Area Control of SVCs using Stability Monitoring

We propose a stability monitoring approach for the mitigation of cyber threats directed at the wide area control (WAC) system used for coordinated control of Flexible AC Transmission Systems (FACTS) used for power oscillation damping (POD) of active power flow on inter-area tie lines. The approach involves monitoring the modes of the active power oscillation on an inter-area tie line using the Matrix Pencil (MP) method. We use the stability characteristics of the observed modes as a proxy for the presence of destabilizing cyber threats. We monitor the system modes to determine whether any destabilizing modes appear after the WAC system engages to control the POD. If the WAC signal exacerbates the POD performance, the FACTS falls back to POD using local measurements. The proposed approach does not require an expansive system-wide view of the network. We simulate replay, control integrity, and timing attacks for a test system and present results that demonstrate the performance of the SM approach for mitigation.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Localized Cyber Threat Mitigation Approach For Wide Area Control of FACTS

We propose a localized oscillation amplitude monitoring (OAM) method for the mitigation of cyber threats directed at the wide area control (WAC) system used to coordinate control of Flexible AC Transmission Systems (FACTS) for power oscillation damping (POD) of active power flow on inter-area tie lines. The method involves monitoring the inter-area tie line active power oscillation amplitude over a sliding window. We use system instability - inferred from oscillation amplitudes growing instead of damping - as evidence of an indication of a malfunction in the WAC of FACTS, possibly indicative of a cyber attack. Monitoring the presence of such a growth allows us to determine whether any destabilizing behaviors appear after the WAC system engages to control the POD. If the WAC signal increases the oscillation amplitude over time, thereby diminishing the POD performance, the FACTS falls back to POD using local measurements. The proposed method does not require an expansive system-wide view of the network. We simulate replay, control integrity, and timing attacks for a test system and present results that demonstrate the performance of the OAM method for mitigation.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Properties of different LLM-105 preparations

LLM-105 (2,6-diamino-3,5-dinitropyrazine-1-oxide) has been prepared at several different size quantities (~10–70 Kg) and not subjected to further purification, such as recrystallization. Chemical and physical properties were compared—small-scale safety testing (impact, friction, ESD), thermal (chemical reactivity, differential scanning calorimetry (DSC), thermogravimetric analysis (TGA), one-dimensional time-to-explosion (ODTX)), morphological (particle-size distribution (PSD), scanning electron microscopy (SEM), powder x-ray diffraction (PXRD), skeletal density). Each preparation had similar properties to the other preparations except for PSD and PXRD. For PSD, all preparations exhibited a mono-modal distribution with a variation in median values from ~ 40 μm to over 80 μm. All PXRD values indicated the same morphology with minor variations in crystal orientations. Possible polymorphism was also observed in a few cases. SEM images and PXRD indicate all preparations to be diamond-type and X-type crystals with some twinning. Impact, friction, and ESD and thermal sensitivities values are consistent with these type of crystal habits as seen in vast literature studies.

Explosive characterization↗

Evaluation of Direct Drive Capsule Fill-Tube Assembly Survivability in Support of the 100 GBar Campaign

Capsule fill-tube target assemblies (CFTAs) for direct-drive have been demonstrated in the past for Laser for Laboratory Energetics (LLE) cryogenic layering studies, evolving and building upon successful deliveries for NIF. The current 100 GigaBar (GBar) campaign requires increased tolerances over prior CFTA work in terms of robustness, cleanliness, reduced fill tube diameter and glue size. To tackle these challenges, GA and LLE are developing a direct drive CFTA that survives all fabrication activities, from assembly, qualification testing and transport to cryogenic layering and target chamber insertion at the OMEGA laser facility. Approximately 55 CFTAs of two main designs have been constructed and tested to date, building off the current LLE cryogenic layering study CFTA design (typically 870 µm diameter x 25 µm thick wall capsule). Variations of glass fill tubes sizes from 30, 20 and 10 µm diameter, which are inserted and glued into the capsule. Testing protocols were developed to enable comparison of different designs against one another and evaluate their robustness at room temperature. The testing protocols include pressure checks, resonant vibration mode sweeps, runout and vibration testing to a power spectral density (PSD) input. In this paper we will compare the different design tradeoffs, measurements and results including glue fillets, sag of the fill tubes under gravity, runout and hysteresis, ringdown response, X-ray imaging of the pipette wall thicknesses, and scanning electron microscope (SEM) images taken of failed fill tubes and glue joints. Assessment of the modal vibration modeling for the designs will be compared against the vibration data. Lastly, a design recommendation is put forth meeting the design constraints, which consists of a polymicro composite tube and 10 µm fill tube, ensuring survivability at cryogenic temperatue, a higher first mode resonance and smaller fuel volume.

100 GBar↗

Final technical report

Our overarching goals in this project were to: Develop and improve high-throughput sequencing methods and analytical approaches for quantitative analyses of microbial gene expression at the Hawaii Ocean Time Series Station and the Bermuda Atlantic Time Series Station; Conduct field analyses following gene expression patterns in picoplankton microbial communities in general, and Prochlorococcus flow sorted from that community, as they respond to different environmental variables (light, macronutrients, dissolved organic carbon), that are predicted to influence activity, productivity, and carbon cycling; Use the expression analyses of flow sorted Prochlorococcus to identify horizontally transferred genes and gene products, in particular those that are located in genomic islands and likely to confer habitat-specific fitness advantages; Use the microbial community gene expression data that we generate to gain insights, and test hypotheses, about the variability, genomic context, activity and function of as yet uncharacterized gene products, that appear highly expressed in the environment. We achieved the above goals, and even more over the course of the project. This includes a number of novel methodological developments, as well as the standardization of microbial community gene expression analyses in both field surveys, and experimental modalities. The availability of these methods, tools and approaches is changing current practice in microbial community analyses.

59 BASIC BIOLOGICAL SCIENCES↗

Cable effects study : tangents, rat holes, dead ends, and valuable results.

An overview of the study of the effects that electrical power and signal cables introduce on the dynamic response of precision structures is presented, along with a summary of lessons learned and most significant results. This was a three-year effort conducted at the Air Force Research Laboratory, Space Vehicles Directorate to discover a set of practical approaches for updating well defined dynamical models of cableless structures where knowledge of the cable type, position, and tie-down method are known. While cables can be found on many different types of structures, the focus of this effort was on precision, low-damping, and low-first modal frequency structures. Various obstacles, classified as tangents, rat holes, and dead ends, were encountered along the way. Rather than following a strictly technical flow, the paper presents the historical, experiential progression of the project. First, methods were developed to estimate cable properties. Problems were encountered because of the flexible, highly damped nature of cables. A simple beam was used as a test article to validate experimentally derived cable properties and to refine the assumptions regarding boundary conditions. A spacecraft bus-like panel with cables attached was designed, and finite element models were developed and validated through experiment. Various paths were investigated at each stage before a consistent test and analysis methodology was developed. These twists and turns are described.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Lymphangiography in the Diagnosis and Localization of Various Chyle Leaks

Purpose: Chyle leaks are rare entities infrequently encountered by most physicians. However, large centers providing advanced surgical care are inevitably confronted with chyle leaks as a complication of surgery, an extension of disease, or as a primary disorder. Regardless of the etiology, proper diagnosis and localization are paramount in the management of any chyle leak. Materials and Methods: Here we present 16 patients with 17 chyle leaks (5 chyluria, 8 chylothorax, and 4 chylous ascites) who underwent bipedal lymphangiography (LAG) and postprocedure computed tomography (CT) imaging. Results: In each case, the source of the chyle leak was identified and properly localized to guide further treatment. Of the 16 patients who underwent LAG and postprocedure CT imaging, the initial LAG alone provided the diagnosis and localized the chyle leak in 4 patients (25%); the postprocedure CT imaging provided the diagnosis and localized the chyle leak in 6 patients (37.5%); and the two modalities were equal in the diagnosing and localizing the chyle leak in the remaining 6 patients (37.5%)ConclusionThese cases highlight the unparalleled abilities of LAG and the added benefit of post-LAG CT imaging in the diagnosis and fine anatomic localization of chyle leaks. In addition, these cases demonstrate the retained utility of LAG in these investigations despite the development of alternative tests involving CT, magnetic resonance imaging, and nuclear medicine imaging.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Noninvasive Assessment of Tumor Microenvironment Using Dynamic Contrast-Enhanced Magnetic Resonance Imaging and {sup 18}F-Fluoromisonidazole Positron Emission Tomography Imaging in Neck Nodal Metastases

Purpose: To assess noninvasively the tumor microenvironment of neck nodal metastases in patients with head-and-neck cancer by investigating the relationship between tumor perfusion measured using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and hypoxia measured by {sup 18}F-fluoromisonidazole ({sup 18}F-FMISO) positron emission tomography (PET). Methods and Materials: Thirteen newly diagnosed head-and-neck cancer patients with metastatic neck nodes underwent DCE-MRI and {sup 18}F-FMISO PET imaging before chemotherapy and radiotherapy. The matched regions of interests from both modalities were analyzed. To examine the correlations between DCE-MRI parameters and standard uptake value (SUV) measurements from {sup 18}F-FMISO PET, the nonparametric Spearman correlation coefficient was calculated. Furthermore, DCE-MRI parameters were compared between nodes with {sup 18}F-FMISO uptake and nodes with no {sup 18}F-FMISO uptake using Mann-Whitney U tests. Results: For the 13 patients, a total of 18 nodes were analyzed. The nodal size strongly correlated with the {sup 18}F-FMISO SUV ({rho} = 0.74, p < 0.001). There was a strong negative correlation between the median k{sub ep} (redistribution rate constant) value ({rho} = -0.58, p = 0.042) and the {sup 18}F-FMISO SUV. Hypoxic nodes (moderate to severe {sup 18}F-FMISO uptake) had significantly lower median K{sup trans} (volume transfer constant) (p = 0.049) and median k{sub ep} (p = 0.027) values than did nonhypoxic nodes (no {sup 18}F-FMISO uptake). Conclusion: This initial evaluation of the preliminary results support the hypothesis that in metastatic neck lymph nodes, hypoxic nodes are poorly perfused (i.e., have significantly lower K{sup trans} and k{sub ep} values) compared with nonhypoxic nodes.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Predictive Factors for Radiation Pneumonitis in Hodgkin Lymphoma Patients Receiving Combined-Modality Therapy

Purpose: This study sought to quantify the risk of radiation pneumonitis (RP) in Hodgkin lymphoma (HL) patients receiving mediastinal radiation therapy (RT) and to identify predictive factors for RP. Methods and Materials: We identified 75 patients with newly diagnosed HL treated with mediastinal RT and 17 patients with relapsed/refractory HL treated with mediastinal RT before or after transplant. Lung dose-volumetric parameters including mean lung dose and percentage of lungs receiving 20 Gy were calculated. Factors associated with RP were explored by use of the Fisher exact test. Results: RP developed in 7 patients (10%) who received mediastinal RT as part of initial therapy (Radiation Therapy Oncology Group Grade 1 in 6 cases). A mean lung dose of 13.5 Gy or greater (p = 0.04) and percentage of lungs receiving 20 Gy of 33.5% or greater (p = 0.009) significantly predicted for RP. RP developed in 6 patients (35%) with relapsed/refractory HL treated with peri-transplant mediastinal RT (Grade 3 in 4 cases). Pre-transplant mediastinal RT, compared with post-transplant mediastinal RT, significantly predicted for Grade 3 RP (57% vs. 0%, p = 0.015). Conclusions: We identified threshold lung metrics predicting for RP in HL patients receiving mediastinal RT as part of initial therapy, with the majority of cases being of mild severity. The risk of RP is significantly higher with peri-transplant mediastinal RT, especially among those who receive pre-transplant RT.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

SU-E-J-251: Incorporation of Pre-Therapy 18F-FDG Uptake with CT Texture Features in a Predictive Model for Radiation Pneumonitis Development

Purpose: To determine whether the addition of standardized uptake value (SUV) statistical variables to CT lung texture features can improve a predictive model of radiation pneumonitis (RP) development in patients undergoing radiation therapy. Methods: Anonymized data from 96 esophageal cancer patients (18 RP-positive cases of Grade ≥ 2) were retrospectively collected including pre-therapy PET/CT scans, pre-/posttherapy diagnostic CT scans and RP status. Twenty texture features (firstorder, fractal, Laws’ filter and gray-level co-occurrence matrix) were calculated from diagnostic CT scans and compared in anatomically matched regions of the lung. The mean, maximum, standard deviation, and 50th–95th percentiles of the SUV values for all lung voxels in the corresponding PET scans were acquired. For each texture feature, a logistic regression-based classifier consisting of (1) the average change in that texture feature value between the pre- and post-therapy CT scans and (2) the pre-therapy SUV standard deviation (SUV{sub SD}) was created. The RP-classification performance of each logistic regression model was compared to the performance of its texture feature alone by computing areas under the receiver operating characteristic curves (AUCs). T-tests were performed to determine whether the mean AUC across texture features changed significantly when SUV{sub SD} was added to the classifier. Results: The AUC for single-texturefeature classifiers ranged from 0.58–0.81 in high-dose (≥ 30 Gy) regions of the lungs and from 0.53–0.71 in low-dose (< 10 Gy) regions. Adding SUVSD in a logistic regression model using a 50/50 data partition for training and testing significantly increased the mean AUC by 0.08, 0.06 and 0.04 in the low-, medium- and high-dose regions, respectively. Conclusion: Addition of SUVSD from a pre-therapy PET scan to a single CT-based texture feature improves RP-classification performance on average. These findings demonstrate the potential for more accurate prediction of RP using information from multiple imaging modalities. Supported, in part, by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under grant number T32 EB002103; SGA receives royalties and licensing fees through the University of Chicago for computer-aided diagnosis technology. HA receives royalties through the University of Chicago for computer-aided diagnosis technology.

60 APPLIED LIFE SCIENCES↗

Defining the mechanistic binding of viral particles to a multi‐modal anion exchange resin

A multi‐tiered approach to determine the binding mechanism of viral clearance utilizing a multi‐modal anion exchange resin was applied to a panel of four viral species that are typically used in validating viral clearance studies (i.e., X‐MuLV, MVM, REO3, and PrV). First, virus spiked buffer‐only experiments were conducted to evaluate the virus's affinity for single mode and multi‐modal chromatography resins under different buffer conditions in a chromatography column setting. From these results we hypothesize that the mechanisms of binding of the viruses involve binding to both the hydrophobic and anionic functional groups. This mechanistic view agreed with the general surface characteristics of the different virus species in terms of isoelectric point and relative hydrophobicity values. This hypothesized mechanistic binding was then tested with commercially relevant, in‐process materials, in which competitive binding occurred between the load components (e.g., viruses, target product, and impurities) and the resin. © 2018 American Institute of Chemical Engineers Biotechnol. Prog. , 34:1019–1026, 2018

Brown, Matthew R.↗

Long-term Results of the UCSF-LBNL Randomized Trial: Charged Particle With Helium Ion Versus Iodine-125 Plaque Therapy for Choroidal and Ciliary Body Melanoma

Purpose: Relevant clinical data are needed given the increasing national interest in charged particle radiation therapy (CPT) programs. Here we report long-term outcomes from the only randomized, stratified trial comparing CPT with iodine-125 plaque therapy for choroidal and ciliary body melanoma. Methods and Materials: From 1985 to 1991, 184 patients met eligibility criteria and were randomized to receive particle (86 patients) or plaque therapy (98 patients). Patients were stratified by tumor diameter, thickness, distance to disc/fovea, anterior extension, and visual acuity. Tumors close to the optic disc were included. Local tumor control, as well as eye preservation, metastases due to melanoma, and survival were evaluated. Results: Median follow-up times for particle and plaque arm patients were 14.6 years and 12.3 years, respectively (P=.22), and for those alive at last follow-up, 18.5 and 16.5 years, respectively (P=.81). Local control (LC) for particle versus plaque treatment was 100% versus 84% at 5 years, and 98% versus 79% at 12 years, respectively (log rank: P=.0006). If patients with tumors close to the disc (<2 mm) were excluded, CPT still resulted in significantly improved LC: 100% versus 90% at 5 years and 98% versus 86% at 12 years, respectively (log rank: P=.048). Enucleation rate was lower after CPT: 11% versus 22% at 5 years and 17% versus 37% at 12 years, respectively (log rank: P=.01). Using Cox regression model, likelihood ratio test, treatment was the most important predictor of LC (P=.0002) and eye preservation (P=.01). CPT was a significant predictor of prolonged disease-free survival (log rank: P=.001). Conclusions: Particle therapy resulted in significantly improved local control, eye preservation, and disease-free survival as confirmed by long-term outcomes from the only randomized study available to date comparing radiation modalities in choroidal and ciliary body melanoma.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

FY25 Mid-Year Report: FNCL Enhancements Implementation

During the first half of FY25 the FNCL team has made consistent progress toward the completion of our project goals. The FNCL prototype panel design has been successfully applied to a fully instrumented 3-panel system which is actively under construction. The FNCL Demonstrator System contains solid scintillators instrumented with SiPMs, which operate on an updated CAEN digitizer, requires no high-voltage, and has a smaller overall footprint. The onboard software will include the LLNL-developed GMM-PSD signal processing. Later this year the system will be experimentally tested alongside the baseline FNCL instrument at LLNLs ISSA facility. In addition to a full systems test, the performance of a DD generator for active interrogation measurements compared to the standard AmLi source will be established for both systems. The data collected at the ISSA facility will be used to experimentally validate the FNCL-Fast Isotopic Fuel Assay’s (FIFA) capability to measure U-235 loading and to predict gadolinium poison content with passive interrogation. The FNCL-FIFA modal was benchmarked with simulation-based data and a user-friendly GUI was added earlier this year. Three separate codes have been submitted to the LLNL ESW system for review prior to their transfers. These include the Predictive Modeling Response toolkit, GMM-PSD firmware beta version, and the FNCL-FIFA analysis package with GUI and user documentation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Quantized Constant-Q Gabor Atoms for Sparse Binary Representations of Cyber-Physical Signatures

Increased data acquisition by uncalibrated, heterogeneous digital sensor systems such as smartphones present new challenges. Binary metrics are proposed for the quantification of cyber-physical signal characteristics and features, and a standardized constant-Q variation of the Gabor atom is developed for use with wavelet transforms. Two different continuous wavelet transform (CWT) reconstruction formulas are presented and tested under different signal to noise ratio (SNR) conditions. A sparse superposition of Nth order Gabor atoms worked well against a synthetic blast transient using the wavelet entropy and an entropy-like parametrization of the SNR as the CWT coefficient-weighting functions. The proposed methods should be well suited for sparse feature extraction and dictionary-based machine learning across multiple sensor modalities.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗

Deep Learning Classification of Cheatgrass Invasion in the Western United States Using Biophysical and Remote Sensing Data

Cheatgrass (Bromus tectorum) invasion is driving an emerging cycle of increased fire frequency and irreversible loss of wildlife habitat in the western US. Yet, detailed spatial information about its occurrence is still lacking for much of its presumably invaded range. Deep learning (DL) has demonstrated success for remote sensing applications but is less tested on more challenging tasks like identifying biological invasions using sub-pixel phenomena. We compare two DL architectures and the more conventional Random Forest and Logistic Regression methods to improve upon a previous effort to map cheatgrass occurrence at >2% canopy cover. High-dimensional sets of biophysical, MODIS, and Landsat-7 ETM+ predictor variables are also compared to evaluate different multi-modal data strategies. All model configurations improved results relative to the case study and accuracy generally improved by combining data from both sensors with biophysical data. Cheatgrass occurrence is mapped at 30 m ground sample distance (GSD) with an estimated 78.1% accuracy, compared to 250-m GSD and 71% map accuracy in the case study. Furthermore, DL is shown to be competitive with well-established machine learning methods in a limited data regime, suggesting it can be an effective tool for mapping biological invasions and more broadly for multi-modal remote sensing applications.

54 ENVIRONMENTAL SCIENCES↗