Engineering Commons^™

Precision Weed Management Based On Uas Image Streams, Machine Learning, And Pwm Sprayers, Jason Allen Davis

Graduate Theses and Dissertations

Weed populations in agricultural production fields are often scattered and unevenly distributed; however, herbicides are broadcast across fields evenly. Although effective, in the case of post-emergent herbicides, exceedingly more pesticides are used than necessary. A novel weed detection and control workflow was evaluated targeting Palmer amaranth in soybean (Glycine max) fields. High spatial resolution (0.4 cm) unmanned aircraft system (UAS) image streams were collected, annotated, and used to train 16 object detection convolutional neural networks (CNNs; RetinaNet, Faster R-CNN, Single Shot Detector, and YOLO v3) each trained on imagery with 0.4, 0.6, 0.8, and 1.2 cm spatial resolutions. Models were …

Machine Learning Land Cover And Land Use Classification Of 4-Band Satellite Imagery, Lorelei Turner [*], Torrey J. Wagner, Paul Auclair, Brent T. Langhals

Faculty Publications

Land-cover and land-use classification generates categories of terrestrial features, such as water or trees, which can be used to track how land is used. This work applies classical, ensemble and neural network machine learning algorithms to a multispectral remote sensing dataset containing 405,000 28x28 pixel image patches in 4 electromagnetic frequency bands. For each algorithm, model metrics and prediction execution time were evaluated, resulting in two families of models; fast and precise. The prediction time for an 81,000-patch group of predictions wasmodels, and >5s for the precise models, and there was not a significant change in prediction time when a …

Arithfusion: An Arithmetic Deep Model For Temporal Remote Sensing Image Fusion, Md Reshad Ul Hoque, Jian Wu, Chiman Kwan, Krzysztof Koperski, Jiang Li

Electrical & Computer Engineering Faculty Publications

Different satellite images may consist of variable numbers of channels which have different resolutions, and each satellite has a unique revisit period. For example, the Landsat-8 satellite images have 30 m resolution in their multispectral channels, the Sentinel-2 satellite images have 10 m resolution in the pan-sharp channel, and the National Agriculture Imagery Program (NAIP) aerial images have 1 m resolution. In this study, we propose a simple yet effective arithmetic deep model for multimodal temporal remote sensing image fusion. The proposed model takes both low- and high-resolution remote sensing images at t₁ together with low-resolution images at a …

Deep Learning For Remote Sensing Image Processing, Yan Lu

Computational Modeling & Simulation Engineering Theses & Dissertations

Remote sensing images have many applications such as ground object detection, environmental change monitoring, urban growth monitoring and natural disaster damage assessment. As of 2019, there were roughly 700 satellites listing “earth observation” as their primary application. Both spatial and temporal resolutions of satellite images have improved consistently in recent years and provided opportunities in resolving fine details on the Earth's surface. In the past decade, deep learning techniques have revolutionized many applications in the field of computer vision but have not fully been explored in remote sensing image processing. In this dissertation, several state-of-the-art deep learning models have been …

Evaluating The Effects Of Water Influx On The Mississippi Sound: Current Vs. Historical Relationships, Jarett Lee Bell

Electronic Theses and Dissertations

This research investigated the influence of the opening of the Bonnet Carre Spillway and other fresh water inputs on the Mississippi Sound. The Bonnet Carre Spillway was completed in 1931 and was constructed to protect New Orleans whenever the Mississippi River is at flood stage. The spillway drains into Lake Pontchartrain a brackish-water lagoon north of New Orleans which then drains into Lake Borgne and subsequently into the Mississippi Sound. The inflow of water from the spillway changes the water chemistry of all receiving water bodies and impacts the waters of the Mississippi Gulf Coast. We collected in-situ temperature specific …

Cross Calibration And Validation Of Landsat 8 Oli And Sentinel 2a Msi, M. M. Farhad

Electronic Theses and Dissertations

This work describes a proposed radiometric cross calibration between the Landsat 8 Operational Land Imager (OLI) and Sentinel 2A Multispectral Instrument (MSI) sensors. The cross calibration procedure involves i) correction of the MSI data to account for spectral band differences with the OLI; and ii) correction of BRDF effects in the data from both sensors using a new model accounting for the view zenith/azimuth angles in addition to the solar zenith/view angles. Following application of the spectral and BRDF corrections, standard least-squares linear regression is used to determine the cross calibration gain and offset in each band. Uncertainties related to …

Remote Sensing Of The Environmental Impacts Of Utility-Scale Solar Energy Plants, Mohammad Masih Edalat

UNLV Theses, Dissertations, Professional Papers, and Capstones

Solar energy has many environmental benefits compared with fossil fuels but solar farming can have environmental impacts especially during construction and development. Thus, in order to enhance environmental sustainability, it is imperative to understand the environmental impacts of utility-scale solar energy (USSE) plants. During recent decades, remote sensing techniques and geographic information systems have become standard techniques in environmental applications. In this study, the environmental impacts of USSE plants are investigated by analyzing changes to land surface characteristics using remote sensing. The surface characteristics studied include land cover, land surface temperature, and hydrological response whereas changes are mapped by comparing …

Development Of A Multiband Remote Sensing System For Determination Of Unsaturated Soil Properties, Cyrus D. Garner

Graduate Theses and Dissertations

A multiband system including active microwave sensing and visible-near infrared reflectance spectroscopy was developed to measure unsaturated soil properties in both field and laboratory environments. Remote measurements of soil volumetric water content (θv), soil water matric potential (ψ), and soil index properties (liquid limit [LL], plastic limit [PL], and clay fraction [CF]) were conducted. Field-based measurement of θv was conducted using a ground-based radar system and field measurements within 10 percentage points of measurements acquired with traditional sampling techniques were obtained. Laboratory-based, visible and near infrared spectroscopy was found to be capable of obtaining empirical, soil specific regression functions (partial …

Using Remote Sensing To Estimate Crop Water Use To Improve Irrigation Water Management, Arturo Reyes-Gonzalez

Electronic Theses and Dissertations

Irrigation water is scarce. Hence, accurate estimation of crop water use is necessary for proper irrigation managements and water conservation. Satellite-based remote sensing is a tool that can estimate crop water use efficiently. Several models have been developed to estimate crop water requirement or actual evapotranspiration (ETa) using remote sensing. One of them is the Mapping EvapoTranspiration at High Resolution using Internalized Calibration (METRIC) model. This model has been compared with other methods for ET estimations including weighing lysimeters, pan evaporation, Bowen Ratio Energy Balance System (BREBS), Eddy Covariance (EC), and sap flow. However, comparison of METRIC model outputs to …

Estimating The Water Quality Condition Of River And Lake Water In The Midwestern United States From Its Spectral Characteristics, Jing Tan

Open Access Dissertations

This study focuses on developing/calibrating remote sensing algorithms for water quality retrieval in Midwestern rivers and lakes. In the first part of this study, the spectral measurements collected using a hand-held spectrometer as well as water quality observations for the Wabash River and its tributary the Tippecanoe River in Indiana were used to develop empirical models for the retrieval of chlorophyll (chl) and total suspended solids (TSS). A method for removing sky and sun glint from field spectra for turbid inland waters was developed and tested. Empirical models were then developed using a subset of the field measurements with the …

Sparse Coding Based Dense Feature Representation Model For Hyperspectral Image Classification, Ender Oguslu, Guoqing Zhou, Zezhong Zheng, Khan Iftekharuddin, Jiang Li

Electrical & Computer Engineering Faculty Publications

We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the l₁/l_q regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear …

Novel Deployment Of Elpasolites As A Dual Neutron / Gamma-Ray Directional Detector, Amber Lynn Guckes

UNLV Theses, Dissertations, Professional Papers, and Capstones

At a time when upholding national security has never been more important, there exists a need for the advancement of radiation detection technologies. Neutron and photon detectors are essential to fulfilling mission areas including detection and localization of missing, stolen or smuggled radiological or nuclear materials, quantification of the effects of a radiological or nuclear event, and supporting nonproliferation efforts. The aim of this study was to evaluate a new radiation detector based on the scintillation elpasolite compound Cs2LiYCl6:Ce (CLYC) for simultaneous measurements of neutron and photon flux and the localization of radiation sources. Previous studies performed on the CLYC …

Remote Sensing Based On Hyperspectral Data Analysis, Ershad Sharifahmadian

UNLV Theses, Dissertations, Professional Papers, and Capstones

In remote sensing, accurate identification of far objects, especially concealed objects is difficult. In this study, to improve object detection from a distance, the hyperspecral imaging and wideband technology are employed with the emphasis on wideband radar. As the wideband data includes a broad range of frequencies, it can reveal information about both the surface of the object and its content. Two main contributions are made in this study:

1) Developing concept of return loss for target detection: Unlike typical radar detection methods which uses radar cross section to detect an object, it is possible to enhance the process of …

Modeling Acoustic Scattering From The Seabed Using Transport Theory, Jorge Quijano, Lisa M. Zurk

Electrical and Computer Engineering Faculty Publications and Presentations

Radiative Transfer (RT) theory has established itself as an important tool for electromagnetic remote sensing in parallel plane geometries with random distributions of scatterers, and most recently it has also been proposed as a model for the propagation of elastic waves in layered ocean sediments. In this work the capabilities of this model are illustrated, as the RT method is used to predict backscattering strength from laboratory models of random media. The RT model is characterized by its flexibility on accommodating scatterers in a broad variety of sizes, shapes, and acoustic contrast relative to the background media. Additionally, this formulation …

Using Multiple Robust Parameter Design Techniques To Improve Hyperspectral Anomaly Detection Algorithm Performance, Matthew T. Davis

Theses and Dissertations

Detecting and identifying objects of interest is the goal of all remote sensing. New advances, specifically in hyperspectral imaging technology have provided the analyst with immense amounts of data requiring evaluation. Several filtering techniques or anomaly detection algorithms have been proposed. However, most new algorithms are insufficiently verified to be robust to the broad range of hyperspectral data being made available. One such algorithm, AutoGAD, is tested here via two separate robust parameter design techniques to determine optimal parameters for consistent performance on a range of data with large attribute variances. Additionally, the results of the two techniques are compared …

Vegetation Identification Based On Satellite Imagery, Vamsi K.R. Mantena, Ramu Pedada, Srinivas Jakkula, Yuzhong Shen, Jiang Li, Hamid R. Arabnia (Ed.)

Electrical & Computer Engineering Faculty Publications

Automatic vegetation identification plays an important role in many applications including remote sensing and high performance flight simulations. This paper presents a method to automatically identify vegetation based upon satellite imagery. First, we utilize the ISODATA algorithm to cluster pixels in the images where the number of clusters is determined by the algorithm. We then apply morphological operations to the clustered images to smooth the boundaries between clusters and to fill holes inside clusters. After that, we compute six features for each cluster. These six features then go through a feature selection algorithm and three of them are determined to …

Seasonal Adaptation Of Vegetation Color In Satellite Images, Srinivas Jakkula, Vamsi K.R. Mantena, Ramu Pedada, Yuzhong Shen, Jiang Li, Hamid R. Arabnia (Ed.)

Electrical & Computer Engineering Faculty Publications

Remote sensing techniques like NDVI (Normal Difference vegetative Index) when applied to phenological variations in aerial images, ascertained the seasonal rise and decline of photosynthetic activity in different seasons, resulting in different color tones of vegetation. The rise and fall of NDVI values decide the biological response, either the green up or brown down [1]. Vegetation in green up period appears with more vegetative vigor and during brown down period it has a dry appearance. This paper proposes a novel method that identifies vegetative patterns in satellite images and then alters vegetation color to simulate seasonal changes based on training …

Dynamics And Control Of Tethered Satellite Formations For The Purpose Of Space-Based Remote Sensing, Kurt A. Vogel

Theses and Dissertations

This dissertation assesses the utility of tethered satellite formations for the space-based remote sensing mission. Energy dissipation is found to have an adverse effect on foundational rigid body (Likins-Pringle) equilibria. It is shown that a continuously earth-facing equilibrium condition for a fixed-length tethered system does not exist since the spin rate required for the proper precession would not be high enough to maintain tether tension. The range of required spin rates for steady-spin motion is numerically defined here, but none of these conditions can meet the continuously earth-facing criteria. Of particular note is the discovery that applying certain rigid body …

Terrain And Spatial Effects On Hazard Prediction And Assessment Capability (Hpac) Software Dose-Rate Contour Plot Predictions As Compared To A Sample Of Local Fallout Data From Test Detonations In The Continental United States, 1945-1962, Kevin D. Pace

Theses and Dissertations

Hazard Prediction and Capability (HPAC) Software is validated by comparing modeled predictions to historical test data. Reanalysis weather data is acquired and reformatted for use in HPAC. Simulations are made using various amounts of weather data by use of a spatial domain. Simulations are also varied by levels of terrain resolution. The predicted output of the software is numerically compared to historical test data. The result of this research culminated in the knowledge that HPAC prediction accuracy is improved by using terrain resolutions beyond the flat earth assumption. Furthermore, this research establishes that domain size variation produces no significant advantage …

Modeling And Simulation Of Commercial Satellite Imagery Processes, David A. Shultz

Theses and Dissertations

The purpose of this research was to develop a general, statistical model of order-to-delivery times for commercial satellite imagery. The research looked at the current four satellite providers with 3-meter or better imagers in the context of a generalized model of commercial imaging satellite operations. Existing methods use orbit analysis tools to determine the imaging time of a specified target based on defined satellite position and times, but can only develop shortest and longest times to an imaging opportunity. To address the general question of the time it takes to deliver an image for non-specific targets, this research develops a …

Simulating A Chromotomographic Sensor For Hyperspectral Imaging In The Infrared, Anthony J. Dearinger

Theses and Dissertations

Hyperspectral imaging systems passively sense radiant electromagnetic energy from a remote scene to form a three dimension profile of the remote scene. The data contained in this profile describes real images of the remote scene for a certain number of spectral wavelength bands across a finite spectral range of electromagnetic radiation. Typical grating type hyperspectral imaging systems collect spectral electromagnetic radiation in the visible and near infrared spectral range, by incrementally scanning across the spatial extent of the remote scene. The legacy of low optical throughput because of the optical scanning techniques employed in these systems means adapting these systems …

Commercial Regional Space/Airborne Imaging, Ugur Akyazi, Ali Durmus, Birce Boga Bakirli, Arif Arin

Theses and Dissertations

In this work goal programming is used to solve a minimum cost multicommodity network flow problem with multiple goals. A single telecommunication network with multiple commodities (e.g., voice, video, data, etc.) flowing over it is analyzed. This network consists of: linear objective function, linear cost arcs, fixed capacities, specific origin-destination pairs for each commodity. A multicommodity network flow problem with goals can be successfully modeled using linear goal programming techniques. When properly modeled, network flow techniques may be employed to exploit the pure network structure of a multicommodity network flow problem with goals. Lagrangian relaxation captures the essence of the …

Manipulation Of High Spatial Resolution Aircraft Remote Sensing Data For Use In Site-Specific Farming, Gabriel B. Senay, Andrew D. Ward, John G. Lyon, Norman R. Fausey, Sue E. Nokes

Biosystems and Agricultural Engineering Faculty Publications

Three spatial data sets consisting of high spatial resolution (1 m) remote sensing images acquired in 12 spectral bands, an on-the-go yield map, and a Digital Elevation Model were co-registered and evaluated for spatial variability studies in a Geographic Information Systems environment. Separate on-the-go yield maps were developed for 3, 5, and 12 statistically significant mean yield classes. For each yield class, the corresponding mean spectral and elevation data were extracted. The relationship between mean spectral and yield data was strongly linear (r = 0.99). Also, a strong linear relationship between mean yield and elevation data (r = 0.92) was …