Geography Commons^™

Effects Of Training Set Size On Supervised Machine-Learning Land-Cover Classification Of Large-Area High-Resolution Remotely Sensed Data, Christopher A. Ramezan, Timothy A. Warner, Aaron E. Maxwell, Bradley S. Price

Faculty & Staff Scholarship

The size of the training data set is a major determinant of classification accuracy. Neverthe- less, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algo- rithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic …

A Karst Feature Prediction Model For Prince Of Wales Island, Alaska Based On High Resolution Lidar Imagery, Alexander Lyles

Master's Theses or Doctor of Nursing Practice

Investigation into surface karst formation is significant to hazard prediction, hydrogeologic drainage, and land management. Southeast Alaska contains over 600,000 acres of mapped carbonate bedrock, and some of the fastest recorded karst dissolution in the world. The objectives of this study are to develop and compare multiple semi-automated models to map and delineate karst features from bare-earth LiDAR imagery using ArcGIS Desktop 10.7, and to apply a preliminary geostatistical analysis of sinkhole morphometric parameters to highlight potential spatial patterns of karst evolution on Prince of Wales Island, Alaska. A semi-automated approach of mapping karst features provides a dataset that minimizes …

Investigating The Spatial Behavior And Habitat Use Of The Matschie’S Tree-Kangaroo (Dendrolagus Matschiei) Using Gps Collars And Unmanned Aircraft Systems (Uas), Jonathan B. Byers

Graduate Student Theses, Dissertations, & Professional Papers

Understanding the movement patterns and habitat needs of the endangered Matschie’s tree-kangaroo (Dendrolagus matschiei) is important for their conservation and management. Endemic to the montane cloud forests of the Huon Peninsula in northeastern Papua New Guinea, these elusive arboreal marsupials are tremendously challenging to study using traditional observational methods.

This study is an assessment of novel techniques to overcome the significant challenges to in-situ data collection in remote and rugged tropical cloud forests. Animal locations are remotely tracked using purpose built altitude and motion logging GPS collars and habitat structure data is measured using photogrammetry from small Unmanned Aircraft …

An Application Of The Sleuth Model: Future Urbanization Of Davidson County, Tennessee, Caitlyn J. Linehan

Theses and Dissertations

As the urban population is expected to grow in the coming decades, there is pressure on urban areas to expand to accommodate this growth. Often times, these expansions are not sustainable, they consume valuable lands and cause significant environmental, social, and economic burdens, a theory which is known as urban sprawl. Therefore it is often imperative to model areas more likely to urbanize in order for cities to plan for their expansion in the most sustainable way possible. Nashville, Tennessee located within Davidson County is an area that has been experiencing a significant period of urban growth. The objective of …

Effects Of Bark Beetle Outbreaks On Forest Landscape Pattern In The Southern Rocky Mountains, U.S.A., Kyle C. Rodman, Robert A. Andrus, Cori L. Butkiewicz, Teresa B. Chapman, Nathan S. Gill, Brian J. Harvey, Dominik Kulakowski, Niko J. Tutland, Thomas T. Veblen, Sarah J. Hart

Geography

Since the late 1990s, extensive outbreaks of native bark beetles (Curculionidae: Scolytinae) have affected coniferous forests throughout Europe and North America, driving changes in carbon storage, wildlife habitat, nutrient cycling, and water resource provisioning. Remote sensing is a cru-cial tool for quantifying the effects of these disturbances across broad landscapes. In particular, Landsat time series (LTS) are increasingly used to characterize outbreak dynamics, including the presence and severity of bark beetle-caused tree mortality, though broad-scale LTS-based maps are rarely informed by detailed field validation. Here we used spatial and temporal information from LTS products, in combination with extensive field data …

Assessment Of Empirical And Semi-Analytical Algorithms Using Modis-Aqua For Representing In-Situ Chromophoric Dissolved Organic Matter (Cdom) In The Bering, Chukchi, And Western Beaufort Seas Of The Pacific Arctic Region, Melishia I. Santiago, Karen E. Frey

Geography

We analyzed a variety of satellite-based ocean color products derived using MODIS-Aqua to investigate the most accurate empirical and semi-analytical algorithms for representing in-situ chromophoric dissolved organic matter (CDOM) across a large latitudinal transect in the Bering, Chukchi, and western Beaufort Seas of the Pacific Arctic region. In particular, we compared the performance of empirical (CDOM index) and several semi-analytical algorithms (quasi-analytical algorithm (QAA), Carder, Garver-Siegel-Maritorena (GSM), and GSM-A) with field measurements of CDOM absorption (aCDOM) at 412 nanometers (nm) and 443 nm. These algorithms were compared with in-situ CDOM measurements collected on cruises during July 2011, 2013, 2014, 2015, …

Remote Sensing Applications In Population Estimation, Regression Analysis, And Urban Growth Simulation Modeling For A Middle Eastern City, Elaf Amer Alyasiri

Graduate Research Theses & Dissertations

Due to a change in government regime and population migration, the City of Hillah in Iraq has been facing several urban issues, particularly population estimating and urban growth planning. Since the last census conducted in 1997, population in Iraq has been estimated based on the annual growth, without considering migration as factor of the population growth. Therefore, the aim of this dissertation study was to develop a population estimation method and an urban growth simulation method for the City of Hillah. Population data were estimated for Hillah, using the Normalized Difference Built-up Index (NDBI) derived from Remote Sensing (RS) and …

Time Lags: Insights From The U.S. Long Term Ecological Research Network, Edward B. Rastetter, Mark D. Ohman, Katherine J. Elliott, J. S. Rehage, Victor H. Rivera-Monroy, R. E. Boucek, Edward Castañeda-Moya, Tess M. Danielson, Laura Gough, Peter M. Groffman, C. Rhett Jackson, Chelcy Ford Miniat, Gaius R. Shaver

Advanced Science Research Center

Ecosystems across the United States are changing in complex ways that are difficult to predict. Coordinated long-term research and analysis are required to assess how these changes will affect a diverse array of ecosystem services. This paper is part of a series that is a product of a synthesis effort of the U.S. National Science Foundation’s Long Term Ecological Research (LTER) network. This effort revealed that each LTER site had at least one compelling scientific case study about “what their site would look like” in 50 or 100 yr. As the site results were prepared, themes emerged, and the case …

Operationalizing Resilience: Co-Creating A Framework To Monitor Hard, Natural, And Nature-Based Shoreline Features In New York State, Katinka Wijsman, D. S. Novem Auyeung, Pippa Brashear, Brett F. Branco, Joseph H. Graziano, Kathryn Graziano, Peter M. Groffman, Helen Cheng, Dylan Corbett

Advanced Science Research Center

There is growing interest in the application of nature-based solutions to adapt to climate change and promote resilience, yet barriers exist to their implementation. These include a perceived lack of evidence of their functioning in comparison to conventional solutions and an inability for existing design, policy, and assessment processes to capture the multiple benefits of these solutions. Positing this as a challenge of operationalizing and measuring resilience, we argue that the concept of resilience needs to be given concrete meaning in applied management contexts. Starting with shoreline vulnerability as a policy problem and natural and nature-based shoreline features as a …

State Changes: Insights From The U.S. Long Term Ecological Research Network, Julie C. Zinnert, Jesse B. Nippert, Jennifer A. Rudgers, Steven C. Pennings, Grizelle González, Merryl Alber, Sara G. Baer, John M. Blair, Adrian Burd, Scott L. Collins, Christopher Craft, Daniela Di Iorio, Walter K. Dodds, Peter M. Groffman, Ellen Herbert, Christine Hladik, Fan Li, Marcy E. Litvak, Seth Newsome, John O’Donnell, William T. Pockman, John Schalles, Donald R. Young

Advanced Science Research Center

Understanding the complex and unpredictable ways ecosystems are changing and predicting the state of ecosystems and the services they will provide in the future requires coordinated, long-term research. This paper is a product of a U.S. National Science Foundation funded Long Term Ecological Research (LTER) network synthesis effort that addressed anticipated changes in future populations and communities. Each LTER site described what their site would look like in 50 or 100 yr based on long-term patterns and responses to global change drivers in each ecosystem. Common themes emerged and predictions were grouped into state change, connectivity, resilience, time lags, and …

Gis And Remote Sensing Groundwater Potentiality Investigation Of Gulu District, Uganda Using Synthetic Aperture Radar And Magnetic Geophysics, Rachel Ann Jones

Doctoral Dissertations

“Developing countries have few resources for ground-based hydrological investigations to determine optimal placement of boreholes for community water access. Remote sensing data are available at a variety of resolutions and sense different parameters, and are useful inputs for hydrologic models, but these data are rarely obtainable in developing countries with the parameters or resolutions necessary for hydrologic applications. This research seeks to use and improve existing remote sensing and GIS techniques to identify areas of optimal water supply in locations with limited geologic or hydrologic information, such as Gulu District, Uganda. Fusing different remotely sensed data sets can produce higher …

Sensing Population Distribution From Satellite Imagery Via Deep Learning:Model Selection, Neighboring Effects, And Systematic Biases, Xiao Huang, Di Zhu, Fan Zhang, Tao Liu, Xiao Li, Lei Zou

Geosciences Faculty Publications and Presentations

The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted. This article marks the first attempt to cross-compare performances of popular state-of-the-art deep learning models in estimating population distribution from remote sensing images, investigate the contribution of neighboring effect, and explore the potential systematic population estimation biases. We conduct an end-to-end training of four popular deep learning architectures, i.e., VGG, ResNet, Xception, and DenseNet, by establishing a mapping between Sentinel-2 image patches and …

Assessing Synthetic Aperture Radar (Sar)-Derived Temporal Patterns And Digital Terrain Data For Palustrine Wetland Mapping, Jaimee L. Pyron

Graduate Theses, Dissertations, and Problem Reports (ETD)

Palustrine wetland systems are important ecosystems and provide numerous ecosystems services to support society. Unfortunately, they remain under constant threat of devastation due to land use practices and global climate change, which underscores the need to identify, map, and monitor these landscape features. This study explores harmonic coefficients and seasonal median values derived from Sentinel-1 synthetic aperture radar (SAR) data, as well as digital elevation model (DEM)-derived terrain variables, to predict palustrine wetland locations in the Vermont counties of Bennington, Chittenden, and Essex. Support vector machine (SVM) and random forest (RF) machine learning models were used with various combinations of …

Deepmapper : Automatic Updating Crowdsourced Maps, Lasith Niroshan Hewa Manage, James Carswell

Other

To get accurate information returned from location-based services (e.g., LBS info on nearby restaurants, retail outlets, points-of-interest, etc.), the underlying map (spatial data) must be up-to-date. However, the built environment (e.g., roads, buildings, bike paths, etc.) can change quickly over time, either through planned developments or as the result of natural/manmade disasters. The problem is that keeping online crowdsourced maps like Open Street Map (OSM) updated is still very much a manual process. As such, it can take considerable time to sync the online maps used by LBS with up-to-date spatial data in "real-time".

Our case study considers the Grangegorman …

An Assessment Of The Hydrological Trends Using Synergistic Approaches Of Remote Sensing And Model Evaluations Over Global Arid And Semi-Arid Regions, Wenzhao Li, Hesham El-Askary, Rejoice Thomas, Surya Prakash Tiwari, Karuppasamy Manikandan, Thomas Piechota, Daniele Struppa

Mathematics, Physics, and Computer Science Faculty Articles and Research

Drylands cover about 40% of the world’s land area and support two billion people, most of them living in developing countries that are at risk due to land degradation. Over the last few decades, there has been warming, with an escalation of drought and rapid population growth. This will further intensify the risk of desertification, which will seriously affect the local ecological environment, food security and people’s lives. The goal of this research is to analyze the hydrological and land cover characteristics and variability over global arid and semi-arid regions over the last decade (2010–2019) using an integrative approach of …

Synergies Among Environmental Science Research And Monitoring Networks: A Research Agenda, J. A. Jones, Peter M. Groffman, J. Blair, F. W. Davis, H. Dugan, E. E. Euskirchen, S. D. Frey, T. K. Harms, E. Hinckley, M. Kosmala, S. Loberg, S. Malone, K. Novick, S. Record, A. V. Rocha, B. L. Ruddell, E. H. Stanley, C. Sturtevant, A. Thorpe, T. White, W. R. Wieder, L. Zhai, K. Zhu

Advanced Science Research Center

Many research and monitoring networks in recent decades have provided publicly available data documenting environmental and ecological change, but little is known about the status of efforts to synthesize this information across networks. We convened a working group to assess ongoing and potential cross-network synthesis research and outline opportunities and challenges for the future, focusing on the US-based research network (the US Long-Term Ecological Research network, LTER) and monitoring network (the National Ecological Observatory Network, NEON). LTER-NEON cross-network research synergies arise from the potentials for LTER measurements, experiments, models, and observational studies to provide context and mechanisms for interpreting NEON …

Monitoring Salt Diapir Related Land Deformation And Distribution: A Geophysical And Remote Sensing Approach Jazan Province, Saudi Arabia, Hannah G. Pankratz

Dissertations

Salt diapirs are rarely preserved on the surface and seldom considered as environmental hazards. The Jazan city diapir (JZD) is located in southwest Saudi Arabia along the Red Sea coastal plain and outcrops in the middle of a rapidly growing port city. The intrusion of the diapir (~ 2 km²) into the overburden sediments continues to cause uneven surfaces, compromises building foundations and infrastructure, caused dissolution sinkholes, and limits the expansion of the city along the coastline. This research aims to better understand the distribution and deformation associated with salt diapirs in arid environments.

Using integrated Interferometric Synthetic …

Atmospheric Turbulence Distortion In Video: Restoration Utilizing Sparse Analysis, Benjamin J. Sanda

Dissertations

The removal of atmospheric turbulence (AT) distortion in long range imaging is one of the most challenging areas of research in imaging processing with an immediate need for solutions in several applications such as in military and transportation systems. AT exacerbates distortion due to non-linear geometric blur and scintillations in long-distance images and videos, severely reducing image quality and information interpretation. AT negatively impacts both human and computer vision systems, compromising visibility essential for accurate object identification and tracking.

In this dissertation, a novel sparse analysis framework is developed to address efficient AT blur and scintillation removal in video. Operating …

Multidecadal Analysis Of Beach Loss At The Major Offshore Sea Turtle Nesting Islands In The Northern Arabian Gulf, Rommel H. Maneja, Jeffrey D. Miller, Wenzhao Li, Rejoice Thomas, Hesham El-Askary, Sachi Perera, Ace Vincent B. Flandez, Abdullajid U. Basali, Joselito Francis A. Alcaria, Jinoy Gopalan, Surya Prakash Tiwari, Mubarak Al-Jedani, Perdana K. Prihartato, Ronald A. Loughlan, Ali Qasem, Mohamed A. Qurban, Wail Falath, Daniele Struppa

Mathematics, Physics, and Computer Science Faculty Articles and Research

Undocumented historical losses of sea turtle nesting beaches worldwide could overestimate the successes of conservation measures and misrepresent the actual status of the sea turtle population. In addition, the suitability of many sea turtle nesting sites continues to decline even without in-depth scientific studies of the extent of losses and impacts to the population. In this study, multidecadal changes in the outlines and area of Jana and Karan islands, major sea turtle nesting sites in the Arabian Gulf, were compared using available Kodak aerographic images, USGS EROS Declassified satellite imagery, and ESRI satellite images. A decrease of 5.1% and 1.7% …

Landscape Fragmentation In Coffee Agroecological Subzones In Central Kenya: A Multiscale Remote Sensing Approach, Gladys Mosomtai, John Odindi, Elfatih M. Abdel-Rahman, Régis Babin, Pinard Fabrice, Onisimo Mutanga, Henri E.Z. Tonnang, Guillaume David, Tobias Landmann

All Peer-Reviewed Publications

Smallholder agroecological subzones (AEsZs) produce an array of crops occupying large areas throughout Africa but remain largely unmapped. We explored multisource satellite datasets to produce a seamless land-use and land-cover (LULC) and fragmentation dataset for upper midland (UM1 to UM4) AEsZs in central Kenya. Specifically, the utility of PlanetScope, Sentinel 2, and Landsat 8 images for mapping coffee-based landscape were tested using a random forest (RF) classifier. Vegetation indices, texture variables, and wavelength bands from all satellite data were used as inputs in generating four RF models. A LULC baseline map was produced that was further analyzed using FRAGSTAT to …

Phenology Of Short Vegetation Cycles In A Kenyan Rangeland From Planetscope And Sentinel-2, Yan Cheng, Anton Vrieling, Francesco Fava, Michele Meroni, Michael Marshall, Stella Gachoki

All Peer-Reviewed Publications

The short revisit times afforded by recently-deployed optical satellite sensors that acquire 3–30 m resolution imagery provide new opportunities to study seasonal vegetation dynamics. Previous studies demonstrated a successful retrieval of phenology with Sentinel-2 for relatively stable annual growing seasons. In semi-arid East Africa however, vegetation responds rapidly to a concentration of rainfall over short periods and consequently is subject to strong interannual variability. Obtaining a sufficient density of cloud-free acquisitions to accurately describe these short vegetation cycles is therefore challenging. The objective of this study is to evaluate if data from two satellite constellations, i.e., PlanetScope (3 m resolution) …

Spatiotemporal Variations Of City-Level Carbon Emissions In China During 2000–2017 Using Nighttime Light Data, Yu Sun, Sheng Zheng, Yuzhe Wu, Uwe Schlink, Ramesh P. Singh

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

China is one of the largest carbon emitting countries in the world. Numerous strategies have been considered by the Chinese government to mitigate carbon emissions in recent years. Accurate and timely estimation of spatiotemporal variations of city-level carbon emissions is of vital importance for planning of low-carbon strategies. For an assessment of the spatiotemporal variations of city-level carbon emissions in China during the periods 2000–2017, we used nighttime light data as a proxy from two sources: Defense Meteorological Satellite Program’s Operational Linescan System (DMSP-OLS) data and the Suomi National Polar-orbiting Partnership satellite’s Visible Infrared Imaging Radiometer Suite (NPP-VIIRS). The results …

The Quest For Greener Pastures: Evaluating The Livelihoods Impacts Of Providing Vegetation Condition Maps To Pastoralists In Eastern Africa, Elia Machado, Helene Purcell, Andrew M. Simons, Stephanie Swinehart

Publications and Research

The survival of millions of pastoral households in Eastern Africa has become increasingly at risk. Due to mounting socioeconomic and climatic stressors, pastoral households are faced with making migration decisions under increasing uncertainty about resource availability and limited coping strategies. We assess the potential of providing vegetation condition maps to support the migration decision of pastoralists in Ethiopia and Tanzania and the effect of map usage on their herd condition and size. The maps were generated from remotely sensed data using the Normalized Difference Vegetation Index (NDVI) as a proxy for vegetation condition and overlain with pastoralists’ preferred grazing areas. …

Long Term Air Quality Analysis In Reference To Thermal Power Plants Using Satellite Data In Singrauli Region, India, H. K. Romana, Ramesh P. Singh, D. P. Shukla

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

The exponentially growing population and related anthropogenic activities have led to modifications in local environment. The change in local environment, evolving pattern of land use, concentrations of greenhouse gases and aerosols alter the energy balance of our climate system. This alteration in climate is leading to pre-mature deaths worldwide. This study analyses the air quality of Singrauli region, Madhya Pradesh, India for the past 15 years. Otherwise known as Urjanchal “the energy capital” of India has been declared as critically polluted by CPCB. The study provides an updated list of thermal power plants in the study area and their emission …

Snow-Albedo Feedback In Northern Alaska: How Vegetation Influences Snowmelt, Lucas C. Reckhaus

Theses and Dissertations

This paper investigates how the snow-albedo feedback mechanism of the arctic is changing in response to rising climate temperatures. Specifically, the interplay of vegetation and snowmelt, and how these two variables can be correlated. This has the potential to refine climate modelling of the spring transition season. Research was conducted at the ecoregion scale in northern Alaska from 2000 to 2020. Each ecoregion is defined by distinct topographic and ecological conditions, allowing for meaningful contrast between the patterns of spring albedo transition across surface conditions and vegetation types. The five most northerly ecoregions of Alaska are chosen as they encompass …

Potential Of Resampled Multispectral Data For Detecting Desmodium-Brachiaria Intercropped With Maize In A 'Push-Pull' System, B. T. Mudereri, E. M. Abdel-Rahman, T. Dube, T. Landmann, S. Niassy, H. E.Z. Tonnang, Z. R. Khan

All Peer-Reviewed Publications

Poor crop yields remain one of the main causes of chronic food insecurity in Africa. This is largely caused by insect pests, weeds, unfavourable climatic conditions and degraded soils. Weed and pest control, based on the climate-adapted g'push-pull' system, has become an important target for sustainable intensification of food production adopted by many small-holder farmers. However, essential baseline information using remotely sensed data is missing, specifically for the g'push-pull' companion crops. In this study, we investigated the spectral uniqueness of two of the most commonly used g'companion' crops (i.e. greenleaf Desmodium (i Desmodium intortum/i) and Brachiaria (i Brachiaria/i cv Mulato) …

A Modeling Framework For Urban Growth Prediction Using Remote Sensing And Video Prediction Technologies: A Time-Dependent Convolutional Encoder-Decoder Architecture, Ahmed Hassan Jaad

Civil and Environmental Engineering Theses and Dissertations

Studying the growth pattern of cities/urban areas has received considerable attention during the past few decades. The goal is to identify directions and locations of potential growth, assess infrastructure and public service requirements, and ensure the integration of the new developments with the existing city structure. This dissertation presents a novel model for urban growth prediction using a novel machine learning model. The model treats successive historical satellite images of the urban area under consideration as a video for which future frames are predicted. A time-dependent convolutional encoder-decoder architecture is adopted. The model considers as an input a satellite image …

Wideband Satcom Model: Evaluation Of Numerical Accuracy And Efficiency, Andrew J. Knisely, Andrew J. Terzuoli Jr.

Faculty Publications

The spectral method is typically applied as a simple and efficient method to solve the parabolic wave equation in phase screen scintillation models. The critical factors that can greatly affect the spectral method accuracy is the uniformity and smoothness of the input function. This paper observes these effects on the accuracy of the finite difference and the spectral methods applied to a wideband SATCOM signal propagation model simulated in the ultra-high frequency (UHF) band. The finite difference method uses local pointwise approximations to calculate a derivative. The spectral method uses global trigonometric interpolants that achieve remarkable accuracy for continuously differentiable …

Predicting And Mapping Plethodontid Salamander Abundance Using Lidar-Derived Terrain And Vegetation Characteristics, Marco Antonio Contreras, Wesley A. Staats, Steve J. Price

Forestry and Natural Resources Faculty Publications

Aim of the study: Use LiDAR-derived vegetation and terrain characteristics to develop abundance and occupancy predictions for two terrestrial salamander species, Plethodon glutinosus and P. kentucki, and map abundance to identify vegetation and terrain characteristics affecting their distribution.

Area of study: The 1,550-ha Clemons Fork watershed, part of the University of Kentucky’s Robinson Forest in southeastern Kentucky, USA.

Materials and methods: We quantified the abundance of salamanders using 45 field transects, which were visited three times, placed across varying soil moisture and canopy cover conditions. We created several LiDAR-derived vegetation and terrain layers and used these …

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 …