Digital Commons Network^™

Using Machine Learning Classification And Esa Sentinel 2 Multispectral Imager Data To Delineate Marsh Vegetation And Measure Ecotone Movement In Coastal Georgia, Thomas A. Pudil

Electronic Theses and Dissertations

Tidal marshes are unique communities that are subjected to environmental stressors including sea level rise, salinity change, and drought, resulting in constant change. It is important to monitor these changing areas because of the ecosystem services they provide to us, such as protection from storms and carbon sequestration. The proposed work for this thesis project is focused on the study of tidal marshes and the dynamics between the vegetation species within them. The aim of this project is to use geospatial technology and analyses, along with machine learning classification methods, to monitor change in these valuable ecosystems. The Georgia coast …

Drone Imagery Protocols To Map Vegetation Are Transferable Between Dryland Sites Across An Elevational Gradient, Anna Roser, Josh Enterkine, Juan M. Requena-Mullor, Nancy F. Glenn, Alex R. Boehm, Marie-Anne De Graaff, Patrick E. Clark, Fred Pierson, T. Trevor Caughlin

Biology Faculty Publications and Presentations

The structure and composition of plant communities in drylands are highly variable across scales, from microsites to landscapes. Fine spatial resolution field surveys of dryland plants are essential to unravel the impact of climate change; however, traditional field data collection is challenging considering sampling efforts and costs. Unoccupied aerial systems (UAS) can alleviate this challenge by providing standardized measurements of plant community attributes with high resolution. However, given widespread heterogeneity in plant communities in drylands, and especially across environmental gradients, the transferability of UAS imagery protocols is unclear. Plant functional types (PFTs) are a classification scheme that aggregates the diversity …

Studies Of Roseau Cane Dieback In The Lower Mississippi River Delta Based On Remote Sensing Data Including Landsat, Worldview, And Drone, Nan Shang

LSU Doctoral Dissertations

This research focused on the Roseau cane (Phragmites australis) dieback assessment in the lower MRD of Louisiana and introduced a comprehensive and systematic multi-source remote sensing method for assessing wetland and Roseau cane dieback and habitat dynamics analysis from three scale levels from large-scale to small scale.

Large-scale historical vegetation/land change analyses were conducted in the lower MRD based on Landsat in the past two decades (2001 - 2021). A strong increasing trend of vegetation was found since 2005. Around 51 km² ofdieback area was detected which accounts for 11% of the overall vegetation coverage. This research …

Next-Generation Technologies Unlock New Possibilities To Track Rangeland Productivity And Quantify Multi-Scale Conservation Outcomes, Caleb P. Roberts, David E. Naugle, Brady W. Allred, Victoria M. Donovan, Dillon T. Fogarty, Matthew O. Jones, Jeremy D. Maestas, Andrew C. Olsen, Dirac L. Twidwell Jr

Department of Agronomy and Horticulture: Faculty Publications

Historically, relying on plot-level inventories impeded our ability to quantify large-scale change in plant biomass, a key indicator of conservation practice outcomes in rangeland systems. Recent technological advances enable assessment at scales appropriate to inform management by providing spatially comprehensive estimates of productivity that are partitioned by plant functional group across all contiguous US rangelands. We partnered with the Sage Grouse and Lesser Prairie-Chicken Initiatives and the Nebraska Natural Legacy Project to demonstrate the ability of these new datasets to quantify multi-scale changes and heterogeneity in plant biomass following mechanical tree removal, prescribed fire, and prescribed grazing. In Oregon’s sagebrush …

Rapid Quantification Of Biofouling With An Inexpensive, Underwater Camera And Image Analysis, Matthew R. First, Scott C. Riley, Kazi Aminul Islam, Victoria Hill, Jiang Li, Richard C. Zimmerman, Lisa A. Drake

Electrical & Computer Engineering Faculty Publications

To reduce the transport of potentially invasive species on ships' submerged surfaces, rapid-and accurate-estimates of biofouling are needed so shipowners and regulators can effectively assess and manage biofouling. This pilot study developed a model approach for that task. First, photographic images were collected in situ with a submersible, inexpensive pocket camera. These images were used to develop image processing algorithms and train machine learning models to classify images containing natural assemblages of fouling organisms. All of the algorithms and models were implemented in a widely available software package (MATLAB^©). Initially, an unsupervised clustering model was used, and three …

An Evaluation Of Unmanned Aerial Systems And Structure-From-Motion For Fluvial Large Wood Sensing And Risk Assessment, Daniel Gerke

Masters Theses

This research aims to show Unmanned Aerial System (UAS) and Structure-from-Motion (SfM) technology can, in combination, improve on traditional large wood (LW) monitoring techniques. More temporally and economically efficient data collected at a finer spatial resolution and greater spatial extent will increase the effectiveness of management plans and risk assessment for LW by providing decision-makers with a complete picture of the river.

Contemporary practices are too inefficient in time and labor for large-scale monitoring of fluvial LW with anything more than the most general management or risk assessment in mind. The paradigm of river research, the river continuum concept (RCC), …

Characterizing Dryland Ecosystems Using Remote Sensing And Dynamic Global Vegetation Modeling, Abdolhamid Dashtiahangar

Boise State University Theses and Dissertations

Drylands include all terrestrial regions where the production of crops, forage, wood and other ecosystem services are limited by water. These ecosystems cover approximately 40% of the earth terrestrial surface and accommodate more than 2 billion people (Millennium Ecosystem Assessment, 2005). Moreover, the interannual variability of the global carbon budget is strongly regulated by vegetation dynamics in drylands. Understanding the dynamics of such ecosystems is significant for assessing the potential for and impacts of natural or anthropogenic disturbances and mitigation planning, and a necessary step toward enhancing the economic and social well-being of dryland communities in a sustainable manner (Global …

An Unsupervised Machine-Learning Framework For Behavioral Classification From Animal-Borne Accelerometers, Jane Elizabeth Dentinger

Theses and Dissertations

Studies of animal spatial distributions typically use prior knowledge of animal habitat requirements and behavioral ecology to deduce the most likely explanations of observed habitat use. Animal-borne accelerometers can be used to distinguish behaviors which allows us to incorporate in situ behavior into our understanding of spatial distributions. Past research has focused on using supervised machine-learning, which requires a priori specification of behavior to identify signals whereas unsupervised approaches allow the model to identify as many signal types as permitted by the data. The following framework couples direct observation to behavioral clusters identified from unsupervised machine learning on a large …

Marine Reserves Shape Seascapes On Scales Visible From Space, Elizabeth M. P. Madin, Alastair R. Harborne, Aaron M. T. Harmer, Osmar J. Luiz, Trisha Brooke Atwood, Brian J. Sullivan, Joshua S. Madin

Watershed Sciences Faculty Publications

Marine reserves can effectively restore harvested populations, and ‘mega-reserves’ increasingly protect large tracts of ocean. However, no method exists of monitoring ecological responses at this large scale. Herbivory is a key mechanism structuring ecosystems, and this consumer–resource interaction's strength on coral reefs can indicate ecosystem health. We screened 1372, and measured features of 214, reefs throughout Australia's Great Barrier Reef using high-resolution satellite imagery, combined with remote underwater videography and assays on a subset, to quantify the prevalence, size and potential causes of ‘grazing halos’. Halos are known to be seascape-scale footprints of herbivory and other ecological interactions. Here we …

The Effects Of Deforestation On Carbon Storage In Khabarovsk Krai, Russia, Rowan E. Cole

Masters Theses

With over one-fifth of the planet’s forested area, Russia has become a major source of round wood and wood products. In 2003, the Russian government established an energy policy aimed at reducing the negative impacts of industry on the environment and improving the nation’s environments as a whole. This study analyzes deforestation and logging activities in the forests along the Amur River in Khabarovsk Krai in the Russian Far East to determine the effectiveness of Russian government policy in achieving the goals put forward in the 2003 energy policy. Changes in land-use and land-cover will be assessed using 500-meter resolution …

Machine Learning To Classify Animal Species In Camera Trap Images: Applications In Ecology, Michael A. Tabak, Mohammad S. Norouzzadeh, David W. Wolfson, Steven J. Sweeney, Kurt C. Vercauteren, Nathan P. Snow, Joseph M. Halseth, Paul A. Di Salvo, Jesse S. Lewis, Michael D. White, Ben Teton, James C. Beasley, Peter E. Schlichting, Raoul K. Boughton, Bethany Wight, Eric S. Newkirk, Jacob S. Ivan, Eric A. Odell, Ryan K. Brook, Paul M. Lukacs, Anna K. Moeller, Elizabeth G. Mandeville, Jeff Clune, Ryan S. Miller

USDA Wildlife Services: Staff Publications

1. Motion-activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and are amongst the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analysed, typically by visually observing each image, in order to extract data that can be used in ecological analyses.

2. We trained machine learning models using convolutional neural networks with the ResNet-18 architecture and 3,367,383 images to automatically classify wildlife species from camera trap images obtained from five states across the United States. We tested our model on an …

Developing A Coastal Gis Model Of Sri Lanka To Pinpoint Areas At Risk Of Tsunamis, John E. Dellysse, Buddhika D. Madurapperuma

IdeaFest: Interdisciplinary Journal of Creative Works and Research from Cal Poly Humboldt

No abstract provided.

A Comparative Study Of Raster And Vector Based Approaches In Vegetation Mapping On Five Islands Off The Coast Of Port Kembla., P B. Barlow

Science, Medicine & Health - Honours Theses

Remote sensing has facilitated extraordinary advances in the modelling, mapping and understanding of vegetation in remote Island ecosystems. With the unforgiving responses of Island ecosystems to anthropogenic influences, it is paramount that managerial strategies are put into place and vegetation conditions are quantified. The Five Islands group has an extensive history of anthropogenic alteration, resulting in widespread change in vegetation dynamics. In recent years introduced vegetation has overpopulated Big Island – The largest of the Island Nature Reserve – and made it inhabitable for protected burrowing and nesting seabird populations. As a result NSW National Parks and Wildlife Service (NPWS) …

Four Years Of Unmanned Aerial System Imagery Reveals Vegetation Change In A Sub-Arctic Mire Due To Permafrost Thaw, Jessica Delgreco

Master's Theses and Capstones

Warming trends in sub-arctic regions have resulted in thawing of permafrost which in turn induces change in vegetation across peatlands both in areal extent and composition. Collapse of palsas (i.e. permafrost plateaus) has also been correlated with increases in methane (CH4) emission to the atmosphere. Vegetation change provides new microenvironments that promote CH4 production and emission, specifically through plant interactions and structure. By quantifying the changes in vegetation at the landscape scale, we will be able to scale the impact of thaw on CH4 emissions in these complex climate-sensitive northern ecosystems. We combine field-based measurements of vegetation composition and Unmanned …

No Consistent Evidence For Advancing Or Delaying Trends In Spring Phenology On The Tibetan Plateau, Xufeng Wang, Jingfeng Xiao, Xin Li, Guodong Cheng, Mingguo Ma, Tao Che, Shaoying Wang, Jinkui Wu

Faculty Publications

Vegetation phenology is a sensitive indicator of climate change and has significant effects on the exchange of carbon, water, and energy between the terrestrial biosphere and the atmosphere. The Tibetan Plateau, the Earth's “third pole,” is a unique region for studying the long‐term trends in vegetation phenology in response to climate change because of the sensitivity of its alpine ecosystems to climate and its low‐level human disturbance. There has been a debate whether the trends in spring phenology over the Tibetan Plateau have been continuously advancing over the last two to three decades. In this study, we examine the trends …

Environmental Factors Correlated With Culturable Enterococci Concentrations In Tropical Recreational Waters: A Case Study In Escambron Beach, San Juan, Puerto Rico, A. E. Laureano-Rosario, E. M. Symonds, Digna Rueda-Roa, Daniel B. Otis, Frank E. Muller-Karger

Marine Science Faculty Publications

Enterococci concentration variability at Escambron Beach, San Juan, Puerto Rico, was examined in the context of environmental conditions observed during 2005–2015. Satellite-derived sea surface temperature (SST), turbidity, direct normal irradiance, and dew point were combined with local precipitation, winds, and mean sea level (MSL) observations in a stepwise multiple regression analyses (Akaike Information Criteria model selection). Precipitation, MSL, irradiance, SST, and turbidity explained 20% of the variation in observed enterococci concentrations based upon these analyses. Changes in these parameters preceded increases in enterococci concentrations by 24 h up to 11 days, particularly during positive anomalies of turbidity, SST, and 480–960 …

Remote Estimation Of Biomass Of Ulva Prolifera Macroalgae In The Yellow Sea, Lianbo Hu, Chuanmin Hu, He Ming-Xia

Marine Science Faculty Publications

Since 2008, macroalgal blooms of Ulva prolifera (also called green tides) occurred every summer in the Yellow Sea (YS), causing environmental and economic problems. A number of studies have used satellite observations to estimate the severity of the blooms through estimating the bloom size and duration. However, a critical bloom parameter, namely biomass, has never been objectively determined due to lack of measurements. In this study, laboratory experiments were conducted to measure U. prolifera biomass (wet weight) per unit area and the corresponding spectral reflectance, through which a robust relationship has been established to link biomass per area to …

Floating Algae Blooms In The East China Sea, Lin Qi, Chuanmin Hu, Mengqiu Wang, Shaoling Shang, Cara Wilson

Marine Science Faculty Publications

A floating algae bloom in the East China Sea was observed in Moderate Resolution Imaging Spectroradiometer (MODIS) imagery in May 2017. Using satellite imagery from MODIS, Visible Infrared Imaging Radiometer Suite, Geostationary Ocean Color Imager, and Ocean Land Imager, and combined with numerical particle tracing experiments and laboratory experiments, we examined the history of this bloom as well as similar blooms in previous years and attempted to trace the bloom source and identify the algae type. Results suggest that one bloom origin is offshore Zhejiang coast where algae slicks have appeared in satellite imagery almost every February–March since 2012. Following …

The Utility Of Fine-Scale Remote Sensing Data For Modeling Habitat Characteristics And Breeding Bird Species Distributions In An Appalachian Mature Deciduous Forest., James Sheehan

Graduate Theses, Dissertations, and Problem Reports

In this study, I tested the potential for remote sensing data with a high spatial resolution to model breeding forest bird species and their habitat at a fine spatial scale. The research took place on ridgetops in a large, relatively contiguous Appalachian mature deciduous forest in northwestern WV, USA. The remote sensing data sources were a leaf-on QuickBird satellite image (0.6-m panchromatic and 2.4-m multispectral) and a 3-m digital elevation model (DEM). For the first part of the study, I extracted spectral and textural measures from the satellite image and terrain information from the DEM. I then used these data …

Using Thermal Infrared Imagery To Estimate Soil Hydraulic Parameters: A Novel Approach, Matthew B. Thomas

Undergraduate Theses, Professional Papers, and Capstone Artifacts

In this study, skin temperature measured with a thermal infrared (TIR) camera was used to estimate soil hydraulic parameters. These physical properties that control how soils transport and retain water are notoriously difficult to measure in the field due to spatial variability. Laboratory experiments were set up to record surface skin temperature response in a clean soil column using a TIR camera after an artificial wetting event. An array of thermocouples, a net radiometer, heat flux sensor and weather station were used to constrain the TIR data and the energy budget during the experiment. The soil column surface was then …

Hybrid Taguchi-Objective Function Optimization Approach For Automatic Cave Bird Detection From Terrestrial Laser Scanning Intensity Image, Mohammed O. Idrees, Biswajeet Pradhan

International Journal of Speleology

This paper proposes an optimized Taguchi-objective function segmentation-based image analysis to detect bird nests in a cave from high resolution terrestrial laser scanning intensity images. First, the Taguchi orthogonal array was used to design 25 experiments with three segmentation parameters: scale, shape, and compactness, each having five variable factor levels. Then, a plateau objective function was computed for each experiment using their respective level combinations. A merger of the factor level combination in the orthogonal array and the computed plateau objective function values was used to generate main effects and interaction plots for signal-to-noise ratios, which provided a measure of …

Evaluating Plant Community Response To Sea Level Rise And Anthropogenic Drying: Can Life Stage And Competitive Ability Be Used As Indicators In Guiding Conservation Actions?, Kristie Susan Wendelberger

FIU Electronic Theses and Dissertations

Increasing sea levels and anthropogenic disturbances have caused the world’s coastal vegetation to decline 25-50% in the past 50 years. Future sea level rise (SLR) rates are expected to increase, further threatening coastal habitats. In combination with SLR, the Everglades ecosystem has undergone large-scale drainage and restoration changing Florida’s coastal vegetation. Everglades National Park (ENP) has 21 coastal plant species threatened by SLR. My dissertation focuses on three aspects of coastal plant community change related to SLR and dehydration. 1) I assessed the extent and direction coastal communities—three harboring rare plant species—shifted from 1978 to 2011. I created a classified …

Quantifying Gully Erosion In West Tennessee Using High Resolution Lidar Data, John James Mcnelis

Masters Theses

This research demonstrates the use of Light Detection and Ranging (LIDAR) for detailed measurement of volume change and erosional and depositional processes within a small gully and assessing the impact of digital elevation model (DEM) resolution on these measurements. The study site is an active gully in Meeman-Shelby Forest State Park in Tennessee, USA. DEMs were derived from an airborne LIDAR survey and multiple terrestrial LIDAR scans. DEM differences were used to quantify gross volumes of erosion and deposition within the gully over a three year period and a 49 day period. Analysis of the airborne LIDAR point cloud indicated …

Historical Riparian Vegetation Changes In Eastern Nsw, Angus Skorulis

Science, Medicine & Health - Honours Theses

Changes in the amount of riparian vegetation can vary significantly over large spatial extents, and this variation is influenced by an array of factors. Riparian vegetation is an important component of riverine ecosystems and acts as a filter for terrestrial runoff, a control on bank stability and a key habitat area. Following European settlement in New South Wales (NSW) Australia in the late 18^th century, extensive areas of floodplain and riparian vegetation were cleared to allow farming of the rich alluvial soil with close proximity to a water supply. As a result of broad scale vegetation clearing, the extent …

Evaluation Of Soil As A Risk Indicator For Human Leptospirosis In Coastal, Rural Ecuador, Chad Allen Weddell

USF Tampa Graduate Theses and Dissertations

Leptospirosis, a zoonotic disease caused by pathogenic spirochete bacteria (family Leptospiraceae, genus Leptospira), is endemic in developing tropical regions of the world. It occurs in epidemics and is endemic in Ecuador where environmental conditions are ideal for maintenance. The role of soil as a long term reservoir has been previously been documented. Geographic Information System (GIS) and Remote Sensing (RS) technology was used in our study to further explore the role of soil as an environmental reservoir and its potential use as a static risk indicator for disease. Red, Green, Blue (RGB) spectral band data from known leptospire …

Remote Sensing Estimates Of Stand-Replacement Fires In Russia, 2002–2011, Alexander Krylov, Jessica L. Mccarty, Peter Potapov, Tatiana Loboda, Alexandra Tyukavina, Svetlana Turubanova, Matthew Hansen

Michigan Tech Research Institute Publications

The presented study quantifies the proportion of stand-replacement fires in Russian forests through the integrated analysis of Landsat and Moderate Resolution Imaging Spectroradiometer (MODIS) data products. We employed 30 m Landsat Enhanced Thematic Mapper Plus derived tree canopy cover and decadal (2001–2012) forest cover loss (Hansen et al 2013 High-resolution global maps of 21st-century forest cover change Science 342 850–53) to identify forest extent and disturbance. These data were overlaid with 1 km MODIS active fire (earthdata.nasa.gov/data/near-real-time-data/firms) and 500 m regional burned area data (Loboda et al 2007 Regionally adaptable dNBR-based algorithm for burned area mapping from …

Quantitative Analysis Of Woodpecker Habitat Using High-Resolution Airborne Lidar Estimates Of Forest Structure And Composition, James E. Garabedian, Robert Mcgaughey, Stephen E. Reutebuch, Bernard R. Parresol, John C. Kilgo, Christopher E. Moorman, M. Nils Peterson

USDA Forest Service / UNL Faculty Publications

Light detection and ranging (LiDAR) technology has the potential to radically alter theway researchers and managers collect data onwildlife–habitat relationships. To date, the technology has fostered several novel approaches to characterizing avian habitat, but has been limited by the lack of detailed LiDAR-habitat attributes relevant to species across a continuum of spatial grain sizes and habitat requirements. We demonstrate a novel three-step approach for using LiDAR data to evaluate habitat based on multiple habitat attributes and accounting for their influence at multiple grain sizes using federally endangered red-cockaded woodpecker (RCW; Picoides borealis) foraging habitat data fromthe Savannah River Site (SRS) …

Assessing The Performance Of A Northern Gulf Of Mexico Tidal Model Using Satellite Imagery, Stephen C. Medeiros, Scott C. Hagen, Naira Chaouch, Jesse Feyen, Marouane Temimi, John F. Weishampel, Yuji Funakoshi, Reza Khanbilvardi

Publications and Research

Tidal harmonic analysis simulations along with simulations spanning four specific historical time periods in 2003 and 2004 were conducted to test the performance of a northern Gulf of Mexico tidal model. A recently developed method for detecting inundated areas based on integrated remotely sensed data (i.e., Radarsat-1, aerial imagery, LiDAR, Landsat 7 ETM+) was applied to assess the performance of the tidal model. The analysis demonstrates the applicability of the method and its agreement with traditional performance assessment techniques such as harmonic resynthesis and water level time series analysis. Based on the flooded/non-flooded coastal areas estimated by the integrated remotely …

Ground-Truthing Maxent In East Texas Rivers, David F. Ford

Biology Theses

Unionid mussels are a guild of freshwater, sedentary filter-feeders, which play a critical role in freshwater systems. Mussels are currently experiencing a global decline in both species richness and abundance, due to invasive species, human alteration of water systems, and climate change. In North America, which is considered to have the highest global diversity of bivalve species, native mussels are currently declining rapidly with at least 37 species considered to already be extinct. If extant mussel species are to be preserved, then it is vital that conservation efforts be prioritized towards areas in which they are likely to be found. …

Low Mortality In Tall Tropical Trees, R. Q. Thomas, J. R. Kellner, D. B. Clark, D. R. Peart

Dartmouth Scholarship

The dynamics of the tallest trees in tropical forests are of special interest due to their carbon content, canopy dominance, and the large canopy gaps created when they die. Known ecological mechanisms that may influence tall tree survival lead to conflicting predictions. Hydraulic stress and exposure to high winds and desiccation should increase death rates, yet the tallest trees have the greatest access to light and escape damage caused by falling boles and branches. The uncertainty in tall tree mortality rates has been difficult to address due to their low density, which makes mortality rates challenging to estimate accurately. Here, …