Spatial Science Commons^™

Road Extraction On Remote Sensing Imagery: Historical Mapping Of The Brazilian Amazon, Jonas Paiva Botelho Jr

Graduate Theses/Dissertations

This work proposes an artificial intelligence model based on U-Net architecture to map road networks in the Brazilian Amazon. Over the years, the Amazon region has been heavily exploited, leading to increased deforestation rates, contributing to CO2 emissions, amplifying global warming, and causing a disturbance in local fauna and flora. The expansion into the forest by illegal miners, loggers, and land grabbers can be tracked down by the construction of roads, which we can refer to as the arteries of deforestation. Previous works on the matter proposed algorithms that use high-resolution imagery to map roads precisely. However, this work approach …

Industrial Hemp Production And Potential Risks In Kentucky, Hoyeon Jeong

Theses and Dissertations--Agricultural Economics

Since the Agricultural Improvement Act of 2014 and 2018 legalized Industrial Hemp (Cannabis Sativa. L), interest in grain, fiber, and floral hemp production has seen growing pains. As an emerging crop, there is a research gap in the impact of weather and agronomic conditions on hemp production including THC (Delta 9 Tetrahydrocannabinol) and pollen drift as risks in hemp cultivation. The first essay aims to measure the impact of weather and agronomic factors on hemp grain, fiber, and floral yields in Kentucky using a yield-weather model with information on field locations. The results show that heat conditions during the growing …

Essays On Public And Nonprofit Financial Dynamics, Yunjun Kim

Theses and Dissertations--Public Policy and Administration

This dissertation consists of three essays that explore different dimensions of financial dynamics in the public and nonprofit sectors. Each chapter examines how the fiscal behavior of neighboring jurisdictions, policy interventions, and financial practices influence fiscal decision-making and financial performance within these entities.

In the first essay, I investigate yardstick competition in local government spending in South Korea by leveraging the exogenous variation introduced by by-elections. This approach allows me to estimate the influence of neighboring jurisdictions on local expenditures. Contrary to previous empirical studies from other countries, my findings reveal no significant interdependence in spending among South Korean municipalities, …

Aboveground Biomass Density Estimation Using Deep Learning: Insight From Neon Ground-Truth Data And Simulated Gedi Waveform, Ashish Mahaur

Dissertations, Master's Theses and Master's Reports

Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth's carbon cycle and informing climate strategies. NASA's GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models.

Mapping Accessibility To Emergency Care Using Public Transportation, Bach Tran

Honors Undergraduate Theses

Intro: Public transit offers various advantages for both communities and individuals in terms of mobility and has the potential to serve as a practical alternative to private motorized transportation. Timely and convenient public transit becomes a lifeline for people who cannot access other types of transportation, especially when it comes to emergency care. Method: We built a private network analysis within ArcGIS Pro using coordinate data from hospitals and stand-alone emergency rooms as designated by the North American Industrial Classification System (NAICS) and public transit data from Orlando, FL. Establishing the accessible time as 30 minutes, we computed and visualized …

A Tale Of Two Working Landscapes, Sage C. Sutcliffe

Graduate Student Theses, Dissertations, & Professional Papers

No abstract provided.

Investigating Flash Flood Occurrence Using Negative Binomial Models In Maryland, United States Of America, Zainab O. Akinsemoyin

College of Graduate Studies: Theses & Dissertations

Globally, as extreme weather patterns intensify, flash floods have emerged as one of the most destructive and immediate environmental threats. In Maryland, flash floods are particularly concerning due to its diverse topography and increasing urban development, which exacerbates runoff and overwhelms drainage systems. The state has experienced significant flash flood events, highlighting the need for effective models to manage risks and inform mitigation strategies. While regression models such as the Negative Binomial (NB) and Zero-Inflated Negative Binomial (ZINB) are commonly used for count data analysis, their application to flash flood modeling in the USA, including regions like Maryland, remains limited …

Assessment Of Spatial Distribution Patterns And Infestation Risk Over Time Of Spotted Lanterfly (Lycorma Delicatula) In New York State, Alanna Richman

Electronic Theses & Dissertations (2024 - present)

Spotted Lanternfly (Lycorma delicatula) is an invasive treehopper native to Asia. It was first introduced to Pennsylvania in 2014, and as of 2020 it has expanded to New York state. Their preferred host tree is the invasive tree of heaven (Ailanthus altissima), but they will feed on over 173 different plants worldwide. Preferred host species in New York state include agricultural vegetation such as grape vines and fruit trees. Positive Spotted Lanternfly site data collected by the New York Department of Agriculture and Markets and iMapInvasives were analyzed using ArcGIS Pro to assess spatial distribution patterns. …

Age, Size, And Composition Of Selected Old-Growth Shortleaf Pine Stands In The Upper Buffalo River, Arkansas, Willa Avery Thomason

Graduate Theses and Dissertations

Shortleaf pine (Pinus echinata) approaches the westernmost limits of its range in the Arkansas Ozarks. Despite heavy logging of shortleaf pine throughout its range during the 19th and 20th centuries, the species was not easily accessible for harvest and transportation in the most rugged areas of the Boston Mountains and, as a result, there are a few extant stands of old-growth shortleaf pine in the region. The shortleaf pine stands in the interior Boston Mountains are unusual in that they exist primarily above bluff lines at topographic breaks in the hardwood canopy and are not disturbed by fire as frequently …

Modeling The Peak Ground Acceleration And Assessing The Economic Loss And Casualty Due To Potential Earthquakes Of Various Magnitudes In The New Madrid Seismic Zone, Mahmud Afroz

Graduate Theses and Dissertations

The New Madrid Seismic Zone (NMSZ) is one of the active tectonic zones capable of producing big earthquakes in the southcentral USA. The objective of this study was to assess the economic losses and casualties that might be caused by various magnitudes of seismic events in the NMSZ. The manifestation is the estimation for each magnitude which is using the Peak Ground Acceleration (PGA) that might occur during an earthquake. It is calculated using an attenuation function that correlates the intensity of local ground movement, the earthquake magnitude, and the distance from its epicenter. The assessment of casualties was conducted …

Airbnb Valuation: A Machine Learning Approach, Katherine Wyatt

Graduate Theses and Dissertations

This thesis uses a geospatially-enhanced, machine learning approach to investigate variations in rental success on the peer-to-peer property sharing website Airbnb.com. Geographic factors, listing attributes and amenities, customer response metrics, and host attributes are included in decision tree modeling to predict the short-term probability of receiving a review. The most important variables in increasing model accuracy are assessed and variations in the importance of these variables investigated using Shapley values.

Development Of A Historic Digital Elevation Model (Hdem) From Archival Aerial Imagery Over The Black Mountain Alluvial Fan, Canada, Emma Menio

Graduate Theses and Dissertations

In a rapidly changing Arctic, reconstructing landscapes pre-warming is essential to understanding impacts due to climate-inducted geomorphic change. High-latitude elevation datasets extend temporally back to the 2000s, while region-wide warming became measurable in the 1980s. Historic aerial imagery archives provide datasets of high-resolution imagery from the mid- to late- 1900s with stereo-capability that can be harnessed to create historic digital elevation models, or hDEMs. A major issue with reconstructing a surface from the past is finding a way to constrain it in space, given a lack of ground control from that era, especially at high latitudes. The main purpose of …

Spatial Associations Of Liver Disease Rates With Socioeconomic And Health Risk Factors In Georgia, Nguyet Le

Symposium of Student Scholars

According to the CDC Cancer Statistics Report in 2020, Liver and Intrahepatic Bile Duct is the 6th leading cancer in both USA and the State of Georgia ranked by Rates of Cancer Death. Aflatoxin-containing foods, alcohol consumption, smoking, overeating, and other risky behaviors are among the factors linked to liver diseases. They have also been related to the socioeconomic status (SES) of individuals. The behaviors and SES of individuals are affected by the socioeconomic characteristics of the communities where they live. However, the relationships between the rates of liver diseases and community-level socioeconomic factors are not well studied. The objective …

Urban Flood And Its Correlation With Built-Up Area In Semarang, Indonesia, Risty Khoirunisa, Bambang Darmo Yuwono

Smart City

The expansion of urban areas is closely related to environmental problems such as changes in land use, flooding, and land subsidence. Semarang is a city with reasonably rapid development and a high land change experiencing floods and land subsidence. This paper will discuss land transformation caused by urban growth and its implications. It uses a combination of geospatial techniques and cloud computing Google Earth Engine (GEE) to carry out mapping over a large area without being constrained by computer capabilities. This study found that the built-up area in 2010 occupied 36.27% of the city, and it went up to 59.79% …

Understanding Tourism Dynamics Using Gis And Forecasting Model In Banswara District, Rajasthan, India, Viranch N. Dave, Mudit D. Mankad, Ami U. Rawal

Journal of Tourism Insights

Understanding the tourism dynamics of an area involves a rigorous literature review, interviewing the local people and experts, and visiting the sites. This also involves getting acquainted with the transport network of the area to know about the accessibility to the tourism destination, which ultimately helps in preparing a suitable plan for tourism development by creating tourist circuits. Forecasting tourism demand with the help of past data helps put a better picture in front of planners and administration so they can plan more efficiently. Thus, a proper understanding of tourism dynamics requires a holistic vision. The present study tried to …

An Agent-Based Modeling Approach To Spatial Accessibility, Alexander C. Michels, Shaowen Wang

I-GUIDE Forum

Place-based spatial accessibility represents the ability of populations within geographic units to access goods and services, and thus is an important indicator for sustainable development. Existing spatial accessibility models treat population as simply demand, calculating statistics or optimizing average cost for the population within each geographic unit, rather than modeling individual decisions. This paper proposes AgentAccess, a general-purpose Agent-Based Model (ABM) for spatial accessibility analysis. An ABM framework brings us closer to reality by simulating individual and imperfect decision-making. We introduce the model and compare its results against existing spatial accessibility models using a case study of hospital beds in …

Reducing Uncertainty In Sea-Level Rise Prediction: A Spatial-Variability-Aware Approach, Subhankar Ghosh, Shuai An, Arun Sharma, Jayant Gupta, Shashi Shekhar, Aneesh Subramanian

I-GUIDE Forum

Given multi-model ensemble climate projections, the goal is to accurately and reliably predict future sea-level rise while lowering the uncertainty. This problem is important because sea-level rise affects millions of people in coastal communities and beyond due to climate change's impacts on polar ice sheets and the ocean. This problem is challenging due to spatial variability and unknowns such as possible tipping points (e.g., collapse of Greenland or West Antarctic ice-shelf), climate feedback loops (e.g., clouds, permafrost thawing), future policy decisions, and human actions. Most existing climate modeling approaches use the same set of weights globally, during either regression or …

Analysis Of Normalized Difference Vegetation Index Change Of The West Bank, Palestine, Using Multitemporal Satellite Remote Sensing Data, Ahmed Ghodieh

An-Najah University Journal for Research - B (Humanities)

The West Bank is characterized by the diversity of its climate despite its small area. It includes four climatic regions:- a humid, semi-humid, arid, and semi-arid climate. This in turn affected the geographical distribution of vegetation cover seasonally and over the years. This study investigated changes in the West Bank, Palestine vegetation cover using multitemporal Landsat data. Four images were selected for this purpose – two corresponding to 2001 and the other two corresponding to 2021. Seasonal change of the Normalized Difference Vegetation Index (NDVI) was investigated for the acquired images. ArcGIS 10.8 software was used for image processing and …

A Mixed Methods Approach To Understanding The Links Between Mining, Climate Change And Selected Health Outcomes In India, Mary J. Cheruvillil

Dissertations and Theses

Despite ample evidence of the significant role that mining activities play in determining health outcomes, in India there is a dearth of comprehensive health studies that draw linkages between mining and health. The purpose of the following study is to investigate the impact of mining activities on population health in India using three different methods: ecological multivariable regression, exploratory spatial data analysis (ESDA) and content analysis of government documents using a phenomenological approach. The first aim uses the ecological multivariable regression to examine associations between mining activities and children’s malnutrition outcomes at the district level. Census data, the Demographic Health …

Forecasting Sea Level Rise-Driven Inundation In Diked And Tidally Restricted Coastal Lowlands, K. M. Befus, A. P.D. Kurnizki, K. D. Kroeger, M. J. Eagle, T. P. Smith

Geosciences Faculty Publications and Presentations

Diked and drained coastal lowlands rely on hydraulic and protective infrastructure that may not function as designed in areas with relative sea-level rise. The slow and incremental loss of the hydraulic conditions required for a well-drained system make it difficult to identify if and when the flow structures no longer discharge enough water, especially in tidal settings where two-way flows occur through the dike. We developed and applied a hydraulic mass-balance model to quantify how water levels in the diked and tidally restricted coastal wetlands and water bodies dynamically respond to sea-level rise, specifically applied to the Herring River Estuary …