Remote Sensing Commons^™

Measuring Agricultural Adaptation Using Remote Sensing: A Study Of Pigeonpea In Malawi, Maria Gorret Nabuwembo

Graduate Theses and Dissertations

Drought, heatwaves, and flooding cause tremendous damage to agricultural production in Malawi, and the continuous production of maize has led to widespread soil degradation. Additionally, climate change is transforming the environment at a scale beyond historical records, posing significant challenges to social, political, and economic systems. To combat these issues, agricultural innovations have been implemented, such as the installation of irrigation systems and development of heat/drought resilient crop varieties. Pigeonpea is one of the prominent drought-tolerant and temperature resilient crops grown as a diversification strategy since it allows farmers to adapt to changes while maintaining subsistence needs. This research investigates …

Comparison Of Airborne Lidar-Derived Elevation Data In Fayetteville, Arkansas, Usa, Angelica M. Otting

Graduate Theses and Dissertations

Light detection and ranging (lidar) laser scanners are prominent remote sensing tools to produce high resolution three-dimensional (3D) imagery of the Earth’s surface. These laser scanners combined with global navigation satellite systems (GNSS) and real-time kinematic (RTK) reference stations can generate some of the most accurate ground surface imagery and elevation data for terrain mapping and related applications. Lidar aerial survey is an important tool in industries such as architecture, civil engineering, forestry, geology, geography, and agriculture where digital terrain models (DTMs) can be used to examine the geographical landscape and urban industry. Currently, there are three different common laser …

Aerialformer: Multi-Resolution Transformer For Aerial Image Segmentation, Taisei Hanyu, Kashu Yamazaki, Minh Tran, Roy A. Mccann, Haitao Liao, Chase Rainwater, Meredith Adkins, Jackson Cothren, Hoang Le

Industrial Engineering Faculty Publications and Presentations

When performing remote sensing image segmentation, practitioners often encounter various challenges, such as a strong imbalance in the foreground–background, the presence of tiny objects, high object density, intra-class heterogeneity, and inter-class homogeneity. To overcome these challenges, this paper introduces AerialFormer, a hybrid model that strategically combines the strengths of Transformers and Convolutional Neural Networks (CNNs). AerialFormer features a CNN Stem module integrated to preserve low-level and high-resolution features, enhancing the model’s capability to process details of aerial imagery. The proposed AerialFormer is designed with a hierarchical structure, in which a Transformer encoder generates multi-scale features and a multi-dilated CNN (MDC) …

Fire Potential In Arkansas Through The Lens Of The Keetch-Byram Drought Index, Charles Steward

Graduate Theses and Dissertations

Vegetation fires are a complicated phenomenon to predict both the occurrence and intensity. In the United States, fire behavior has been widely studied in high-risk regions such as in the American West, but fires also occur regularly in states that receive greater levels of precipitation, such as Arkansas. Fires are an expensive and dangerous environmental problem. As climate trends caused by global warming continue to progress, quantifying the extent to which climate factors influence their occurrence in Arkansas would be useful for land management, public safety, public health, agriculture, urban development, and to advance the science of fire-climate dynamics in …

Remote, Rugged Field Scenarios For Archaeology And The Field Sciences: Object Avoidance And 3d Flight Planning With Suas Photogrammetry, Carla Klehm, Malcolm D. Williamson, Leland C. Bement, Brandi Bethke

Center for Advanced Spatial Technologies Publications and Presentations

Advances built into recent sUASs (drones) offer a compelling possibility for field-based data collection in logistically challenging and GPS-denied environments. sUASs-based photogrammetry generates 3D models of features and landscapes, used extensively in archaeology as well as other field sciences. Until recently, navigation has been limited by the expertise of the pilot, as objects, like trees, and vertical or complex environments, such as cliffs, create significant risks to successful documentation. This article assesses sUASs’ capability for autonomous obstacle avoidance and 3D flight planning using data collection scenarios carried out in Black Mesa, Oklahoma. Imagery processed using commercial software confirmed that the …

Analyzing The Adoption, Cropping Rotation, And Impact Of Winter Cover Crops In The Mississippi Alluvial Plain (Map) Region Through Remote Sensing Technologies, Zobaer Ahmed

Graduate Theses and Dissertations

This dissertation explores the application of remote sensing technologies in conservation agriculture, specifically focusing on identifying and mapping winter cover crops and assessing voluntary cover crop adoption and cropping patterns in the Arkansas portion of the Mississippi Alluvial Plain (MAP). In the first chapter, a systematic review using the PRISMA methodology examines the last 30 years of thematic research, development, and trends in remote sensing applied to conservation agriculture from a global perspective. The review uncovers a growing interest in remote sensing-based research in conservation agriculture and emphasizes the necessity for further studies dedicated to conservation practices. Among the 68 …

The Terroir Of Swiss Cheese: A Temporal And Geomorphological Investigation Of The Martian Co2 Sublimation Pits, Racine D. Cleveland

Graduate Theses and Dissertations

Observations by NASA Mars Global Surveyor showed evidence of rough topography on the South Pole of Mars. The topography is the result of CO2 sublimation processes that occur through the changing seasons on the red planet. These sublimation areas are known to scientists as Swiss Cheese Features (SCF). SCF are erosional degradation pits that have been studied for over two decades. Studies show that these SCF increase in area over time, but these values are collected by hand on a per feature basis. Models for the pit evolution have also played a part in understanding these SCF. This work is …

Reproducibility And Replicability In Unmanned Aircraft Systems And Geographic Information Science, Cassandra Howe

Graduate Theses and Dissertations

Multiple scientific disciplines face a so-called crisis of reproducibility and replicability (R&R) in which the validity of methodologies is questioned due to an inability to confirm experimental results. Trust in information technology (IT)-intensive workflows within geographic information science (GIScience), remote sensing, and photogrammetry depends on solutions to R&R challenges affecting multiple computationally driven disciplines. To date, there have only been very limited efforts to overcome R&R-related issues in remote sensing workflows in general, let alone those tied to disruptive technologies such as unmanned aircraft systems (UAS) and machine learning (ML). To accelerate an understanding of this crisis, a review was …

Efficient Hierarchical Space-Time Models For Large Areal Datasets With Application To Forest Inventory Mapping Using Remote Sensing Imagery, Md Kamrul Hasan Khan

Graduate Theses and Dissertations

The focus of this dissertation is development of a novel hierarchical framework, that can be used for predictive modeling of Forest Inventory and Analysis (FIA) data over large regions. This dissertation has two significant contributions. Based on a study region in north-central Wisconsin, we analyze satellite imagery, along with a sample of national forest inventory field plots, to monitor and predict changes in forest conditions over time. The auxiliary data from the satellite imagery of this region are relatively dense in space and time, and can be used to learn how forest conditions changed over that decade. However, these records …

Delineating Field Variation Using Apparent Electrical Conductivity In An Ozark Highlands Agroforestry System, Shane Reid Ylagan

Graduate Theses and Dissertations

Little to no work has been conducted assessing field variability using repeated electromagnetic induction (EMI) apparent electrical conductivity (ECa) surveys in agroforestry (AF) systems within regions similar to the Ozark Highlands. The objectives of this thesis were to identify i) spatiotemporal ECa variability; ii) ECa-derived soil management zones (SMZs); iii) correlations among EMI-ECa and in-situ, sentential-site soil properties; iv) whether fewer, EMI-ECa surveys could be conducted to capture similar ECa variance as mid-monthly EMI-ECa surveys; v) correlations between ECa and forage yield, tree growth, and terrain attributes based on plant (forage and tree) species, and fertility treatments, and ECa-derived SMZs, …

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 …

Deep Learning Applications In Industrial And Systems Engineering, Winthrop Harvey

Graduate Theses and Dissertations

Deep learning - the use of large neural networks to perform machine learning - has transformed the world. As the capabilities of deep models continue to grow, deep learning is becoming an increasingly valuable and practical tool for industrial engineering. With its wide applicability, deep learning can be turned to many industrial engineering tasks, including optimization, heuristic search, and functional approximation. In this dissertation, the major concepts and paradigms of deep learning are reviewed, and three industrial engineering projects applying these methods are described. The first applies a deep convolutional network to the task of absolute aerial geolocalization - the …

Multi-Trophic Biodiversity Increases With Increasing Structural Complexity Of Forest Canopy, Ayanna St. Rose

Graduate Theses and Dissertations

Understanding the effects of forest canopy structural complexity on multi-trophic diversity is critical for conserving biodiversity and managing land sustainably. But multi-trophic diversity is often ignored when making decisions about land management due to lack of cost- and time-effective methods to evaluate it. Here, we explored a new method based on widely available remote sensing data to quantify canopy structural complexity and its relationships with multi-trophic biodiversity at landscape scale using 32 forested sites of the National Ecological Observatory Network. We investigated the influence of vertical and horizontal structural complexity of forest canopy on multi-trophic (primary producers, herbivores (beetles), omnivores …

Toward Global Localization Of Unmanned Aircraft Systems Using Overhead Image Registration With Deep Learning Convolutional Neural Networks, Rachel Linck

Graduate Theses and Dissertations

Global localization, in which an unmanned aircraft system (UAS) estimates its unknown current location without access to its take-off location or other locational data from its flight path, is a challenging problem. This research brings together aspects from the remote sensing, geoinformatics, and machine learning disciplines by framing the global localization problem as a geospatial image registration problem in which overhead aerial and satellite imagery serve as a proxy for UAS imagery. A literature review is conducted covering the use of deep learning convolutional neural networks (DLCNN) with global localization and other related geospatial imagery applications. Differences between geospatial imagery …

Machine Learning For Modeling Wildfire Susceptibility At The State Level: An Example From Arkansas, Usa, Abdullah Al Saim, Mohamed H. Aly

Geosciences Faculty Publications and Presentations

Fire susceptibility modeling is crucial for sustaining and managing forests among many other valuable land resources. With 56% of its area covered by forests, Arkansas is known as the "natural state". About 1000 wildfires occurred and burned more than 10,000 acres each year during 1981-2018. In this paper, we use remote-sensing-based machine learning methods to address the natural and anthropogenic factors influencing wildfires and model fire susceptibility in Arkansas. Among the 15 explored variables, potential evapotranspiration, soil moisture, Palmer drought severity index, and dry season precipitation were recognized as the most significant factors contributing to the fire density. The obtained …

Direct Aerial Visual Geolocalization Using Deep Neural Networks, Winthrop Harvey, Chase Rainwater, Jackson Cothren

Industrial Engineering Faculty Publications and Presentations

Unmanned aerial vehicles (UAVs) must keep track of their location in order to maintain flight plans. Currently, this task is almost entirely performed by a combination of Inertial Measurement Units (IMUs) and reference to GNSS (Global Navigation Satellite System). Navigation by GNSS, however, is not always reliable, due to various causes both natural (reflection and blockage from objects, technical fault, inclement weather) and artificial (GPS spoofing and denial). In such GPS-denied situations, it is desirable to have additional methods for aerial geolocalization. One such method is visual geolocalization, where aircraft use their ground facing cameras to localize and navigate. The …

Geolocation Of Monitoring Wells Using Small Unmanned Aircraft Systems, Joel Deyoung

Graduate Theses and Dissertations

Groundwater monitoring wells are commonly installed on a property as part of an environmental investigation to observe hydrological subsurface conditions, facilitate the collection of groundwater samples, and predict the flow of groundwater across a site. In addition to their installation, monitoring wells should be surveyed or mapped as accurately as possible. Traditional surveying techniques have employed the use of global navigation satellite systems (GNSS) technologies or other surveying equipment. A common surveying approach is to use real-time kinematic (RTK) GNSS to accurately measure the coordinates of each monitoring well on the site.In recent years, drones, or small unmanned aircraft systems …

Assessing Impacts Of Winter-Hay Feeding On Soil And Forage Nutrient Dynamics In A Rotationally-Grazed Pasture System In Arkansas, Lawrence Gordon Berry Iv

Graduate Theses and Dissertations

More than 38 % of United States’ rural land area was used for grazing (i.e., pastureland or rangeland) ruminant animals in 2017, constituting the largest private land use group. The expansive nature of these lands means that grazing and pasture management decisions have potential to impact water quality as well as profit margins. As a result, beef producers are under increased pressure from economic and environmental standpoints to limit application of nutrients beyond those required to grow the forage needed for animal consumption. At the same time, a large amount of nutrients is recycled back to pasture systems directly from …

Machine Learning & Big Data Analyses For Wildfire & Air Pollution Incorporating Gis & Google Earth Engine, Abdullah Al Saim

Graduate Theses and Dissertations

The climatic condition, the vegetation type, and the landscape of the United States have made it susceptible to wildfires. This research is divided into two parts based on the analysis of two different aspects of wildfires of two distinct regions. The first part of the study investigates the wildfire susceptibility in Arkansas. Arkansas is a natural state, and it is heavily dependent on its forest and agricultural resources. During the last 30 years, more than 1,000 wildfires occurred in Arkansas and caused more than 10,000 acres of burned areas. Therefore, identifying wildfire-susceptible areas is crucial for ensuring sustainable forest and …

Spatial Assessment Of Urban Growth In Cities Of The Decapolis; And The Implications For Modern Cities, Wade A. Pierson

Graduate Theses and Dissertations

The Levant’s Decapolis was a network of ten cities in Greco-Roman Israel, Jordan, and Syria that established a thriving economic community. The Decapolis was home to ancient and modern cities like Damascus (Dammásq) and Amman (Philadelphia). Despite the various origins of these cities, Roman administration and their city planners oversaw the implementation of idealized Roman city form throughout the region. Three Decapolis cities represent intriguing examples of the larger confederation. Philadelphia (Amman), Gerasa (Jerash), and Gadara (Umm Qais) represent cities of common original urban form which developed drastically diverse urban morphologies over time.

Spatial analyses of these cities required working …

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 …

Geospatial Analyses Of Seismic Hazards And Risk Perception In Libya, Somaia Suwihli

Graduate Theses and Dissertations

Libya is not considered a highly active seismic region. However, several earthquakes of magnitude >5.0 have occurred there. This dissertation analyzes the seismicity of Libya in order to better understand earthquake hazards, related geomorphic features, and the current evolution of Libyan perceptions of seismic risk. The first article developed a baseline of past and current seismic inventory in Libya, which represented an assessment of Libya seismic hazard by translating, analyzing, and compiling historical sources and archaeological data. This study shows that Libya has experienced earthquakes in varying degrees since ancient times. Through the spatial and temporal distribution of earthquakes from …

Remote Sensing And Gis Study Of Hazards And Risks In East Africa, Hafid Nanis

Graduate Theses and Dissertations

East Africa encompasses numerous developing countries and involves one of the most active continental rifts on Earth; namely, the East African Rift System. This region is prone to diverse geohazards due to its geographical location at the plate boundary. Several damaging events had happened across the region and more are predicted to occur in the near future. Therefore, it is crucial to investigate, assess, and forecast natural hazards and potential risks in the region. In this dissertation, remote sensing and Geographic Information System (GIS) were employed to conduct three independent studies focused on assessing geohazards in east Africa. Each study …

An Evaluation Of Unmanned Aircraft Systems' Ability To Assess Stripe Rust In Large Wheat Breeding Nursies, Jamison T. Murry

Graduate Theses and Dissertations

Stripe Rust (Puccinia striiformis f. sp. tritici) is a foliar disease that significantly impacts global wheat production, and resistant cultivars provide the most efficient method of control. High-throughput phenotyping using unmanned aircraft systems (UAS) offers a potentially more efficient method for field-based phenotyping compared to visual assessment. Here we tested the ability of remote sensing to predict stripe rust severity in a diverse population of 594 soft red winter wheat lines, planted in single-rows, and evaluated them by visually rating stripe rust intensity and remotely using the dark green color index (DGCI), normalized difference vegetation index (NDVI) and blue NDVI. …

The Structure And Dynamics Of A River Delta Are Related Through Its Nourishment Area, Suggesting Optimality, Christopher A. Cathcart

Graduate Theses and Dissertations

Scaling relations in tributary network geomorphology are well understood with respect to optimality. However, the scaling relations between structure and dynamics in distributary network geomorphology are less well understood. This is primarily due to the fact that nourishment area boundaries are difficult to map compared to tributary network catchment area boundaries. Furthermore, most previous work has focused either on the distributary channel networks or the delta’s partitioning of discharge. Here we show that, on the Wax Lake Delta (WLD) in Louisiana, the asymmetry in nourishment areas and downstream nourishment boundary width (∏) at a channel bifurcation, acts as a control …

Decadal Land Surface Phenology And Water Quality In The Headwaters Illinois River Watershed, Justin Ray Rollans

Graduate Theses and Dissertations

Over 25 percent of the world’s population either lives on or obtains water from karst aquifers. The complex interactions between subsurface karst geologic features, the constant motion of the plant life cycle, and significant water resource demand all suggest the need to better define those interactions. The relationship of historical land surface phenology and water quality in karst topography were investigated in the Headwaters Illinois River watershed in Northwest Arkansas (NWA). This area represents high vulnerability to surface water and groundwater contamination, with both natural and anthropogenic processes such as over application of broil litter for enhanced cattle browse, affecting …

Spatio-Temporal Reconstruction Of Remote Sensing Observations, Kamrul Khan

Graduate Theses and Dissertations

The USDA Forest Service aims to use satellite imagery for monitoring and predicting changes in forest conditions over time within the country. We specifically focus on a 230, 400 hectares region in north-central Wisconsin between 2003 - 2012. The auxiliary data collected from the satellite imagery of this region are relatively dense in space and time and can be used to efficiently predict how the forest condition changed over that decade. However, these records have a significant proportion of missing values due to weather conditions and system failures. To fill in these missing values, we build spaciotemporal models based on …

Seeing Prehistory Through New Lenses: Using Geophysical And Statistical Analysis To Identify Fresh Perspectives Of A 15th Century Mandan Occupation, Amber Marie Mitchum

Graduate Theses and Dissertations

Great Plains prehistoric research has evolved over the course of a century, with many sites like Huff Village (32MO11) in North Dakota recently coming back to the forefront of discussion through new technological applications. Through a majority of its studies and excavations, Huff Village appeared to endure as the final stage in the Middle Missouri tradition. Long thought to reflect only systematically placed long-rectangular structure types of its Middle Missouri predecessors, recent magnetic gradiometry and topographic mapping data revealed circular structure types that deviated from long-held traditions, highlighting new associations with Coalescent groups. A compact system for food capacity was …

Uas As An Inventory Tool: A Photogrammetric Approach To Volume Estimation, Richard Kramer Rhodes

Graduate Theses and Dissertations

Unmanned aircraft systems (UAS), also referred to as unmanned aerial vehicles (UAV) or remotely piloted vehicles (RPV), are associated with unmanned aircraft either controlled by a pilot on the ground or pre-programmed with specific flight paths. Small UASs have seen a massive increase in public interest in recent years as hobbyist platforms; they are, however, a potentially powerful tool in remote sensing and geospatial applications. Due to the increased availability of low-cost UAS, this technology could soon revolutionize many industries, including those that require volumetric estimation. Traditionally volumetric inventories have been performed with tape measurements, and in some instances where …

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 …