With the development of small satellites it has become easier and cheaper to deploy satellites for earth observation from space. While optical sensors capture high-resolution data, this data is traditionally sent to earth for analysis which puts a high constraint on the data link and increases the time for making data based decisions. This thesis explores the possibilities of deploying an AI model in small satellites for detecting objects in satellite imagery and therefore reduce the amount of data that needs to be transmitted. The neural network model YOLOv8 was trained on the xView and DIOR dataset and evaluated in a hardware restricted execution environment. The model achieved a mAP50 of 0.66 and could process satellite images at a speed of 309m2/s.

<p>Rivers are constantly undergoing change due to erosion and sedimentation along their banks. Although these processes generally occur gradually, flood events can significantly accelerate river migration, creating a risk for human life and infrastructure. As a result, it is important to identify river reaches that are prone to channel migration and determine the extent of migration. However, detailed information about river migration across entire river networks is not readily available. This study seeks to develop a Python-based tool that can generate river migration rasters across large watersheds using Landsat imagery. The methodology involves extracting the centerlines of river features in Landsat imagery using the Modified Normalized Difference Water Index (MNDWI) and the Skeletonize function available in the scikit-image library, followed by the application of the Particle Image Velocimetry (PIV) algorithm to compute the river channel migration. The PIV algorithm generates a set of migration rasters that are analyzed to extract the long-term migration of each of the reaches. The tool also creates intermediate outputs, such as the MNDWI raster, binary land-water raster, and skeletonized river centerlines, which can be further analyzed to gain insights into the river's behavior. The methodology is implemented in the Wabash and Lower Mississippi River Basins, and the tool's effectiveness is validated against manual measurements of the river migration available for the Wabash Basin. In addition, this study analyzes the correlation between long-term migration and various factors, such as reach sinuosity, drainage area, geology, and streamflow. The results of the analysis show that drainage area is highly correlated with river migration. The correlation results are compared with the prior literature, thereby serving to validate the developed framework. This framework has the potential to aid decision-makers and policymakers in identifying the long-term patterns of river channel migration, facilitating their efforts to plan for infrastructure resilience. By utilizing this methodology, river managers and other stakeholders can gain insights into river migration across large watersheds and identify areas that require further monitoring and management.</p>

Indiana University-Purdue University Indianapolis (IUPUI) / Despite growing recognition as a significant natural resource, methods for accurately estimating urban tree canopy cover extent and change over time are not well-established. This study evaluates new methods and data sources for mapping urban tree canopy cover, assessing the potential for increased accuracy by integrating high-resolution satellite imagery and 3D imagery derived from LIDAR and stereoscopic sensors. The results of urban tree canopy classifications derived from imagery, 3D data, and vegetation index data are compared across multiple urban land use types in the City of Indianapolis, Indiana. Results indicate that incorporation of 3D data and vegetation index data with high resolution satellite imagery does not significantly improve overall classification accuracy. Overall classification accuracies range from 88.34% to 89.66%, with resulting overall Kappa statistics ranging from 75.08% to 78.03%, respectively. Statistically significant differences in accuracy occurred only when high resolution satellite imagery was not included in the classification treatment and only the vegetation index data or 3D data were evaluated. Overall classification accuracy for these treatment methods were 78.33% for both treatments, with resulting overall Kappa statistics of 51.36% and 52.59%.

A combination of factors including land use change and fire suppression has resulted in the loss of pine savanna habitats across the southeastern U.S., affecting many avian species dependent on these habitats. However, due to the ephemeral nature of the habitat requirements of many pine savanna species (e.g., habitat is only present for a couple of years after a fire), targeted management of such habitats can be challenging. Moreover, the growing numbers of imperiled pine savanna species can make prioritizing management difficult. One potential tool to better inform management of pine savanna species is satellite imagery. Sentinel-2 satellite imagery data provides an instantaneous snapshot of habitat quality at a high resolution and across a large geographic area, which may make it more efficient than traditional, ground-based vegetation surveying. Thus, the objectives of my research were to 1) evaluate the use of remote sensing technology to predict habitat occupancy for pine savanna species, and 2) use satellite imagery-based models to inform multispecies management in a pine savanna habitat. To meet my objectives, I conducted point count surveys and built predictive models for three pine savanna bird species: Bachman's Sparrow (BACS; Peuacea aestivalis), Northern Bobwhite (NOBO; Colinus virginianus), and Red-Cockaded Woodpecker (RCW; Dryobates borealis) across Georgia. I assessed the performance of satellite imagery in predicting habitat occupancy of these pine savanna species and its potential for multispecies management. I found that models created using satellite imagery habitat metric data performed well at predicting the occupancy of all three species as measured by the Area Under the Receiver Operating Characteristic Curve: BACS=0.84, NOBO=0.87, RCW=0.76 (with values between 0.7-1 defined as acceptable or good predictive capacity). For BACS and NOBO, I was able to compare these satellite imagery models to field-based models, and satellite models performed better than those using traditional vegetation survey data (BACS=0.80, NOBO=0.79). Moreover, I found that satellite imagery data provided useful insights into the potential for multispecies management within the pine savanna habitats of Georgia. Finally, I found differences in the habitat selected by BACS, NOBO, and RCW, and that BACS may exhibit spatial variations in habitat use. The results of this study have significant implications for the conservation of pine savanna species, demonstrating that satellite imagery can allow users to build reliable occupancy models and inform multispecies management without intensive vegetation surveying. / Master of Science / Land-use changes have resulted in the disruption of natural disturbances such as fires, resulting in the loss of pine savanna habitats throughout the southeastern U.S. Although many of the species that occupy these habitats are experiencing rapid population declines, habitat for pine savanna species can be challenging to manage. Without reoccurring fire, pine savanna habitat can become unsuitable for obligate species within short periods of time, forcing these species to disperse to newly disturbed habitats. The transient nature of the preferred habitat of pine savanna species makes targeting management for these species difficult, as it can be challenging to locate exactly where occupied habitats exist. Furthermore, as the number of pine savanna species that are declining is large, prioritizing management of these species can be difficult especially given limited conservation funding. One potential tool to better inform the management of pine savanna species is satellite imagery. Satellite imagery can capture habitat information across broad areas, at fine resolutions, and at frequent intervals, potentially making satellite imagery more efficient than conducting field vegetation surveys on the ground for gaining information on habitat suitability. Thus, the objectives of my research were to 1) determine if satellite imagery can effectively predict the habitats occupied by pine savanna species (habitat occupancy), and 2) use satellite imagery-based models to inform the simultaneous management of multiple species (multispecies management) in a pine savanna habitat. To meet these objectives, I conducted surveys and built predictive models for three pine savanna bird species: Bachman's sparrow (BACS; Peuacea aestivalis), Northern Bobwhite (NOBO; Colinus virginianus), and Red-Cockaded Woodpecker (RCW; Dryobates borealis) in Georgia. I found models informed by satellite imagery performed well at predicting habitats occupied for all three species. Furthermore, models developed using satellite imagery performed better at predicting the habitats occupied by pine savanna species than models developed using on the ground vegetation surveys. I also found that satellite imagery data provided useful insights into strategies to manage pine savanna species simultaneously. I found evidence that BACS, NOBO, and RCW may have contrasting habitat needs and that BACS may use habitat differently between sites in Georgia. The results of this study demonstrate that satellite imagery can be used to predict the habitats occupied by pine savanna species and inform multispecies management without surveying vegetation on the ground, which is a more efficient use of time and funding.

One of the many challenges humanity faces is developing energy access in a sustainable manner, that does not further contribute to the burning of fossil fuels, increasing greenhouse gas emissions, and global warming. In 2020, 2.4 billion people used inefficient and polluting cooking systems due to lack of energy access while 25% of schools lacked access to electricity, drinking water and basic sanitation. This thesis seeks to investigate this challenge by using satellite imagery big data to improve energy access in a sustainable manner.The theoretical framework explains the key concepts and outlines the theoretical underpinnings of this research in transformative social innovation theory and behavioural theory which help guide the analysis. The link between this research and existing research is also explained in this section. The methodology used will be to research review articles and choose the most appropriate and credible texts to answer two research questions. The first challenge relates to identifying promising applications of satellite imagery big data in improving energy access, and the second relates to explaining how we can ensure that development of energy access from satellite imagery is conducted in a sustainable manner.The primary findings of this research are that there are a number of credible review articles which contain real opportunities for improved energy access and include identifying optimum photovoltaics investment locations, identifying optimum small hydropower plant sites, CAM plant cultivation locations, an indicator to directly address sustainable energy investments and rural electricity access needs, and mapping of remote off-grid homes for improvement of energy access. The findings also indicated three key factors that are crucial for the sustainable development of energy access which include communication, collaboration, and community.There are a number of varied applications of satellite imagery big data discovered that each exhibit significant value in improving energy access. The value that can be gained is closely related to the ability of the research community, to engage with local actors, to build a collaborative environment, where knowledge is shared, and community is built.

No description available.

This dissertation develops new algorithms with different techniques in utilizing spatial and spectral information for hyperspectral image classification. It is necessary to perform spatial and spectral analysis and conduct dimensionality reduction (DR) for effective feature extraction, because hyperspectral imagery consists of a large number of spatial pixels along with hundreds of spectral dimensions. In the first proposed method, it employs spatial-aware collaboration-competition preserving graph embedding by imposing a spatial regularization term along with Tikhonov regularization in the objective function for DR of hyperspectral imagery. Moreover, Collaboration representation (CR) is an efficient classifier but without using spatial information. Thus, structure-aware collaborative representation (SaCRT) is introduced to utilize spatial information for more appropriate data representations. It is demonstrated that better classification performance can be offered by the SaCRT in this work. For DR, collaborative and low-rank representation-based graph for discriminant analysis of hyperspectral imagery is proposed. It can generate a more informative graph by combining collaborative and low-rank representation terms. With the collaborative term, it can incorporate within-class atoms. Meanwhile, it can preserve global data structure by use of the low-rank term. Since it employs a collaborative term in the estimation of representation coefficients, its closed-form solution results in less computational complexity in comparison to sparse representation. The proposed collaborative and low-rank representation-based graph can outperform the existing sparse and low-rank representation-based graph for DR of hyperspectral imagery. The concept of tree-based techniques and deep neural networks can be combined by use of an interpretable canonical deep tabular data learning architecture (TabNet). It uses sequential attention for choosing appropriate features at different decision steps. An efficient TabNet for hyperspectral image classification is developed in this dissertation, in which the performance of TabNet is enhanced by incorporating a 2-D convolution layer inside an attentive transformer. Additionally, better classification performance of TabNet can be obtained by utilizing structure profiles on TabNet.

<p>The use of banned toxic weapons in Iraq during Gulf War 1991 started new debates. The increase in cancer cases was the main focus of these issues. The gap in literature motivated this study to find out the correlation between use of DU weapons and its effects on human health. The different probable causes of increase in cancer cases, in Iraq after Gulf War 1991, have been discussed in this study. Three causes; DU, brick kilns smoke near Basra and Kuwait oil fire smoke have been selected. The major emphasis of this study is on use of Depleted Uranium (DU). Different statistical data sets have been used and displayed in the form of maps and graphs using GIS methodologies. It’s hard to say after this GIS based study that the fired Depleted Uranium is the sole cause of increase in cancer incidences in Iraq, while some trends and risk factors at least can be observed where increase in cancer cases in different Governorates in Iraq is clearly visible after Gulf War 1991. After analyzing satellite images of different dates, the second part of this study concludes that Kuwait oil wells smoke is not responsible for increase in cancer incidences in Iraq. A small debate has been initiated regarding smoke in brick kilns near Basra. No study has been found in this regard which can provide evidences that brick kilns smoke is the cause of increase in cancer incidences in southern Iraq.</p><p>It’s not easy to carry out a full fledge GIS based study to prove DU as cause of increase in cancer cases. The main limitation in this regard is unavailability of required data. Therefore a new GIS based methodology has been devised which can be used to prove relationship between exposure to DU and increase in cancer cases in Iraq. This new methodology is also dependent on specific data sets. Hence this methodology also recommends the collection of specific data sets required for this study.</p><p>At the end, a detailed study, with honesty, has been suggested to fill up the gaps found in literature whether use of Depleted Uranium in weapons is harmful for human health or not.</p>

<p>This&nbsp / thesis&nbsp / examines&nbsp / the&nbsp / changes&nbsp / that&nbsp / have&nbsp / occurred&nbsp / within&nbsp / West-Coast Renosterveld within&nbsp / the&nbsp / last 350 years, and assesses&nbsp / the viability of&nbsp / the&nbsp / remaining fragments.</p>

Thesis (M.S.)--Indiana University, 2009. / Department of Geography, Indiana University-Purdue University Indianapolis (IUPUI). Advisor(s): Jeffrey S. Wilson, Lenore P. Tedesco, Daniel P. Johnson. Includes vitae. Includes bibliographical references (leaves 71-77).