Hydrological connectivity is crucial for understanding and managing water resources, ecological processes, and landscape dynamics. High-Resolution Digital Elevation Models (HRDEMs) derived from Light Detection and Ranging (LiDAR) data offer unprecedented detail and accuracy in representing terrain features, making them invaluable for mapping hydrological networks and analyzing landscape connectivity. However, challenges persist in accurately delineating flow networks, identifying flow barriers, and optimizing computational efficiency, particularly in large-scale applications and complex terrain conditions. This dissertation addresses these challenges through a comprehensive exploration of advanced techniques in deep learning, spatial analysis, and parallel computing. A common practice is to breach the elevation of roads near drainage crossing locations to remove flow barriers, which, however, are often unavailable or with variable quality. Thus, developing a reliable drainage crossing dataset is essential to improve the HRDEMs for hydrographic delineation. Deep learning models were developed for classifying images that contain the locations of flow barriers. Based on HRDEMs and aerial orthophotos, different Convolutional Neural Network (CNN) models were trained and compared to assess their effectiveness in image classification in four different watersheds across the U.S. Midwest. The results show that most deep learning models can consistently achieve over 90% accuracies. The CNN model with a batch size of 16, a learning rate of 0.01, an epoch of 100, and the HRDEM as the sole input feature exhibits the best performance with 93% accuracy. The addition of aerial orthophotos and their derived spectral indices is insignificant to or even worsens the model’s accuracy. Transferability assessments across geographic regions show promising potential of best-fit model for broader applications, albeit with varying accuracies influenced by hydrography complexity. Based on identified drainage crossing locations, Drainage Barrier Processing (DBP), such as HRDEM excavation, is employed to remove the flow barriers. However, there's a gap in quantitatively assessing the impact of DBP on HRDEM-derived flowlines, especially at finer scales. HRDEM-derived flowlines generated with different flow direction algorithms were evaluated by developing a framework to measure the effects of flow barrier removal. The results show that the primary factor influencing flowline quality is the presence of flow accumulation artifacts. Quality issues also stem from differences between natural and artificial flow paths, unrealistic flowlines in flat areas, complex canal networks, and ephemeral drainageways. Notably, the improvement achieved by DBP is demonstrated to be more than 6%, showcasing its efficacy in reducing the impact of flow barriers on hydrologic connectivity. To overcome the computational intensity and speed up data processing, the efficiency of parallel computing techniques for GeoAI and hydrological modeling was evaluated. The performance of CPU parallel processing on High-Performance Computing (HPC) systems was compared with serial processing on desktop computers and GPU processing using Graphics Processing Units (GPUs). Results demonstrated substantial performance enhancements with GPU processing, particularly in accelerating computationally intensive tasks such as deep learning-based feature detection and hydrological modeling. However, efficiency trends exhibit nonlinear patterns influenced by factors such as communication overhead, task distribution, and resource contention. In summary, this dissertation presents a GeoAI-Hydro framework that significantly advances the quality of hydrological connectivity modeling. By integrating deep learning for accurate flow barrier identification, employing DBP to enhance flowline quality, and utilizing parallel computing to address computational demands, the framework offers a robust solution for high-quality hydrological network mapping and analysis. It paves the way for contributions to more effective water resource management, ecological conservation, and landscape planning.

High-resolution digital elevation models (HRDEMs) enable precise mapping of hydrographic features. However, the absence of drainage crossings underpassing roads or bridges hinders accurate delineation of stream networks. Traditional methods such as on-screen digitization and field surveys for locating these crossings are time-consuming and expensive for extensive areas. This study investigates the effectiveness of deep learning models for automated drainage crossing detection using HRDEMs. The study also explores the performance of advanced classification algorithm such as EfficientNetV2 model using various co-registered HRDRM-derived geomorphological features, such as positive openness, geometric curvature, and topographic position index (TPI) variants, for drainage crossings classification. The results reveal that individual layers, particularly HRDEM and TPI21, achieve the best performance, while combining all five layers doesn't improve accuracy. Hence, effective feature screening is crucial, as eliminating less informative features enhances the F1 score. For drainage crossing detection, this study develops and trains deep learning models, Faster R-CNN and YOLOv5 object detectors, using HRDEM tiles and ground truth labels. These models achieve an average F1-score of 0.78 in Nebraska watershed and demonstrate successful transferability to other watersheds. This spatial object detection approach offers a promising avenue for automated, large-scale drainage crossing detection, facilitating the integration of these features into HRDEMs and improving the accuracy of hydrographic network delineation.

abstract: Big data that contain geo-referenced attributes have significantly reformed the way that I process and analyze geospatial data. Compared with the expected benefits received in the data-rich environment, more data have not always contributed to more accurate analysis. “Big but valueless” has becoming a critical concern to the community of GIScience and data-driven geography. As a highly-utilized function of GeoAI technique, deep learning models designed for processing geospatial data integrate powerful computing hardware and deep neural networks into various dimensions of geography to effectively discover the representation of data. However, limitations of these deep learning models have also been reported when People may have to spend much time on preparing training data for implementing a deep learning model. The objective of this dissertation research is to promote state-of-the-art deep learning models in discovering the representation, value and hidden knowledge of GIS and remote sensing data, through three research approaches. The first methodological framework aims to unify varied shadow into limited number of patterns, with the convolutional neural network (CNNs)-powered shape classification, multifarious shadow shapes with a limited number of representative shadow patterns for efficient shadow-based building height estimation. The second research focus integrates semantic analysis into a framework of various state-of-the-art CNNs to support human-level understanding of map content. The final research approach of this dissertation focuses on normalizing geospatial domain knowledge to promote the transferability of a CNN’s model to land-use/land-cover classification. This research reports a method designed to discover detailed land-use/land-cover types that might be challenging for a state-of-the-art CNN’s model that previously performed well on land-cover classification only. / Dissertation/Thesis / Doctoral Dissertation Geography 2019

L’abeille mellifère (Apis mellifera) occupe une place centrale dans nos systèmes agro-alimentaires et écologiques. En plus de produire du miel, l’espèce assure un rôle crucial pour la pollinisation d’un grand nombre de cultures, améliorant les récoltes tant en qualité qu’en quantité. Depuis une vingtaine d’années, les apiculteurs constatent dans leurs colonies des taux de mortalité plus élevés que la normale. Si cette tendance s’observe sur plusieurs continents, c’est en Amérique du Nord que les apiculteurs sont le plus affectés, avec des taux de mortalité hivernale dépassant les 40 %. La perte d’habitats et des habitats inadéquats sont parmi les facteurs les plus souvent mis en cause dans les dernières études. Ce mémoire présente une analyse des différents habitats afin de mesurer les effets du paysage environnant sur la mortalité. Pour ce faire, des images satellites et des nouveaux ensembles massifs de données sur la santé des ruches au Québec ont pu être mobilisés. Ce mémoire présente un cadre méthodologique prometteur pour une analyse géographique des effets du paysage avec de grands jeux de données. Les méthodes utilisées font appel à l’analyse spatiale par système d’information géographique et à des modèles d’apprentissage automatique. Un domaine d’étude récent a émergé de la combinaison de ces techniques: l’intelligence artificielle géospatiale, ou GéoIA. Deux cas d’études furent réalisés dans ce mémoire: un premier sur l’apiculture urbaine et un second sur l’apiculture commerciale. En ville, nos principaux résultats révèlent l’importance de la végétation locale autour de la ruche, ainsi que l’effet négatif d’un paysage urbain fragmenté limitant la connectivité. En apiculture commerciale, on trouve qu'une plus grande diversité de cultures est bénéfique dans un rayon de cinq kilomètres, mais que l'effet se dissipe au fur et à mesure que la distance de mesure se réduit. On observe aussi qu’une abondance de ressources florales en milieu de saison est cruciale pour la survie de la colonie. Dans l’ensemble, la performance prédictive des modèles utilisés dans ce mémoire confirme la solidité du GéoIA comme cadre d’analyse de pointe offrant des outils puissants et généralisables pour mener des études géographiques à grande échelle. / The honeybee (Apis mellifera) plays a central role in our agri-food and ecological systems. Beyond honey production, the species plays a crucial role in pollinating a large number of crops, improving harvests in terms of both quality and quantity. Over the last twenty years or so, beekeepers have observed much higher-than-normal mortality rates in their colonies. While this trend can be observed on several continents, it is in North America that beekeepers are most affected, with winter mortality rates sometimes exceeding 40%. Habitat loss and unsuitable habitats are among the explaining factors most often suspected in recent studies. This thesis presents an analysis of different habitats to measure the effects of the surrounding landscape. To this end, satellite images and massive new datasets on beehive health in Quebec were mobilized. This thesis also presents a promising methodological framework for the geographical analysis of landscape effects with large datasets. The methods used fall within the framework of spatial analysis, geographic information systems and machine learning models. A recent field of study has emerged from the combination of these techniques: geospatial artificial intelligence, or GeoAI. Two case studies were carried out in this thesis: the first on urban beekeeping and the second on commercial beekeeping. In urban beekeeping, our main results reveal the importance of local vegetation around the hive, as well as the negative effect of a fragmented urban landscape limiting connectivity. In commercial beekeeping, we first observe that greater crop diversity is beneficial at a radius of five kilometers, but that the effect dissipates as the measuring distance is reduced. We also found that an abundance of mid-season floral resources is crucial for colony survival. More generally, the predictive performance of the models used in the presented studies confirms the strength of GeoAI as a state-of-the-art analytical framework offering powerful and generalizable tools for conducting large-scale geographical studies.

<p dir="ltr">This dissertation explores the integration of remote sensing and artificial intelligence (AI) in geospatial mapping, specifically through the development of knowledge-based mapping systems. Remote sensing has revolutionized Earth observation by providing data that far surpasses traditional in-situ measurements. Over the last decade, significant advancements in inferential capabilities have been achieved through the fusion of geospatial sciences and AI (GeoAI), particularly with the application of deep learning. Despite its benefits, the reliance on data-driven AI has introduced challenges, including unpredictable errors and biases due to imperfect labeling and the opaque nature of the processes involved.</p><p dir="ltr">The research highlights the limitations of solely using data-driven AI methods for geospatial mapping, which tend to produce spatially heterogeneous errors and lack transparency, thus compromising the trustworthiness of the outputs. In response, it proposes novel knowledge-based mapping systems that prioritize transparency and scalability. This research has developed comprehensive techniques to extract key Earth and urban features and has introduced a 3D urban land cover mapping system, including a 3D Landscape Clustering framework aimed at enhancing urban climate studies. The developed systems utilize universally applicable physical knowledge of targets, captured through remote sensing, to enhance mapping accuracy and reliability without the typical drawbacks of data-driven approaches.</p><p dir="ltr">The dissertation emphasizes the importance of moving beyond mere accuracy to consider the broader implications of error patterns in geospatial mappings. It demonstrates the value of integrating generalizable target knowledge, explicitly represented in remote sensing data, into geospatial mapping to address the trustworthiness challenges in AI mapping systems. By developing mapping systems that are open, transparent, and scalable, this work aims to mitigate the effects of spatially heterogeneous errors, thereby improving the trustworthiness of geospatial mapping and analysis across various fields. Additionally, the dissertation introduces methodologies to support urban pathway accessibility and flood management studies through dependable geospatial systems. These efforts aim to establish a robust foundation for informed urban planning, efficient resource allocation, and enriched environmental insights, contributing to the development of more sustainable, resilient, and smart cities.</p>