Dissertations
Permanent URI for this collectionhttps://hdl.handle.net/1969.6/1139
Browse
Browsing Dissertations by Department "Computing Sciences"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Geospatial monitoring and assessment of coastal land subsidence(2023-12) Qiao, Xiaojun; Chu, Tianxing; Tissot, Philippe; King, Scott; Xie, Feiqin; Rao, MohanSubsidence, the downward movement of the land, presents risks in coastal areas such as shoreline erosion and coastal flooding. The accurate estimation of subsidence and the identification of its underlying causes holds significant values for comprehending subsidence processes and guiding decision-making. However, both the subsidence estimation and interpretation are challenging due to its spatio-temporal variability, limited observability, and the complexity caused by natural processes and anthropogenic activities. The contributions of this dissertation were to 1) estimate subsidence at locations of tide gauge (TG) stations along the coastlines; 2) investigate coastal subsidence by integrating measurements from a variety of geodetic techniques such as global navigation satellite systems (GNSS), interferometric synthetic aperture radar (InSAR), TGs, and satellite radar altimtery (SRA); and 3) model subsidence with features related to natural processes and anthropogenic activities and identify potential drivers with machine learning (ML) techniques. These contributions were exemplified through case studies at the Texas Gulf Coast areas. First, two sea-level difference methods, through leveraging TG and SRA measurements, were developed to reconstruct subsidence time series at tide gauge (TG) locations along the Texas coastlines with observation periods exceeding ten years. In addition, synthetic aperture radar (SAR) imagery, continuously operating GNSS (cGNSS) observations, and sea-level measurements were harnessed to estimate the spatio-temporal patterns of subsidence spanning around three decades since the 1990s at the Eagle Point TG station, a prominent hotspot of sea-level rise in the United States. The results obtained from multiple geodetic techniques provided strong and consistent evidence of subsidence processes in the vicinity of Eagle Point. Moreover, a large-scale subsidence map along the Texas coastlines post-2016 was generated with SAR images, revealing that the Texas Gulf Coast experienced an average subsidence rate of -1 mm/yr near the shoreline with an increasing trend in magnitude inland. Attribution analysis indicated that hydrocarbon extraction and groundwater withdrawal were the predominant factors responsible for identified subsidence hotspots in the Texas Gulf Coast. ML demonstrated an impressive performance (with an 𝑅2 of 0.56) in modeling the observed large-scale subsidence, by incorporating a range of features related to natural terrain variations and anthropogenic activities. Explainable artificial intelligence (XAI) methods provided quantitative estimates of feature contributions of the ML model, and the data-driven results revealed that the digital elevation model (DEM) and anthropogenic factors were contributing features in relation to subsidence.Item Towards intelligent and sustainable IOT system(2023-8) Zhang, Wen; Pan, Chen; Li, Longzhuang; Kar, Dulal; Chu, TianxingThe rapid integration of Artificial Intelligence into the Internet of Everything (AIoE) has led to the ubiquitous presence of embedded devices, playing crucial roles in various aspects of our lives. However, the limited battery life of these devices poses a significant challenge as they are expected to deliver an increasing number of services and applications. Consequently, the sustainability of embedded devices has become a paramount concern for both academia and industry. In response, Energy Harvesting (EH) has emerged as a promising solution, enabling devices to harvest energy from the surrounding environment, such as radio frequency and thermal energy, to power them- selves perpetually. While EH has extended device lifetimes, effectively utilizing EH-powered de- vices in large-scale deployments remains a challenge. The transient nature of energy harvesting ne- cessitates that EH devices alternate between active (discharging) and dormant (recharging) states, resulting in frequent interruptions during sensing and communication activities. Traditional strate- gies for sensing, communication, and energy allocation are ill-suited for EH devices, as those tradi- tional strategies assume devices can be activated at any time, contrary to the characteristics of EH devices. Although prior research has focused on EH-aware sensing and communication strategies, most existing studies have predominantly approached optimization from an individual perspective. To address these challenges, this dissertation proposes a sustainable and intelligent IoT system leveraging emerging technologies, such as deep reinforcement learning and compressed sensing. The proposed framework encompasses three key components: 1) A comprehensive sparsity-aware spatiotemporal data sensing framework for EH IoT systems, aiming to optimize data collection by selectively sensing and processing relevant data based on sparsity characteristics with the consid- eration of the intermittency of EH IoT devices. 2) Environment adaptive multi-hop routing and energy allocation for EH IoT networks, considering the intermittent nature of EH devices. This component incorporates dynamic changes in energy harvesting and jointly optimizes routing poli- cies and energy allocation for efficient data routing. 3) A unmanned aerial vehicles (UAVs)-assisted EH IoT framework that assists ground EH devices in completing data collection tasks such as environment monitoring. By leveraging the capabilities of UAVs, this integrated approach enhances data collection efficiency and extends the reach of EH-powered IoT systems. Through these contributions, this dissertation addresses the challenges associated with EH IoT systems, emphasizing energy efficiency, sustainable operation, and intelligent decision-making. The proposed framework integrates deep reinforcement learning and compressed sensing tech- niques, fostering the development of a resilient and efficient IoT ecosystem.