Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted Multi-sensor assessment of vegetation phenology in Rawdat Khuraim oasis: climate controls and spatiotemporal dynamics(Saudi Digital Library, 2025) Alharbi, Raed; Dewan, AshrafThis study investigated the dynamics of vegetation phenology in the Rawdat Khuraim Oasis, Saudi Arabia, using a multi-sensor remote sensing approach to assess climate-driven seasonal patterns from 2014 to 2024. The research addressed critical knowledge gaps on phenological responses in Arabian Peninsula oasis ecosystems through an integrated analysis of remote sensing data from three satellite systems: the Moderate Resolution Imaging Spectroradiometer (MODIS), Landsat 8/9, and Sentinel-2. Daily Normalized Difference Vegetation Index (NDVI) time series were reconstructed using hierarchical gap-filling and Savitzky–Golay filtering. Phenological metrics—Start of Season (SOS), End of Season (EOS), and Length of Season (LOS)—were extracted using threshold-based and derivative-based methods to ensure robust detection of seasonal transitions for shrub–grass communities. The analysis showed that Rawdat Khuraim exhibits a single-pulse phenological system driven mainly by the winter rainfall regime. Vegetation greening typically begins between late November and January, followed by senescence between March and early May, with growing seasons of 70–140 days depending on the timing and magnitude of rainfall. Cross-correlation analysis confirmed a lag of 2–8 weeks between peak rainfall and maximum NDVI response. Temperature was identified as the main limiting factor on season length, with land surface temperatures above 40 °C consistently triggering rapid senescence regardless of residual soil moisture. Climate–phenology relationships were quantified using multiple regression with precipitation from CHIRPS and temperature from the ERA5-Land reanalysis product. Early winter rainfall events and multiple rainfall pulses produced the strongest vegetation responses, whereas late or absent winter rainfall resulted in short growing seasons. Despite high interannual variability, Mann–Kendall trend analysis indicated no significant directional shifts in phenological timing, suggesting that year-to-year weather variability, rather than long-term climate trends, dominated during the study period. The multi-sensor framework successfully compensated for the limitations of individual platforms, with MODIS providing temporal continuity, Landsat contributing historical detail, and Sentinel-2 enhancing spatial resolution in recent years.12 0Item Restricted Information Integrity: From a Lens of Explainable AI With Cultural and Social Behaviors(2023-08-11) Alharbi, Raed; Thai, My TThe rapid development of Artificial intelligence (AI), such as machine learning (ML) and deep neural networks (DNNs), has changed the way information is processed and used. However, along with these advancements, challenges to information integrity have emerged. The widespread dissemination of misinformation through digital platforms, coupled with the lack of transparency in black-box ML models, has raised concerns about the reliability and trustworthiness of informa- tion to expert users (ML developers) and non-expert users (end-users). Unfortunately, employing eXplainable Artificial Intelligence (XAI) approaches on real-world applications to improve the trustworthiness of DNNs models is still far-fetched and not straightforward. Motivated by these observations, this thesis concentrates on two directions. • Misinformation Mitigation. In the first direction, we leverage XAI techniques to mitigate misinformation through three main approaches: evaluating the trustworthiness of fake news detection models from a user perspective, studying the influence of social and cultural behavior on misinformation propa- gation, and analyzing the diffusion of descriptive norms in social media networks to promote positive norms and combat misinformation. • Developing Advanced ML Models. In the second direction, we turn our attention to developing ML models from two aspects. The first aspect exploits XAI behaviors to provide a new method to simultaneously preserve the performance and explainability of student models, which in their primitive form provide little transparency. In the second aspect, we develop the Temporal graph Fake News Detec- tion Framework (T-FND), which effectively captures heterogeneous and repetitive charac- teristics of fake news behavior.36 0