Egyptian Journal of Remote Sensing and Space Sciences最新文献

Accurate geoid modeling is significant in geodetic, geological, and environmental sciences. Owing to challenges in establishing reference stations, particularly in rugged terrains, such as in Northern Vietnam, leveraging global geopotential models (GGMs) is imperative. Herein, we proposed a superior method that integrates GGMs with advanced artificial intelligence (AI) algorithms to enhance the accuracy and spatial resolution of regional geoid models. A total of six contemporary GGMs (XGM2019e_2159, SGG-UGM-2, SGG-UGM-1, GECO, EIGEN-6C4, and EGM2008) were systematically evaluated to identify the optimal GGM that represents the Earth’s gravitational field in Northern Vietnam. Subsequently, sophisticated AI algorithms, including tree-based ensembles, support vector machines, Gaussian linear regression, regression trees, and linear regression models, were implemented. These AI algorithms were trained on the integrated global navigation satellite system (GNSS) leveling data and corresponding height anomalies to capture complex relationships in the geopotential field. Among the six investigated GGMs, XGM2019e_2159 shows optimal performance for Northern Vietnam, displaying a standard deviation of ±0.17 m. Rigorous assessment results from cross-validation and validation against independent datasets demonstrate satisfactory accuracy across all considered models. However, the Gaussian process regression model with an exponential kernel exhibits marginal superiority, boasting a standard deviation of approximately 0.07 m. This model is therefore chosen for the construction of the geoid model by integrating ground data with optimal GGMs, which shows superior performance, particularly in challenging topographic and geophysical conditions, thereby contributing to a marked improvement in the realized spatial resolution.

Despite comprising only one per cent of global forests, mangroves provide vital ecological and economic benefits to their ecosystems. Due to its decreasing extent over the past decade, there is a rise in research innovations supporting mangrove conservation. Specifically, consumer-grade Unmanned Aerial Vehicles (UAV) were proven effective as potential remote sensing alternatives to support mangrove research and monitoring in recent studies. As most studies use custom UAV-mounted sensors for mangrove species classification, similar studies using a UAV’s default red–green–blue (RGB) cameras were scarce. This study explores the potential of high-resolution RGB aerial images through state-of-the-art object detection algorithm, YOLOv5 to detect the dominant Rhizophora mangroves in Sarawak, Malaysia. A total of 400 RGB images were equally selected from two study areas and allocated into three datasets, two corresponding to each study area and one combining all images. The annotation process was performed using a previously proposed novel method, assisted by YOLOv5 for a semi-automated annotation process with expert verification. Systematic training experiments were conducted to select an optimal epoch size across models trained with each dataset. The final models produced an average true positive rate of 73.8% and 71.7% for each study site, while the combined dataset model produced an average true positive rate of 73.7%. Overall, this study demonstrated the potential of UAV-based RGB images and deep learning object detection architectures to identify specific mangrove objects, while also highlighting key considerations for similar future research.