A novel approach for optimizing regional geoid modeling over rugged terrains based on global geopotential models and artificial intelligence algorithms

• Published in: The Egyptian journal of remote sensing and space sciences 2024-12, Vol.27 (4), p.656-668
• Main Authors: Elshewy, Mohamed A., Trung Thanh, Phung, Elsheshtawy, Amr M., Refaat, Mervat, Freeshah, Mohamed
• Format: Article
• Language: English
• Subjects: Artificial Intelligence (AI); Geoid modeling; Global Geopotential Models (GGMs); GNSS/leveling; Machine Learning (ML)
• ISSN: 1110-9823
• DOI: 10.1016/j.ejrs.2024.09.002

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.