Application of neural network technique to determine a corrector surface for global geopotential model using GPS/levelling measurements in Egypt

Abstract

Owing to the appearance of many global geopotential models, it is necessary to determine the most appropriate model for use in Egyptian territory. In this study, we aim to investigate three global models, namely EGM2008, EIGEN-6c4, and GECO. We use five mathematical transformation techniques, i.e., polynomial expression, exponential regression, least-squares collocation, multilayer feed forward neural network, and radial basis neural networks to make the conversion from regional geometrical geoid to global geoid models and vice versa. From a statistical comparison study based on quality indexes between previous transformation techniques, we confirm that the multilayer feed forward neural network with two neurons is the most accurate of the examined transformation technique, and based on the mean tide condition, EGM2008 represents the most suitable global geopotential model for use in Egyptian territory to date. The final product gained from this study was the corrector surface that was used to facilitate the transformation process between regional geometrical geoid model and the global geoid model.

A crossvalidation-based comparison of kriging and IDW in local GNSS/levelling quasigeoid modelling

“…Through the years many interpolation methods have been involved in generating conversion surfaces (in local and regional scales) enabling transition between geometric and physical heights, e.g., polynomial regression (Borowski and Banaś, 2019;Gucek and Bašić, 2009;Kim et al, 2018;Zhong, 1997), neural networks (Aky-ilmaz et al, 2009;Kaloop et al, 2021), geographically weighted regression (Dawod and Abdel-Aziz, 2020), kriging (Ligas and Szombara, 2018;Orejuela et al, 2021), least-squares collocation (LSC) (You, 2006), Inverse Distance Weighting (IDW) (Radanović and Bašić, 2018) to mention only a few. Very often, conversion surfaces take the form of corrector surfaces due to the use of global geopotential models or gravimetric models generated prior to eliminating inconsistencies by fitting to GNSS/levelling data (Elshambaky, 2018;You, 2006).…”

Research on Creating Local Geoid Models for the Coastal Territories of Egypt

“…2. Elshambaky подтвердил, что многослойная нейронная сеть с прямой связью с двумя нейронами является наиболее точной из исследованных методик преобразования [6]. Albayrak сообщил, что модель геоида, идентифицированная с помощью ИНС, кажется более надежной по сравнению с моделью, рассчитанной с использованием традиционных методов интерполяции [7].…”

Integration of Artificial Neural Network and the Optimal GNSS Satellites’ Configuration for Improving GNSS Positioning Techniques (A Case Study in Egypt)

“…Besides, Mohammed et al (2015), Wang et al (2016), Kim and Kim (2015), and Barrile et al (2016) applied ANN to predict GPS positioning, GPS satellite clock bias, IGS real time service corrections, and displacement in tectonically active areas, respectively. Furthermore, it has been used for geodetic coordinates' transformation (Elshambaky et al 2018, Ziggah et al 2016b), a corrector surface determination for global geopotential model (Elshambaky 2018), planimetric coordinates' transformation (Ziggah et al 2016a), and Geometrical Dilution of Precision (GDOP) approximation for improving GPS accuracy , Azami et al 2012, Chien-Sheng and Szu-Lin 2010, Jwo and Lai 2006, Azami and Sanei 2013, Azarbad et al 2014, Azami et al 2016. The general insight gathered from these previous works indicate that ANN is suitable for numerous geodetic applications.…”