Mostafa Kiani Shahvandi

ETH Zurich | ETH Zürich · Department of Civil, Environmental and Geomatic Engineering

Rapid provision of Earth Orientation Parameters (EOPs, here polar motion and dUT1) is indispensable in many geodetic applications and also for spacecraft navigation. There are, however, discrepancies between the rapid EOPs and the final EOPs that have a higher latency, but the highest accuracy. To reduce these discrepancies, we focus on a data‐driv...

The International GNSS Service analysis centers provide orbit products of GPS satellites with weekly, daily, and sub-daily latency. The most frequent ultra-rapid products, which include one day of orbits derived from observations and one day of orbit prediction, are vital for real-time applications. However, the predicted part of the ultra-rapid or...

Earth orientation parameters (EOPs) are essential in geodesy, linking the terrestrial and celestial reference frames. Due to the time needed for data processing and combining different space geodetic techniques, EOPs of the highest quality suffer latencies from several days to several weeks. However, real-time EOPs are needed for multiple geodetic...

Rapid provision of Earth Orientation Parameters (EOPs, here polar motion and dUT1) is indispensable in many geodetic applications and also for spacecraft navigation. There are, however, discrepancies between the rapid EOPs and the final EOPs that have a higher latency, but the highest accuracy. To reduce these discrepancies, we focus on a data-driv...

Earth orientation parameters (EOP) are needed for precise navigation on Earth and in space and to connect the terrestrial to the celestial reference frame, and for several real-time applications. EOP are typically determined from the observations of different space-geodetic techniques. In order to overcome latencies in the processing and combinatio...

Determination of Earth Orientation Parameters (EOP) with utmost accuracy requires the combination of various data sources from different space geodetic techniques, some of which requiring long processing time. This results in a latency of up to several weeks by which the so-called final EOP are released. Since some of the important applications, in...

This paper introduces a new learning algorithm for accurate, physically driven time series prediction. The fundamental assumption behind the method is that the phenomena follow Ordinary Differential Equations. We investigate the general case where the time series follows an ODE of degree m∈N $m\in \mathbb{N}$. The resulting method is a learning alg...

Data uncertainty plays an important role in the field of geodesy. Even though deep learning is becoming increasingly important for geodetic applications due to its high accuracy, it typically does not consider the data uncertainty. As we demonstrate in this study, we propose to include the uncertainty of data in deep neural network architectures to...

Precise orbit determination is vital for the increasingly vast number of space objects around the Earth. Moreover, accurate orbit prediction of GNSS satellites is essential for many real-time geodetic applications, including real-time navigation. The typical way to obtain accurate orbit predictions is using physics-based orbit propagators. However,...

Geodetic measurements allow the determination of a wide variety of parameters describing the Earth system, including its shape, gravity field, and orientation in space. The importance of such parameters to science and society is manifested through geodetic contributions to the examination of geodynamic phenomena, climate change monitoring and navig...

Nowadays, many applications such as Global Navigation Satellite Systems (GNSS) or spacecraft tracking require a rapid determination, or even predictions, of the Earth Orientation Parameters (EOP). However, due to the measurement techniques utilized to estimate EOP, the latency can be considerably longer than required, which especially hinders real-...

In case only a limited amount of data is available, deep learning models often do not generalize well. We propose a novel deep learning architecture to deal with this problem and achieve high prediction accuracy. To this end, we combine four different concepts: greedy layer-wise pretraining, attention via performers, residual connections, and LSTM...

Data uncertainty plays an important role in the field of geodesy. We propose to include the uncertainty of data in deep neural network architectures to achieve better generalization, even in small data sets. Inspired by weighted and total least squares, we formulate the problem for both input and target uncertainties, and combine it with the Bayesi...

The Earth Orientation Parameters (EOP) are fundamentals of geodesy, connecting the terrestrial and celestial reference frames. The typical way to generate EOP of highest accuracy is combining different space geodetic techniques. Due to the time demand for processing data and combining different techniques, the combined EOP products often have laten...

Graph neural networks are a newly established category of machine learning algorithms dealing with relational data. They can be used for the analysis of both spatial and/or temporal data. They are capable of modeling how time series of nodes, which are located at different spatial positions, change by the exchange of information between nodes and t...

In this paper a new method of image smoothing and its applications in the field of remote sensing are presented. This method is based on the minimization of the iterated Laplace operator of an arbitrary degree in the Cartesian coordinate system. Using the method of finite differences, a linear combination is derived, which represents the solution o...

In this paper, two applications of numerical integration in geodesy and geophysics are presented. In the first application, the Molodenskij truncation coefficients for the Abel-Poisson kernel are computed using eleven different numerical integration procedures, namely two-, three-, four-, and five-point Gaussian, Gauss–Kronrod, trapezoidal rule, Si...

This paper is aimed at introducing the concept of Spherical Interpolating Moving Least Squares to the problems in geodesy and geophysics. Based on two previously known methods, namely Spherical Moving Least Squares and Interpolating Moving Least Squares, a simple theory is formulated for using Spherical Moving Least Squares as an interpolant. As an...

This paper is aimed at introducing the concept of Spherical Interpolating Moving Least Squares to the problems in geodesy and geophysics. Based on two previously known methods, namely Spherical Moving Least Squares and Interpolating Moving Least Squares, a simple theory is formulated for using Spherical Moving Least Squares as an interpolant. As an...

In this paper, Sentinel-2 satellite imagery is used for the classification of different soil types using the method of deep convolutional neural networks. Role of the presence of different phenomena in the image, including clouds, on the accuracy of the classification is analyzed. Two case studies are presented for Iran. In the first study, a regio...

This paper is concerned with the spline interpolation problem in ellipsoidal geometry for a set of point functionals. Spline functions are defined based on the minimization of the norm of the Beltrami and Laplace operators for all functions belonging to an appropriate semi-Hilbert space. The semi-Hilbert space is a Reproducing Kernel Hilbert Space...

In this paper, a method is proposed for producing gravity acceleration at sea surface in the Persian Gulf. This method is based on the Geoid height from satellite altimetry, high resolution Geopotential models, and ellipsoidal splines. First, the definition of the ellipsoidal spline functions is presented in a Hilbert space, which is consisted of i...

We focus on a study in which crops in the hyperspectral imagery are classified using very deep convolutional neural networks. A case study is presented for the 125-band hyperspectral imagery of Stennis Space Center. It is shown that besides other phenomena in the image, the main crop texture of the image is identified and classified. The overall ac...

The aim of this paper is to study the spline interpolation problem in spheroidal geometry. We follow the minimization of the norm of the iterated Beltrami-Laplace and consecutive iterated Helmholtz operators for all functions belonging to an appropriate Hilbert space defined on the spheroid. By exploiting surface Green’s functions, reproducing kern...

در این مقاله، روش درونیابی برای تولید دادههای شتاب ثقل در سطح دریا در خلیج فارس با استفاده از ژئوئید حاصل از ارتفاع سنجی ماهواره ای، مدلهای ژئوپتانسیل با قدرت تفکیک بالا و اسپلاین بیضوی ارائه میگردد. ابتدا به تعریف توابع اسپلاین بیضوی در یک فضای هیلبرت متشکّل از تمامی توابع بینهایت بار مشتقپذیر پرداخته شده است. جهت تعریف توابع اسپلاین، نرم عملگرهای...

The aim of this paper is to study the theory of spline interpolation and smoothing problems on the surface of a triaxial ellipsoid for the Consecutive Iterated Helmholtz operator and a set of linearly independent evaluation functionals. Spline functions were introduced based on the minimization of a semi-norm in the context of a semi-Hilbert space...

The objectives of this paper are twofold: (1) to present a new method of approximation such that the function and some of its derivatives are simultaneously approximated; and (2) to investigate the potential applications of this new method in the field of satellite geodesy by deriving a numerical solver of ordinary differential equations. To fulfil...

Earthquake prediction is one of the most pursued problems in geoscience. Different geological and seismological approaches exist for the prediction of the earthquake and its subsequent land change. However, in many cases, they fail in their mission. In this paper, we address the well-established earthquake prediction problem by a novel approach. We...

We present a simple yet efficient supervised machine learning algorithm that is designed for the GNSS position time series prediction. This algorithm has four steps. First, the mean value of the time series is subtracted from it. Second, the trends in the time series are removed. Third, wavelets are used to separate the high and low frequencies. An...

We investigate the accuracy of conventional machine learning aided algorithms for the prediction of lateral land movement in an area using the precise position time series of permanent GNSS stations. The machine learning algorithms that are used are tantamount to the ones used in [1], except for the radial basis functions, i.e. multilayer perceptro...

This paper is aimed at the problem of predicting the land subsidence or upheave in an area, using GNSS position time series. Since machine learning algorithms have presented themselves as strong prediction tools in different fields of science, we employ them to predict the next values of the GNSS position time series. For this reason, we present an...

In this paper, the generalized regression neural network is used to predict the GNSS position time series. Using the IGS 24-hour final solution data for Bad Hamburg permanent GNSS station in Germany, it is shown that the larger the training of the network, the higher the accuracy is, regardless of the time span of the time series. In order to analy...

The present paper is focused on the comparison of the efficiency of two important meshless interpolants for gravity acceleration interpolation. Compactly-supported spherical radial basis functions and interpolating moving least squares are used to interpolate actual gravity accelerations in southern Africa. Interpolated values are compared with act...

In this paper a new method of image smoothing for satellite imagery and its applications in environmental remote sensing are presented. This method is based on the global gradient minimization over the whole image. With respect to the image discrete identity, the continuous minimization problem is discretized. Using the finite difference numerical...

This paper is focused on deriving an optimal image smoother. The optimization is done through the minimization of the norm of the Laplace operator in the image coordinate system. Discretizing the Laplace operator and using the method of Euler-Lagrange result in a weighted average scheme for the optimal smoother. Satellite imagery can be smoothed by...

In this paper a new Geophysical gravimetry approach is presented, which is based on satellite imagery in remote sensing. The method uses a satellite image, together with a set of points in the image the gravity values of which are known. Template-based spheroidal spline method of interpolation is used to constitute a system of equations to find the...

In this paper a new method of numerically solving ordinary differential equations is presented. This method is based on the Gaussian numerical integration of different orders. Using two different orders for numerical integration, an adaptive method is derived. Any other numerical solver for ordinary differential equations can be used alongside this...

We investigate the efficiency of the generalized neural networks for the prediction of earthquakes. We particularly focus on the Tohoku 2011 earthquake. Using this machine learning method, we focus on the prediction performance assessment, using the different criteria.

The main focus of this paper is on the application of Tchebycheff rational approximation in the field of Geodesy and Geophysics. The problem considered here is the approximation of Stokes' kernel. The mathematical formulae for the rational approximant are derived. A comparsion between the rational approximant and spline method is also presented.

This paper is aimed at the derivation of a discrete data smoothing function for the discrete Dirichlet condition in a regular grid on the surface of a spheroid. The method employed here is the local L2−semi-norm minimization, through Euler-Lagrange method, for the Beltrami operator. The method results in a weighted average of the surrounding points...

In this paper an introduction of the moving least squares approach is presented in the context of data approximation and interpolation problems in Geodesy. An application of this method is presented for geoid height approximation and interpolation using different polynomial basis functions for the approximant and interpolant, respectively, in a reg...

The success of the deep learning methods in the prediction of different types of time series is becoming increasingly evident. We use these models to predict sea level change from the SAR altimetry data time series. We use LSTM and deep Bayesian neural networks. Large datasets are used, which contain the global sea level values at different times....

A study of the state-of-the-art machine learning algorithms is presented for different GNSS time series across the globe. Using different criteria, the performance of the methods are checked against each other.

We discuss the application of Finslerian metrics in geodesy and geophysics. Currently, all the applications in the field of geoscience are based on the Euclidean metrics, which may not represent the full information in a given problem. We present the application of Finslerian metrics in the modeling of satellite dynamics in the orbit, together with...

The aim of this paper is to study the theory and applications of spline interpolation and smoothing problems on the surface of a triaxial ellipsoid for a specific operator, namely Consecutive Iterated Helmholtz, and a set of linearly independent evaluation functionals. Spline functions are introduced based on the minimization of a semi-norm in the...