Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.9
5.0
Journals
Remote Sensing
Special Issues
Signal Processing and Machine Learning for Space Geodesy Applications
remotesensing-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Remote Sensing Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Signal Processing and Machine Learning for Space Geodesy Applications

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Engineering Remote Sensing".

Deadline for manuscript submissions: 30 September 2024 | Viewed by 3765

Special Issue Editors

Dr. Maria Kaselimi

E-Mail Website
Guest Editor
School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15773 Athens, Greece
Interests: machine learning; deep learning; time series and signal processing; satellite geodesy; geoinformatics
Prof. Dr. Benedikt Soja

E-Mail Website
Guest Editor
Department of Civil, Environmental and Geomatic Engineering, ETH Zurich, 8093 Zurich, Switzerland
Interests: geodetic data analysis and parameter estimation; GNSS; very long baseline interferometry; machine learning; determination of atmospheric parameters; geodetic reference frames
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Mattia Crespi

E-Mail Website
Guest Editor
Geodesy and Geomatics Division-DICEA, Sapienza University of Rome, Rome, Italy
Interests: remote sensing big data analysis; optical and SAR satellite remote sensing; photogrammetry and stereo-SAR; 3D terrain and object modeling; GNSS positioning and monitoring; GNSS seismology; GNSS meteorology
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The field of geodesy has seen a significant increase in observational data in recent years, particularly from Global Navigation Satellite Systems (GNSSs), Very-Long-Baseline Interferometry (VLBI), Satellite Laser Ranging (SLR), Interferometric Synthetic Aperture Radar (InSAR), Doppler Orbitography and Radio-positioning Integrated by Satellite (DORIS), satellite altimetry and gravimetry, etc.. The rapid development of satellite techniques and the establishment of ground/space-based observing systems contribute to the maintenance of the terrestrial reference frame, the monitoring of Earth’s rotation and gravity field, navigation and positioning with high precision, detection of deformation in GNSS time series related to geodynamics, as well as remote sensing and modeling of the Earth’s atmosphere, including the ionosphere. Rapidly increasing volumes of diverse data from distributed sources create new challenges for extracting valuable knowledge from these data and attract increasing attention to solve complex geodetic problems.

Machine learning in space geodesy has the potential to facilitate the automation of geodetic data processing, spatiotemporal pattern modelling, anomaly detection in time-dependent geophysical signals, and the prediction of parameters into the future (e.g., Earth orientation parameters). Special emphasis will be placed on innovative approaches for harnessing geodetic “big data” using deep learning algorithms in space geodesy applications. We encourage contributions dealing with the rich family of deep learning methods, that encompasses neural networks, hierarchical probabilistic models, as well as unsupervised and supervised learning algorithms. Furthermore, we specifically invite contributions that address the trustworthy aspects of machine learning,  which will help with the wide adoption of machine learning by the geodetic scientific community. Challenges related to the quantification of uncertainties, interpretability and explainability of results, as well as the integration of physics-informed models and geometric deep learning algorithms are additional topics of interest.

Dr. Maria Kaselimi
Prof. Dr. Benedikt Soja
Prof. Dr. Mattia Crespi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • space geodesy
  • GNSS
  • machine learning
  • deep learning
  • spatio-temporal data modelling

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 1644 KiB  
Article
Modeling the Differences between Ultra-Rapid and Final Orbit Products of GPS Satellites Using Machine-Learning Approaches
by Junyang Gou, Christine Rösch, Endrit Shehaj, Kangkang Chen, Mostafa Kiani Shahvandi, Benedikt Soja and Markus Rothacher
Remote Sens. 2023, 15(23), 5585; https://doi.org/10.3390/rs15235585 - 30 Nov 2023
Viewed by 937
Abstract
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 24 h of orbits derived from observations and 24 h of orbit predictions, are vital for real-time applications. [...] Read more.
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 24 h of orbits derived from observations and 24 h of orbit predictions, are vital for real-time applications. However, the predicted part of the ultra-rapid orbits is less accurate than the estimated part and has deviations of several decimeters with respect to the final products. In this study, we investigate the potential of applying machine-learning (ML) and deep-learning (DL) algorithms to further enhance physics-based orbit predictions. We employed multiple ML/DL algorithms and comprehensively compared the performances of different models. Since the prediction errors of the physics-based propagators accumulate with time and have sequential characteristics, specific sequential modeling algorithms, such as Long Short-Term Memory (LSTM), show superiority. Our approach shows promising results with average improvements of 47% in 3D RMS within the 24-hour prediction interval of the ultra-rapid products. In the end, we applied the orbit predictions improved by LSTM to kinematic precise point positioning and demonstrated the benefits of LSTM-improved orbit predictions for positioning applications. The accuracy of the station coordinates estimated based on these products is improved by 16% on average compared to those using ultra-rapid orbit predictions. Full article
(This article belongs to the Special Issue Signal Processing and Machine Learning for Space Geodesy Applications)
►▼ Show Figures

Figure 1

19 pages, 9392 KiB  
Article
Ensemble Learning for Blending Gridded Satellite and Gauge-Measured Precipitation Data
by Georgia Papacharalampous, Hristos Tyralis, Nikolaos Doulamis and Anastasios Doulamis
Remote Sens. 2023, 15(20), 4912; https://doi.org/10.3390/rs15204912 - 11 Oct 2023
Cited by 2 | Viewed by 1394
Abstract
Regression algorithms are regularly used for improving the accuracy of satellite precipitation products. In this context, satellite precipitation and topography data are the predictor variables, and gauged-measured precipitation data are the dependent variables. Alongside this, it is increasingly recognised in many fields that [...] Read more.
Regression algorithms are regularly used for improving the accuracy of satellite precipitation products. In this context, satellite precipitation and topography data are the predictor variables, and gauged-measured precipitation data are the dependent variables. Alongside this, it is increasingly recognised in many fields that combinations of algorithms through ensemble learning can lead to substantial predictive performance improvements. Still, a sufficient number of ensemble learners for improving the accuracy of satellite precipitation products and their large-scale comparison are currently missing from the literature. In this study, we work towards filling in this specific gap by proposing 11 new ensemble learners in the field and by extensively comparing them. We apply the ensemble learners to monthly data from the PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and IMERG (Integrated Multi-satellitE Retrievals for GPM) gridded datasets that span over a 15-year period and over the entire contiguous United States (CONUS). We also use gauge-measured precipitation data from the Global Historical Climatology Network monthly database, version 2 (GHCNm). The ensemble learners combine the predictions of six machine learning regression algorithms (base learners), namely the multivariate adaptive regression splines (MARS), multivariate adaptive polynomial splines (poly-MARS), random forests (RF), gradient boosting machines (GBM), extreme gradient boosting (XGBoost) and Bayesian regularized neural networks (BRNN), and each of them is based on a different combiner. The combiners include the equal-weight combiner, the median combiner, two best learners and seven variants of a sophisticated stacking method. The latter stacks a regression algorithm on top of the base learners to combine their independent predictions. Its seven variants are defined by seven different regression algorithms, specifically the linear regression (LR) algorithm and the six algorithms also used as base learners. The results suggest that sophisticated stacking performs significantly better than the base learners, especially when applied using the LR algorithm. It also beats the simpler combination methods. Full article
(This article belongs to the Special Issue Signal Processing and Machine Learning for Space Geodesy Applications)
►▼ Show Figures

Figure 1

13 pages, 4195 KiB  
Article
Toward Real-Time GNSS Single-Frequency Precise Point Positioning Using Ionospheric Corrections
by Vlad Landa and Yuval Reuveni
Remote Sens. 2023, 15(13), 3333; https://doi.org/10.3390/rs15133333 - 29 Jun 2023
Viewed by 825
Abstract
Real−time single−frequency precise point positioning (PPP) is a promising low−cost technique for achieving high−precision navigation with sub−meter or centimeter−level accuracy. However, its effectiveness depends heavily on the availability and quality of the real−time ionospheric state estimations required for correcting the delay in global [...] Read more.
Real−time single−frequency precise point positioning (PPP) is a promising low−cost technique for achieving high−precision navigation with sub−meter or centimeter−level accuracy. However, its effectiveness depends heavily on the availability and quality of the real−time ionospheric state estimations required for correcting the delay in global navigation satellite system (GNSS) signals. In this study, the dynamic mode decomposition (DMD) model is used with global ionospheric vertical total electron content (vTEC) RMS maps to construct 24 h global ionospheric vTEC RMS map forecasts. These forecasts are assimilated with C1P forecast products, and L1 single−frequency positioning solutions are compared with different ionospheric correction models. The study examines the impact of assimilating predicted RMS data and evaluates the presented approach’s practicality in utilizing the IGRG product. The results show that the IGSG RMS prediction−based model improves positioning accuracy up to five hours ahead and achieves comparable results to other models, making it a promising technique for obtaining high−precision navigation. Full article
(This article belongs to the Special Issue Signal Processing and Machine Learning for Space Geodesy Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop