| Date: | 2020-12-11 12:44:02 | |
| Sender: | Benedikt Soja <soja@ethz.ch> | |
| Subject: | [SLR-Mail] No.2684: vEGU2021 session on machine learning and data science in geodesy | |
| Author: | unknown | |
| Content: | Dear colleagues, We would like to introduce you to a new session at the EGU General Assembly 2021: *G1.4 Data science and machine learning in geodesy* Please find the detailed description below. vEGU2021 will be held virtually from April 19-30, 2021, based on a new vPICO session format. We would be happy if you would consider submitting an abstract to our session. The abstract submission deadline is January 13, 2021, 13:00 CET. If you have any questions about our session, please feel free to contact us. Useful links: vEGU2021 website: www.egu2021.eu vEGU2021 format: https://egu21.eu/about/provisional_format_of_egu21.html Session details: https://meetingorganizer.copernicus.org/EGU21/session/39912 Abstract submission: https://meetingorganizer.copernicus.org/EGU21/abstractsubmission/39912 We are looking forward to your contributions and apologize for cross-posting. Best wishes, Benedikt Soja, Kyriakos Balidakis, Maria Kaselimi, Ryan McGranaghan, Randa Natras --------------------------------------------------------------------- Session description G1.4 Data science and machine learning in geodesy This session aims to showcase novel applications of data science and machine learning methods in geodesy. In recent years, the amount of data from geodetic observation techniques has increased dramatically. Innovative approaches are required to efficiently handle and harness the vast amount of geodetic data available nowadays for scientific purposes. In particular, Global Navigation Satellite System (GNSS) and Interferometric Synthetic Aperture Radar (InSAR) are facing challenges, but also opportunities, related to the expansive data collection (big data). Similarly, numerical weather models and other geophysical models important for geodesy come with ever growing resolutions and dimensions. Strategies and methodologies from the fields of data science and machine learning have shown great potential not only in this context, but also when applied to more limited data sets to solve complex non-linear problems in geodesy. We invite contributions related to various aspects of applying methods from data science and machine learning (including both shallow and deep learning techniques) to geodetic problems and data sets. We welcome investigations related to (but not limited to): more efficient and automated processing of geodetic data, pattern and anomaly detection in geodetic time series, images or higher-dimensional data sets, improved predictions of geodetic parameters into the future, combination and extraction of information from multiple inhomogeneous data sets (multi-temporal, multi-sensor, multi-modal fusion), feature selection, super-sampling of geodetic data, and improvements of large-scale simulations. Especially encouraged are contributions that discuss the uncertainty quantification and interpretability of results from machine learning algorithms, as well as the integration of physical modeling into data-driven frameworks. -- Prof. Dr. Benedikt Soja Space Geodesy, ETH Zurich Robert-Gnehm-Weg 15, 8093 Zurich, Switzerland Phone: +41 44 633 73 40, room HPV G54 soja@ethz.ch Dear colleagues, We would like to introduce you to a new session at the EGU General Assembly 2021: G1.4 Data science and machine learning in geodesy Please find the detailed description below. vEGU2021 will be held virtually from April 19-30, 2021, based on a new vPICO session format. We would be happy if you would consider submitting an abstract to our session. The abstract submission deadline is January 13, 2021, 13:00 CET. If you have any questions about our session, please feel free to contact us. Useful links: vEGU2021 website: www.egu2021.eu vEGU2021 format: Session details: Abstract submission: We are looking forward to your contributions and apologize for cross-posting. Best wishes, Benedikt Soja, Kyriakos Balidakis, Maria Kaselimi, Ryan McGranaghan, Randa Natras New";mso-fareast-font-family:"Times New Roman"”> New";mso-fareast-font-family:"Times New Roman"”> New";mso-fareast-font-family:"Times New Roman"”>--------------------------------------------------------------------- Session description G1.4 Data science and machine learning in geodesy This session aims to showcase novel applications of data science and machine learning methods in geodesy. In recent years, the amount of data from geodetic observation techniques has increased dramatically. Innovative approaches are required to efficiently handle and harness the vast amount of geodetic data available nowadays for scientific purposes. In particular, Global Navigation Satellite System (GNSS) and Interferometric Synthetic Aperture Radar (InSAR) are facing challenges, but also opportunities, related to the expansive data collection (big data). Similarly, numerical weather models and other geophysical models important for geodesy come with ever growing resolutions and dimensions. Strategies and methodologies from the fields of data science and machine learning have shown great potential not only in this context, but also when applied to more limited data sets to solve complex non-linear problems in geodesy. We invite contributions related to various aspects of applying methods from data science and machine learning (including both shallow and deep learning techniques) to geodetic problems and data sets. We welcome investigations related to (but not limited to): more efficient and automated processing of geodetic data, pattern and anomaly detection in geodetic time series, images or higher-dimensional data sets, improved predictions of geodetic parameters into the future, combination and extraction of information from multiple inhomogeneous data sets (multi-temporal, multi-sensor, multi-modal fusion), feature selection, super-sampling of geodetic data, and improvements of large-scale simulations. Especially encouraged are contributions that discuss the uncertainty quantification and interpretability of results from machine learning algorithms, as well as the integration of physical modeling into data-driven frameworks. -- |