The paper presents the potential of combining satellite radar data and neural networks for quasi-automatic detection of glacier grounding lines. The conducted research covered five years and was carried out in the area of the Amery Ice Shelf. It has a very complex shoreline, so its grounding-line location is uncertain. Thus, it has always been the subject of much research. The main objective of our work was to find out if Synthetic Aperture Radar data combined with a deep learning implementation would enable rapid detection of ice shelf grounding lines over large areas. For this purpose, 290 radar images from the Sentinel-1 satellite covering 46 000 km2 were used. Processed by the Differential Interferometry of Synthetic Aperture Radar four-pass method, the images formed a time-consistent series between 2017 and 2021. As a result of performed calculations, a total length of 1280 km of grounding line was determined. They were validated by comparing with other independent data sources based on manual measurements. It has been demonstrated that the combination of satellite radar data and automated data processing allows for obtaining high-precision results continuously in a very short time. Such an approach allows monitoring of grounding line position in the long term with intervals of less than one week. It enables analysis of the dynamics changes with unprecedented frequency and the identification of patterns.

Zjawiska dynamiczne – zarówno pochodzenia antropogenicznego, jak i naturalnego – występują zazwyczaj nieoczekiwanie i ujawniają się z dużą prędkością. Zmiany morfologii powierzchni terenu cechują się w takich przypadkach dużą gwałtownością, a rejony ich występowania nie podlegają najczęściej stałemu monitoringowi naziemnemu. Z tego względu kompleksowe opisanie skutków zaistnienia zjawisk tego typu – zwłaszcza po upływie pewnego czasu od ich wystąpienia – jest trudne, a często niemożliwe. J ednocześnie, dla badań nad charakterystykami jakościowymi i ilościowymi zjawisk dynamicznych, wartości i kierunki przemieszczeń powierzchni terenu będące ich wynikiem mają duże znaczenie. Zastosowanie satelitarnej interferometrii radarowej w badaniach zmian rzeźby powierzchni terenu wywołanych przez zjawiska takie jak trzęsienia ziemi jest już od pewnego czasu rutyną. N iemniej misja S entinel, która prowadzona jest przez Europejską Agencję Kosmiczną, stwarza nowe możliwości prowadzenia monitoringu na obszarach, na których wystąpiły zjawiska o charakterze dynamicznym. Autorzy postanowili sprawdzić, czy wstrząs pochodzenia górniczego generuje ruchy powierzchni terenu oraz zbadać, w jakiej odległości od epicentrum mają one miejsce oraz określić rząd wielkości ruchów tego typu. Analizy interferometryczne, które oparto na metodzie satelitarnej interferometrii różnicowej DInSAR na podstawie zobrazowań radarowych pochodzących z misji S entinel pozwoliły na uzyskanie odpowiedzi na te pytania.

The geodetic measurements optimization problem has played a crucial role in the mining areas affected by continuous ground movement. Such movements are most frequently measured with the classical geodetic methods such as levelling, tachymetry or GNSS (Global Navigation Satellite System). The measuring techniques are selected with respect to the dynamics of the studied phenomena, surface hazard degree, as well as the financial potential of the mining company. Land surface changes caused by underground exploitation are observed with some delay because of the mining and geological conditions of the deposit surroundings. This delay may be considerable in the case of salt deposits extraction due to slow convergence process, which implies ground subsidence maximum up to a few centimeters per year. Measuring of such displacements requires high precision instruments and methods. In the case of intensely developed urban areas, a high density benchmark network has to be provided. Therefore, the best solution supporting the monitoring of vertical ground displacements in the areas located above the salt deposits seems to be the Sentinel 1-A radar imaging satellite system. The main goal of the investigation was to verify if imaging radar from the Sentinel 1 mission could be applied to monitor of slow ground vertical movement above word heritage Wieliczka salt mine. The outcome of the analysis, which was based on DInSAR (Differential SAR Interferometry). technology, is the surface distribution of annual subsidence in the period of 2015-2016. The comparison of the results with levelling confirmed the high accuracy of satellite observations. What is significant, the studies allowed to identify areas with the greatest dynamics of vertical ground movements, also in the regions where classical surveying was not conducted. The investigation proved that with the use of Sentinel-1 images sub centimeters slow vertical movements could be obtained.