Szczegóły publikacji
Opis bibliograficzny
Training dataset for the machine learning approach in glacier monitoring applying SAR data / Łukasz Piwowar, Magdalena ŁUCKA, Wojciech WITKOWSKI // W: IGARSS 2023 [Dokument elektroniczny] : IEEE International Geoscience and Remote Sensing Symposium : 16–21 July 2023, Pasadena, USA. — Wersja do Windows. — Dane tekstowe. — [Piscataway] : IEEE, cop. 2023. — Dod. ISBN: 979-8-3503-2010-7. — e-ISBN: 979-8-3503-2009-1. — S. 191–194. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 194, Abstr.
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 148345 |
|---|---|
| Data dodania do BaDAP | 2023-09-18 |
| Tekst źródłowy | URL |
| DOI | 10.1109/IGARSS52108.2023.10281675 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | IEEE International Geoscience and Remote Sensing Symposium 2023 |
Abstract
The study analysed the possibility of utilizing machine learning to determine glacier displacements. The obtained results were compared with the offset-tracking method available in SNAP software. The Jakobshavn glacier in Greenland served as the test site. Analyses were carried out using Sentinel-1 data during the period of August 1 to August 7, 2021. To generate a dataset for the selected part of the glacier, a synthetic training dataset comprising 4,500 samples was created. It was constructed by applying rotation in the range of ±30º and resizing within the range of ±10-20 pixels to the original patch. The final neural network (NN) consisted of 7 layers. The maximum displacement value is 250 m, corresponding to a velocity of 41 m/day. Notably, these maximum values are consistent with the results from offset-tracking. Nevertheless, the results in the slowly moving areas are not reliable because of the coarse resolution of the NN output.
