Login
- Original title:
- Interpretation of Structures in Polar Regions with Deep Learning Methods
- Translated title:
- Interpretation von Strukturen in Polarregionen mithilfe von Deep Learning Methoden
- Author:
- Heidler, Konrad Marten Harald
- Year:
- 2024
- Document type:
- Dissertation
- Faculty/School:
- TUM School of Engineering and Design
- Institution:
- Data Science in Earth Observation (Prof. Zhu)
- Advisor:
- Zhu, Xiaoxiang (Prof. Dr. habil.)
- Referee:
- Zhu, Xiaoxiang (Prof. Dr. habil.); Bamler, Richard Hans Georg (Prof. Dr. habil.); Lefèvre, Sébastien (Prof. Dr.)
- Language:
- en
- Subject group:
- GEO Geowissenschaften
- TUM classification:
- BAU 967; MSR 915
- Abstract:
- Global climate change is rapidly changing the polar regions. In an effort to support monitoring these changes, this thesis develops deep learning methods for the remote sensing analysis of targets in these regions. Firstly, models for mapping glacier calving fronts are developed by rethinking how the task is encoded computationally. Secondly, the feasibility of detecting retrogressive thaw slumps in permafrost areas is established and made data-efficient through semi-supervised learning.
- Translated abstract:
- Der globale Klimawandel hat massive Auswirkungen auf die Polarregionen. Diese Dissertation entwickelt Deep Learning Methoden für die Fernerkundung bestimmter Objekte in diesen Regionen. Zuerst werden Modelle für die Kartierung von Gletscherkalbungsfronten entwickelt, indem neue Ansätze für deren Kodierung verfolgt werden. Weiterhin werden Modelle für die Detektion von Retrogressiven Taurutschungen in Permafrostregionen mithilfe von Trainingstechniken wie Semi-Supervised Learning optimiert.
- WWW:
- https://mediatum.ub.tum.de/?id=1731924
- Date of submission:
- 22.01.2024
- Oral examination:
- 06.06.2024
- File size:
- 73620508 bytes
- Pages:
- 177
- Urn (citeable URL):
- https://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:91-diss-20240606-1731924-1-2
- Last change:
- 12.07.2024
BibTeX