Latest Posts

07/11/2023
Event

Annual workshop of the doctoral programme M3OCCA in Obergurgl

The annual workshop of the International Doctoral College M3OCCA took place this year in September at the University Centre in Obergurgel. The doctoral students presented the current status of their research projects and gave an outlook on upcoming activities. In addition to the report colloquium and organisational discussions, there were topic-specific guest lectures by Prof. Dr. Francisco Navarro (UPM, Madrid), Prof. Dr. Helmut Rott (Uni. Innsbruck & ENVEO), and Dr. Wolfgang Gurgiser (Uni. Innsbruck). The workshop was followed by a two-day excursion to the Vernagtferner. Dr Christoph Mayer from the Bavarian Academy of Science explained to the participants the diverse glacier monitoring programme, which has been carried out for more than 50 years.

08/07/2023
Event

M3OCCA PhD candidates visited DLR in Oberpfaffenhofen

Members of the M3OCCA project visited the facilities of DLR in Oberpfaffenhofen on the 5th. July 2023.

During the visit, the project partners and M3OCCA members gave an overview of the activities at DLR including a guided tour of the Techlab.

Impressive was in particular the visit of the German Space Operations Centre (GSOC), where different space missions and the Columbus Module of the International Space Station are monitored and controlled.

08/07/2023
Allgemein Publications

Caffe – A Benchmark Dataset for Glacier Calving Front Extraction from Synthetic Aperture Radar Imagery

The study emphasizes the importance of understanding marine-terminating glacier dynamics in glacier projections. Deep learning methods can automate the extraction of calving front positions from satellite imagery, reducing manual effort. The “CaFFe” dataset, which includes annotated calving fronts in Synthetic Aperture Radar (SAR) imagery, offers a standardized benchmark for evaluating deep learning techniques in this area. Researchers can use CaFFe to assess the performance of upcoming deep learning models and identify promising research directions. A leaderboard of models can be found at https://paperswithcode.com/sota/calving-front-delineation-in-synthetic.

https://ieeexplore.ieee.org/abstract/document/10283406

08/07/2023
Publications

Conditional Random Fields for Improving Deep Learning-Based Glacier Calving Front Delineations

Advancements in Deep Learning have enabled the automated identification of glacier calving fronts in satellite imagery. This study improves the accuracy of this process by incorporating a Conditional Random Field (CRF) into the post-processing of the neural network’s predictions. Experiments using the CaFFe dataset showed a 27-meter improvement in mean distance error. The code is available at https://github.com/EntChanelt/GlacierCRF.

https://ieeexplore.ieee.org/document/10282915

05/07/2023
Event

Invited talk by Susanne Støle-Hentschel 31.07.2023

Title: How can we understand the dynamics of ocean waves from measurements and simulations?

The presentation introduces some of the core techniques used for measuring ocean waves and outlines why it is difficult to interpret those measurements.
The main focus of the talk will be dedicated to explaining the imaging mechanism of X-band radars. The talk will include a brief overview to freak waves in sea states where multiple wave systems meet.

Susanne is a PostDoc in the ERC project HIGHWAVE at Ecole Normale Supérieure (ENS) Paris-Saclay. She has achieved her Master’s and PhD at the University of Oslo, Norway. With a background in applied maths and fluid mechanics, Susanne has worked with a number of different applications, ranging from biomedical flows to ocean waves. In recent years she has pursued the study of ocean waves by combining numerical simulations and measurements. One of her focus areas is the interpretation of radar measurements of the ocean surface. Extracting wave information from radar images requires combining signal processing and an understanding of the imaging mechanism.

27/06/2023
Event

M³OCCA PhD students participate in field campaign on the Jungfraufirn in Switzerland

In March 2023 two of our M³OCCA PhD students, Lena Krabbe from LHFT/ FAU Erlangen and Akash Patil from BAdW Munich, joined a three-week field test campaign taking place at the Jungfraufirn on the Aletsch glacier in Switzerland. Therein, they were able to collect multiple data sets from different Ground Penetrating Radar (GPR) systems, namely a commercial GPR system as well as a GPR sled developed by Lena Krabbe at LHFT.  Field campaigns like this are an essential part of glacier and ice research in order to assess the system performance in the field as well as to check, whether the systems and solutions developed in the lab are also capable of enduring extreme environmental conditions that are present on glaciers. Moreover, the collected data is a great basis for a performance comparison not only between the two surface-based GPR systems, but also for comparing them to further measurement equipment tested during this field campaign. The latter includes a melting probe consisting of a radar, a sonar and a permittivity sensor as well as UAV-based radar and lidar systems. During the field test, two main measurement sites were evaluated, including an area close to the Mönchsjoch as well as the camp site below the Sphinx, which is also close to the glacier entrance. Furthermore, also more remote places where evaluated after being explored and assessed together with a mountain guide. Overall, this field test was a great opportunity to gain experience in applied glacier research and intensify the collaboration inside the M³OCCA doctoral program.

 

15/05/2023
Outreach

AI Newcomer Award 2023 goes to Nora Gourmelon from FAU’s Pattern Recognition Lab

Nora Gourmelon (Photo: second from right) is honored with the AI Newcomer Award 2023 in the field of natural and life sciences for her research in Green AI, a research field that tackles sustainability-related problems with AI.

In her current work, conducted as part of the International Doctoral Program (IDP) “Measuring and Modeling Mountain glaciers and ice caps in a Changing ClimAte (M³OCCA),” she is developing deep-learning techniques for extracting glacier front positions from satellite imagery.

When asked what the award means to her, Gourmelon responds: “The award helps to raise awareness of how you can also get involved in biodiversity and climate protection as a computer scientist. In addition, I am, of course, also very pleased about the great recognition for my research to date.”

The AI Newcomer Award is granted by the German Association of Computer Science (Gesellschaft für Informatik) to young researchers under 30 years for innovative developments in the area of artificial intelligence.

The award ceremony took place in Berlin on April 26 as part of “KI-Camp 2023,” an event for young AI researchers organized by the German Association of Computer Science and the German Federal Ministry for Education and Research (Bundesministerium für Bildung und Forschung).

The recording of the ceremony will be published here soon.

The award has also attracted the attention of the media and the press!

02/05/2023
Event

Invited talk on „Keeping track of change – Monitoring Antarctic calving front dynamics with earth observation and deep learning“

The Institute of Geography at FAU Erlangen-Nürnberg will host an invited talk by Dr. Celia Baumhoer (DLR/DFG Oberpfaffenhofen).

When: Wednesday, 14.06.2023, 12:30-14:00

Where: Seminar room, Wetterkreuz 15, 91058 Erlangen

Abstract:

The Antarctic coastline is constantly changing. Three-quarters of the coastline are fringed by ice shelves, the floating extensions of the Antarctic ice sheet. The retreat or disintegration of ice shelves with buttressing forces cause enhanced mass loss of the Antarctic ice sheet increasing global sea level rise.  Continuously tracking ice shelves is challenging because manual mapping cannot keep up with growing satellite archives and automated approaches fail due to the complexity of the Antarctic coastline. Recent advances in deep learning and easy access to high performance computing facilitated a fully-automated framework able to regularly monitor Antarctic ice shelf front dynamics. This presentation explores the unprecedented dense time series of calving front change providing new insights into ice shelf front dynamics and establishes links to ice dynamical and environmental controls on ice shelf extents.

02/05/2023
Event

Invited talk on “Deep-learning-driven estimation of global glacier thickness”

The Institute of Geography at FAU Erlangen-Nürnberg will host an invited talk by Dr. Samuel Cook (Univ. Lausanne).

When: Wednesday, 17.05.2023, 12:30-14:00

Where: Seminar room, Wetterkreuz 15, 91058 Erlangen

Abstract:

I present my ongoing work using the emulator from the Instructed Glacier Model (IGM) (https://github.com/jouvetg/igm) to invert for ice thickness at the 200,000 glaciers in the world outside the polar ice sheets. The basis of the emulator is a convolutional neural network trained on the outputs of full-Stokes simulations of real glaciers. Provided with surface velocities – taken from the new global dataset compiled by Millan et al. (2022) – and surface DEMs, this emulator can invert for thickness at any glacier in the world with a comparable accuracy to traditional full-Stokes inversion, but at a fraction of the computational cost. This allows us to greatly improve our estimates of global glacier volume, vital both for prediction of sea-level rise, but also for local communities in mountainous areas, who often rely on glacier melt for a large proportion of their water resources. I will discuss the rationale and methods behind my work, as well as preliminary results and the problems I’m currently working on.