Month: May 2023

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.