AI4Glaciers: AI-Enabled Prediction of Glacial Calving based on 4D Real-Time Multi-Sensor Monitoring (AI4G)

• Applicants: Dr.-Ing. Xabier Blanch Gorriz; Professorin Dr. Anette Eltner
• Subject Area: Physical Geography
• Term: since 2024
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 536233846

Glaciers play a critical role in the Earth's climate system and serve as important indicators of climate change. However, climatic influences and dynamic changes in glaciers are causing a loss of ice. One significant factor contributing to mass loss is glacier calving. Calving at the glacier front is a particularly challenging process to monitor, making it often a poorly understood part of the glacier dynamics. Ac-curately forecasting these events requires an in-depth understanding of the calving process, which will also lead to a better identification of factors that control its activity. This project aims to develop an approach for 4D multi-sensor monitoring by integrating methods from photogrammetry and artificial intelligence algorithms applied to multi-modal data. To capture 3D spatio-temporal data with unprece-dented detail in glacier front studies, we will employ high-resolution synchronized time-lapse cameras, along with thermal cameras, allowing for sub-daily image acquisition of the glacier front even at night. Acknowledging the profound influence that environmental factors and glacier dynamics have on the glacier calving, multi-sensor systems will be exploited to collect weather data and glacier velocities, among others, to enable a more holistic analysis of the calving phenomenon. Firstly, we will focus on creating a comprehensive 3D inventory of glacier calving with an unprecedented level of temporal fre-quency. To achieve this, we will develop and fine-tune a multi-sensor monitoring system. The obtained data will enable the generation of time-series of 3D models for calving detection. We will further in-tegrate data from various sensors, such as thermal cameras and seismometers, together with AI tech-niques for an accurate automatic identification of calving events and their volume. Sub-daily image acquisition will allow for 4D data analysis, integrating the evolution of changes into the study of the behaviour of the glacier front. Secondly, we will focus on the development of two methodologies to contribute to the forecast of glacier calving and to address the factors that control it. By accurately monitoring the calving blocks, we can identify fracture activation and monitor their deformation until they reach a point of non-stability. This approach will allow us to establish power-law functions for estimating the break-up time in advance. The second method will integrate the extensive calving inven-tory, together with environmental and glacier dynamics data, to train a specialized neural network for time series prediction. This type of AI predicts future states in non-linear processes allowing us to fo-recast the volume and location of future calving events. The project's main outcome will provide in-sights into the influential factors controlling glacier calving. This knowledge represents a significant advancement in understanding calving processes and glacier behavior, particularly in the context of climate change's challenges.

• DFG Programme: Research Grants
• International Connection: Chile
• Cooperation Partner: Professor Dr. David Farias Barahona