Research

The UN Decade of Action on Cryospheric Sciences aims to reduce uncertainties regarding the causes and effects of changes in snow, ice, and permafrost. Snow is a major contributor to these uncertainties due to the incomplete understanding and representation of snow processes in climate models. SnowShifts seeks to significantly enhance our comprehension of snow volume and mass, their non-linear dynamics and properties and, specifically, snow regime shifts within the Earth and climate systems. This will be achieved through a novel combination of in-situ and remote sensing observations, along with high-end numeric model developments. Innovative technologies such as photon-counting space-borne laser altimeters, terrestrial superconducting gravimeters, and novel scale-bridging approaches and downscaling of satellite gravimetry in extreme snow environments will be integrated with the latest multi-sensor satellite data and modelling. This will enable the retrieval of snow volume, mass, extent, and other properties, such as snow albedo, at unprecedented spatio-temporal resolutions. The combined observational and modelling advancements will define and describe trends and shifts in snow climates ranging from high-latitude polar regions to mid-latitude high-mountain ranges. This project will provide future snow scenarios for at least three socio-economic pathways refining current global and regional climate models, exploring and defining potential non-linearities in snow changes. SnowShifts will not only demonstrate the accuracy of our new models in reproducing snow quantities and dynamics but will also generate extensive datasets characterising snow in remote and understudied regions. The new representations of snow processes will be a major outcome permitting the scientific community to incorporate the knowledge gained into climate and land surface models, and to replace in parts computationally expensive model components with machine learning emulators.

The study aims to develop a model system that uses artificial intelligence (AI) to predict the output of VERBUND's hydroelectric power plant chains along the Danube and Inn rivers. The AI system will use discharge forecasts from several operational precipitation-runoff models, all based on VERBUND's internal precipitation-runoff system COSERO. The input data and the measured power plant outputs are provided by the client at hourly intervals. The project aims to predict output up to a forecast horizon of 72 hours. Attempts will also be made to interpret the AI model, quantifying the individual contribution of a COSERO discharge forecast to the overall output forecast.

The study as part of the ‘Digital Transformation in the BMLRT’ is intended to drive forward the future digitalisation, networking and automation of Austria-wide flood risk management. In the first phase, modern geodata and AI technologies were analysed and integrated into an overall model for area-wide monitoring. An AI-based prototype for flood forecasting was developed and successfully tested, improving accuracy compared to existing models. Applications for event analysis and documentation were also developed. Phase 2 aims to extend the AI modelling system to predict exceedance probabilities and hazard indices for entire watercourse sections. This will be implemented and tested using a selected catchment area such as the Mur. It is also being investigated which updated data sets are required for the continuous operation of the modelling system and how these can be provided. The ‘deliverables’ will be a description of the methods developed and an analysis of the necessary data updates and data streams in a report.