Extreme weather events (e.g., hail, late frost, heavy rainfall, droughts) in Germany are expected to become more frequent in the near future due to climate change, which will exacerbate the weather-associated risks to agriculture. Forecasting where and when hazards might occur is therefore crucial for increasing the resilience of agricultural activities to climate change.

The project Dynamic Agricultural Weather Indicators (AWI) for Extreme Weather Forecasts in Agriculture (DynAWI) aims to develop a process chain for spatial data integration and analysis by coupling scalable spatial data infrastructures with methods of artificial intelligence or machine learning (AI/ML). The project focuses on identifying optimal AWIs for droughts, late frosts, and soil erosion by water, which will be subsequently used to develop region-specific models to provide spatiotemporal forecasts of extreme weather hazards to agriculture. In specific, the project aims to:

1. Develop a multidimensional geodata infrastructure (i.e., DataCube) to allow for the processing and analysis of large volumes of satellite and meteorological data from which AWIs can be derived for any area in Germany, historically and in real-time.
2. Consolidate, standardise, and integrate existing monitoring data (e.g. crop yields, results from soil erosion mapping) into a dynamic database, which will be used as representative spatiotemporal training data for the AI.
3. Select, integrate, and implement AI methods for providing region-specific spatiotemporal forecasts of extreme weather hazards to agriculture in Germany.

?

Link to research project page

?

?

back to research overview

?

back to research overview

?