KI:STE
AI Strategy for Earth system data

About KI:STE

The KISTE project aimed to exploit recent developments in artificial intelligence – especially deep learning methods – for sound environmental data analysis. The scientific goal was the implementation of current AI approaches for spatiotemporal variable pattern recognition and pattern analysis in environmental data in the subject areas clouds, geohazards, water, air quality and vegetation within the framework of five dissertations. During this time, a technical platform was created to make powerful AI applications on environmental data portably available. An online AI learning platform with various interfaces for this AI platform was set up for this purpose. This e-learning offer is aimed at the location-independent education of young scientists and other interested parties. It will use the concepts and methods developed in the five research fields as teaching material.

Work packages

Clouds

Improved predictability of the availability of solar energy through the analysis of spatial-temporal patterns of cloud parameters based on geostationary satellite observations

Geohazards

Development of a generic and FAIR susceptibility and hazard mapping framework for facilitated and streamlined geohazard mapping , as well as analysis of sensitivity of ml-based mapping on various research study-specific design parameters to support transparency and reliability.

Water

Improve predictions of droughts or floods by examining extreme hydrometeorological events from the combination of simulation and observation data

Air quality

Air quality: Development of a methodology for seasonal forecasts of extreme values of air pollution by examining the influence of plant health on air quality

Vegetation

Development of multi-task methods to predict several parameters of the plant condition simultaneously, especially with regard to extreme events.

AI lighthouse for the environment, climate, nature and resources

KISTE is part of the initiative “AI light house for the environment, climate, nature and resources”. These are projects that use their digital know-how and creativity to overcome ecological challenges.

Latest News

Research
Scarlet Stadtler

Jungle-Net Poster presentation

Within the HDS-LEE graduate school and the ISPRS congress Timo Stomberg presented his Jungle-Net capable of giving insights into wilderness using explainable machine learning.

Read More »
Meeting
Scarlet Stadtler

KI:STE Project Meeting

The KI:STE consortium meets on the 15th and 16th of November to exchange their latest scientific results, get insights to the newest functionalities of the

Read More »

Get in touch

Phone: + +49 2461 61 96870
Email: m.schultz [at] fz-juelich.de
Forschungszentrum Jülich GmbH
Institute for Advanced Simulation (IAS) Jülich Supercomputing Centre (JSC)
Wilhelm-Johnen-Straße 52425 Jülich Germany
MON-FRI 08:00 - 17:00