When rivers burst their banks, the consequences can be devastating, as the catastrophic floods in North Rhine-Westphalia and Rhineland-Palatinate three years ago have shown. In order to decrease flood damage in the future and optimize the assessment of flood risks, it is necessary to better understand which variables can lead to extreme forms of flooding and to what extent. Using methods of Explainable Machine Learning, researchers at the Helmholtz Centre for Environmental Research (UFZ) have shown that flooding is more extreme when several factors are involved in its development. The new findings were published in the journal Science Advances. Detailed information on the study can also be found here.

Publication:
Shijie Jiang, Larisa Tarasova, Guo Yu, Jakob Zscheischler (2024): Compounding effects in flood drivers challenge estimates of extreme river floods. Science Advances, https://www.science.org/doi/10.1126/sciadv.adl4005