Abstract. Agricultural production is highly dependent on the weather. The mechanisms of action are complex and interwoven, making it difficult to identify relevant management and adaptation options. The present study uses random forests to investigate such highly non-linear systems for predicting yield anomalies in winter wheat at district level in Germany. In order to take into account sub-seasonality, monthly features are used that explicitly take soil moisture into account in addition to extreme meteorological events. Clustering is used to show spatially different damage potentials, such as a higher susceptibility to drought damage from April to July in eastern Germany compared to the rest of the country. The variable that explains most differences is soil moisture in March, where higher soil moisture has a detrimental effect on crop yields. In general, soil moisture explains more yield variations than the meteorological variables, while the top 25 cm of soil moisture is a better yield predictor than the total soil column. The approach has proven to be suitable to explain historical extreme yield anomalies for years with exceptionally high losses (2003, 2018) and gains (2014) and the spatial distribution of these anomalies. The highest test R-square is about 0.70. Furthermore, the sensitivity of yield variations to soil moisture and extreme meteorological conditions, as shown by the visualisation of average marginal effects, contributes to the promotion of targeted decision support systems.
Machine learning methods to assess the effects of a non-linear
damage spectrum taking into account soil moisture on winter wheat
yields in Germany