Preprints
https://doi.org/10.5194/hess-2021-9
https://doi.org/10.5194/hess-2021-9

  12 Jan 2021

12 Jan 2021

Review status: a revised version of this preprint is currently under review for the journal HESS.

Machine learning methods to assess the effects of a non-linear damage spectrum taking into account soil moisture on winter wheat yields in Germany

Michael Peichl1, Stephan Thober1, Luis Samaniego1, Bernd Hansjürgens2, and Andreas Marx1 Michael Peichl et al.
  • 1UFZ-Helmholtz Centre for Environmental Research, Department Computational Hydrosystems, Permoserstrasse 15, D-04318 Leipzig, Germany
  • 2UFZ-Helmholtz Centre for Environmental Research, Department Economics, Permoserstrasse 15, D-04318 Leipzig, Germany

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.

Michael Peichl et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2021-9', Anonymous Referee #1, 30 Jan 2021
    • AC1: 'Reply on RC1', Michael Peichl, 30 Apr 2021
  • RC2: 'Comment on hess-2021-9', Anonymous Referee #2, 06 Feb 2021
    • AC2: 'Reply on RC2', Michael Peichl, 30 Apr 2021

Michael Peichl et al.

Michael Peichl et al.

Viewed

Total article views: 666 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
497 157 12 666 7 5
  • HTML: 497
  • PDF: 157
  • XML: 12
  • Total: 666
  • BibTeX: 7
  • EndNote: 5
Views and downloads (calculated since 12 Jan 2021)
Cumulative views and downloads (calculated since 12 Jan 2021)

Viewed (geographical distribution)

Total article views: 587 (including HTML, PDF, and XML) Thereof 583 with geography defined and 4 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 Jul 2021
Download
Short summary
A statistical model that can account for complex systems is used to identify the main factors affecting wheat yield in Germany. In many parts of Germany, the main adverse effect is caused by too much soil water in spring. Yield losses in northeastern Germany are related to soil moisture drought. Meteorological effects such as heat do not seem to play a prominent role. Furthermore, the model is able to explain both exceptionally high yields (2014) and yields in very high loss years (2003, 2018).