Preprints
https://doi.org/10.5194/nhess-2021-110
https://doi.org/10.5194/nhess-2021-110

  15 Apr 2021

15 Apr 2021

Review status: this preprint is currently under review for the journal NHESS.

Applying machine learning for drought prediction using data from a large ensemble of climate simulations

Elizaveta Felsche1,2,3 and Ralf Ludwig2 Elizaveta Felsche and Ralf Ludwig
  • 1Center for Digital Technology and Management, Munich, Germany
  • 2Department of Geography, Ludwig Maximilians University of Munich, Munich, Germany
  • 3Technical University of Munich, Munich, Germany

Abstract. There is strong scientific and social interest to understand the factors leading to extreme events in order to improve the management of risks associated with hazards like droughts. In this study, artificial neural networks are applied to predict the occurrence of a drought in two contrasting European domains, Munich and Lisbon, with a lead time of one month. The approach takes into account a list of 30 atmospheric and soil variables as input parameters from a single-model initial condition large ensemble (CRCM5-LE). The data was produced the context of the ClimEx project by Ouranos with the Canadian Regional Climate Model (CRCM5) driven by 50 members of the Canadian Earth System Model (CanESM2). Drought occurrence was defined using the Standardized Precipitation Index. The best performing machine learning algorithms managed to obtain a correct classification of drought or no drought for a lead time of one month for around 55–60 % of the events of each class for both domains. Explainable AI methods like SHapley Additive exPlanations (SHAP) were applied to gain a better understanding of the trained algorithms. Variables like the North Atlantic Oscillation Index and air pressure one month before the event proved to be of high importance for the prediction. The study showed that seasonality has a high influence on goodness of drought prediction, especially for the Lisbon domain.

Elizaveta Felsche and Ralf Ludwig

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2021-110', Anonymous Referee #1, 10 Jun 2021
    • AC1: 'Reply on RC1', Elizaveta Felsche, 09 Jul 2021
  • RC2: 'Comment on nhess-2021-110', Anonymous Referee #2, 17 Jun 2021
    • AC2: 'Reply on RC2', Elizaveta Felsche, 09 Jul 2021

Elizaveta Felsche and Ralf Ludwig

Elizaveta Felsche and Ralf Ludwig

Viewed

Total article views: 696 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
455 226 15 696 1 2
  • HTML: 455
  • PDF: 226
  • XML: 15
  • Total: 696
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 15 Apr 2021)
Cumulative views and downloads (calculated since 15 Apr 2021)

Viewed (geographical distribution)

Total article views: 648 (including HTML, PDF, and XML) Thereof 648 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 16 Oct 2021
Download
Short summary
This study applies artificial neural networks to predict the occurrence of a drought in Munich and Lisbon, with a lead time of one month. An analysis of the variables that have the highest impact on the prediction is performed. The study shows that North Atlantic Oscillation Index and air pressure one month before the event have the highest importance for the prediction. Moreover it shows that seasonality has a high influence on the goodness of prediction for the Lisbon domain.
Altmetrics