Journal cover Journal topic
Natural Hazards and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 2.883 IF 2.883
  • IF 5-year value: 3.321 IF 5-year
    3.321
  • CiteScore value: 3.07 CiteScore
    3.07
  • SNIP value: 1.336 SNIP 1.336
  • IPP value: 2.80 IPP 2.80
  • SJR value: 1.024 SJR 1.024
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 81 Scimago H
    index 81
  • h5-index value: 43 h5-index 43
Discussion papers
https://doi.org/10.5194/nhess-2020-67
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-2020-67
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 09 Mar 2020

Submitted as: research article | 09 Mar 2020

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

Skill of large-scale seasonal drought impact forecasts

Samuel J. Sutanto1, Melati van der Weert1, Veit Blauhut2, and Henny A. J. Van Lanen1 Samuel J. Sutanto et al.
  • 1Hydrology and Quantitative Water Management Group, Environmental Sciences Department, Wageningen University and Research, Droevendaalsesteeg 3a, 6708PB, Wageningen, the Netherlands
  • 2Hydrological Environmental Systems, University of Freiburg, Fahnenbergplatz, D-79098, Freiburg, Germany

Abstract. Forecasting drought impacts is still missing in drought early warning systems that presently do not go beyond hazard forecasting. Therefore, we developed drought impact functions using machine learning approaches (Logistic Regression and Random Forest) to predict drought impacts with a lead-time of 7 months ahead. The skill of the drought impact functions to forecast drought impacts was evaluated using the Brier Skill Score and Relative Operating Characteristic metrics for 5 Cases representing different spatial aggregation and lumping of impacted sectors. For German regions, impact functions developed using Random Forest show a higher discriminative ability to forecast drought impacts than Logistic Regression. Moreover, skill is higher for Cases with higher spatial resolution and less-lumped impacted sectors (Cases 4 and 5), with considerable skill up to 3–4 months ahead.

Samuel J. Sutanto et al.

Interactive discussion

Status: open (until 04 May 2020)
Status: open (until 04 May 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Samuel J. Sutanto et al.

Samuel J. Sutanto et al.

Viewed

Total article views: 224 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
172 52 0 224 15 0 0
  • HTML: 172
  • PDF: 52
  • XML: 0
  • Total: 224
  • Supplement: 15
  • BibTeX: 0
  • EndNote: 0
Views and downloads (calculated since 09 Mar 2020)
Cumulative views and downloads (calculated since 09 Mar 2020)

Viewed (geographical distribution)

Total article views: 190 (including HTML, PDF, and XML) Thereof 189 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved

No saved metrics found.

Discussed

No discussed metrics found.
Latest update: 05 Apr 2020
Publications Copernicus
Download
Short summary
Present-day drought early warning systems only provide information on drought hazard forecasts. Here, we have developed drought impact functions to forecast drought impacts up to 7 months ahead using machine learning techniques, Logistic Regression, and Random Forest. Our results show that Random Forest produces higher impact forecasting skill than Logistic Regression. For German county levels, drought impacts can be forecasted up to 4 months ahead using Random Forest.
Present-day drought early warning systems only provide information on drought hazard forecasts....
Citation