Journal metrics

Journal metrics

  • IF value: 4.252 IF 4.252
  • IF 5-year value: 4.890 IF 5-year 4.890
  • CiteScore value: 4.49 CiteScore 4.49
  • SNIP value: 1.539 SNIP 1.539
  • SJR value: 2.404 SJR 2.404
  • IPP value: 4.28 IPP 4.28
  • h5-index value: 40 h5-index 40
  • Scimago H index value: 51 Scimago H index 51
Discussion papers | Copyright
https://doi.org/10.5194/gmd-2018-136
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Development and technical paper 10 Aug 2018

Development and technical paper | 10 Aug 2018

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Geoscientific Model Development (GMD).

Modeling Error Learning based Post-Processor Framework for Hydrologic Models Accuracy Improvement

Rui Wu1, Lei Yang1, Chao Chen2, Sajjad Ahmad3, Sergiu M. Dascalu1, and Frederick C. Harris Jr.1 Rui Wu et al.
  • 1Department of Computer Science & Engineering, University of Nevada, Reno, USA
  • 2Department of Geosciences, Boise State University, USA
  • 3Department of Civil and Environmental Engineering and Construction, University of Nevada, Las Vegas, USA

Abstract. This paper studies how to improve the accuracy of hydrologic models using machine learning models as post-processors and presents possibilities to reduce the workload to create an accurate hydrologic model by removing the calibration step. It is often challenging to develop an accurate hydrologic model, due to the time-consuming model calibration procedure and the non-stationarity of hydrologic data. Our findings show that the errors of hydrologic models are correlated with model inputs. Thus motivated, we propose a modeling error learning based post-processor framework by leveraging this correlation to improve the accuracy of a hydrologic model. The key idea is to predict the differences (errors) between the observed values and the hydrologic model predictions by using machine learning techniques. To tackle the non-stationarity issue of hydrologic data, a moving window based machine learning approach is proposed to enhance the machine learning error predictions by identifying the local stationarity of the data using a stationarity measure developed based on Hilbert-Huang transform. Two hydrologic models, the Precipitation-Runoff Modeling System (PRMS) and the Hydrologic Modeling System (HEC-HMS), are used to evaluate the proposed framework. Two case studies are provided to exhibit the improved performance over the original model using multiple statistical metrics.

Rui Wu et al.
Interactive discussion
Status: open (until 17 Nov 2018)
Status: open (until 17 Nov 2018)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Rui Wu et al.
Model code and software

Hydrologic model accuracy improvement: Prototype Version 1 R. Wu https://doi.org/10.5281/zenodo.1342891

Rui Wu et al.
Viewed
Total article views: 282 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
229 48 5 282 6 5
  • HTML: 229
  • PDF: 48
  • XML: 5
  • Total: 282
  • BibTeX: 6
  • EndNote: 5
Views and downloads (calculated since 10 Aug 2018)
Cumulative views and downloads (calculated since 10 Aug 2018)
Viewed (geographical distribution)
Total article views: 282 (including HTML, PDF, and XML) Thereof 281 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: 18 Oct 2018
Publications Copernicus
Download
Short summary
The paper mainly has two contributions. First, a post-processor framework is proposed to improve hydrologic model's accuracy. The key is to characterize possible connections between model inputs and errors. Based on results, it is also possible to replace the time-consuming model calibration step using our post-processor framework. Second, a window selection method is proposed to handle non-stationary data. A window size is chosen containing stable data using a measure named “DS” proposed by us.
The paper mainly has two contributions. First, a post-processor framework is proposed to improve...
Citation
Share