Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Towards a comprehensive assessment of statistical versus soft computing models in hydrology : Application to monthly pan evaporation prediction

Zounemat-Kermani, Mohammad ; Keshtegar, Behrooz ; Kisi, Ozgur and Scholz, Miklas LU (2021) In Water 13(17).
Abstract

This paper evaluates six soft computational models along with three statistical data-driven models for the prediction of pan evaporation (EP). Accordingly, improved kriging—as a novel statistical model—is proposed for accurate predictions of EP for two meteorological stations in Turkey. In the standard kriging model, the input data nonlinearity effects are increased by using a nonlinear map and transferring input data from a polynomial to an exponential basic function. The accuracy, precision, and over/under prediction tendencies of the response surface method, kriging, improved kriging, multilayer perceptron neural network using the Levenberg–Marquardt (MLP-LM) as well as a conjugate gradient (MLP-CG), radial basis function neural... (More)

This paper evaluates six soft computational models along with three statistical data-driven models for the prediction of pan evaporation (EP). Accordingly, improved kriging—as a novel statistical model—is proposed for accurate predictions of EP for two meteorological stations in Turkey. In the standard kriging model, the input data nonlinearity effects are increased by using a nonlinear map and transferring input data from a polynomial to an exponential basic function. The accuracy, precision, and over/under prediction tendencies of the response surface method, kriging, improved kriging, multilayer perceptron neural network using the Levenberg–Marquardt (MLP-LM) as well as a conjugate gradient (MLP-CG), radial basis function neural network (RBFNN), multivariate adaptive regression spline (MARS), M5Tree and support vector regression (SVR) were compared. Overall, all the applied models were highly capable of predicting monthly EP in both stations with a mean absolute error (MAE) < 0.77 mm and a Willmott index (d) > 0.95. Considering periodicity as an input parameter, the MLP-LM provided better results than the other methods among the soft computing models (MAE = 0.492 mm and d = 0.981). However, the improved kriging method surpassed all the other models based on the statistical measures (MAE = 0.471 mm and d = 0.983). Finally, the outcomes of the Mann–Whitney test indicated that the applied soft computational models do not have significant superiority over the statistical ones (p-value > 0.65 at α = 0.01 and α = 0.05).

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Improved kriging, Machine learning models, MARS, Pan evaporation, SVR
in
Water
volume
13
issue
17
article number
2451
publisher
MDPI AG
external identifiers
  • scopus:85114558873
ISSN
2073-4441
DOI
10.3390/w13172451
language
English
LU publication?
yes
id
ecbef060-1f4c-4238-af69-5deccea5d2b5
date added to LUP
2021-10-11 11:17:12
date last changed
2022-04-27 04:37:42
@article{ecbef060-1f4c-4238-af69-5deccea5d2b5,
  abstract     = {{<p>This paper evaluates six soft computational models along with three statistical data-driven models for the prediction of pan evaporation (EP). Accordingly, improved kriging—as a novel statistical model—is proposed for accurate predictions of EP for two meteorological stations in Turkey. In the standard kriging model, the input data nonlinearity effects are increased by using a nonlinear map and transferring input data from a polynomial to an exponential basic function. The accuracy, precision, and over/under prediction tendencies of the response surface method, kriging, improved kriging, multilayer perceptron neural network using the Levenberg–Marquardt (MLP-LM) as well as a conjugate gradient (MLP-CG), radial basis function neural network (RBFNN), multivariate adaptive regression spline (MARS), M5Tree and support vector regression (SVR) were compared. Overall, all the applied models were highly capable of predicting monthly EP in both stations with a mean absolute error (MAE) &lt; 0.77 mm and a Willmott index (d) &gt; 0.95. Considering periodicity as an input parameter, the MLP-LM provided better results than the other methods among the soft computing models (MAE = 0.492 mm and d = 0.981). However, the improved kriging method surpassed all the other models based on the statistical measures (MAE = 0.471 mm and d = 0.983). Finally, the outcomes of the Mann–Whitney test indicated that the applied soft computational models do not have significant superiority over the statistical ones (p-value &gt; 0.65 at α = 0.01 and α = 0.05).</p>}},
  author       = {{Zounemat-Kermani, Mohammad and Keshtegar, Behrooz and Kisi, Ozgur and Scholz, Miklas}},
  issn         = {{2073-4441}},
  keywords     = {{Improved kriging; Machine learning models; MARS; Pan evaporation; SVR}},
  language     = {{eng}},
  number       = {{17}},
  publisher    = {{MDPI AG}},
  series       = {{Water}},
  title        = {{Towards a comprehensive assessment of statistical versus soft computing models in hydrology : Application to monthly pan evaporation prediction}},
  url          = {{http://dx.doi.org/10.3390/w13172451}},
  doi          = {{10.3390/w13172451}},
  volume       = {{13}},
  year         = {{2021}},
}