Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.17 MB
Add to list
  1. Search results
  2. Introducing a Kriging-based Gaussian ...

Introducing a Kriging-based Gaussian Process approach in pedotransfer functions : evaluation for the prediction of soil water retention with temperate and tropical datasets

Jan De Pue, Yves-Dady Botula, Phuong M. Nguyen, Marc Van Meirvenne (UGent) and Wim Cornelis (UGent)
(2021) JOURNAL OF HYDROLOGY. 597.
Author
Organization
Abstract
Data mining algorithms such as Artificial Neural Networks (ANN) and k-Nearest Neighbour (kNN) have proven their merits in pedotransfer function modelling. Kriging is a well-known algorithm for spatial interpolation, but in this study it is proposed as an alternative data mining technique. It was compared to kNN as a benchmark pedotransfer function to predict soil water retention for a wide range of datasets, containing soil data from both temperate and tropical regions. The performance of both methods was compared through Monte Carlo cross-validation and the precision of the predictions was assessed with an ensemble procedure. Across all datasets, a significant improvement in prediction bias, accuracy and precision was found with Kriging, compared to kNN. Moreover, it was demonstrated how predictions with Kriging are more robust and insensitive to non-correlated predictor variables, and how the optimized hyperparameters provide additional insight in the training dataset properties. Kriging was found to be a accurate, precise and robust data mining solution for pedotransfer function modelling.
Keywords
Water Science and Technology, Data mining, Water retention curve, k-Nearest neighbours, Precision, HYDRAULIC PARAMETERS, ENGINEERING DESIGN, SUPPORT

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.17 MB

Citation

Please use this url to cite or link to this publication:

MLA
De Pue, Jan, et al. “Introducing a Kriging-Based Gaussian Process Approach in Pedotransfer Functions : Evaluation for the Prediction of Soil Water Retention with Temperate and Tropical Datasets.” JOURNAL OF HYDROLOGY, vol. 597, 2021, doi:10.1016/j.jhydrol.2020.125770.
APA
De Pue, J., Botula, Y.-D., Nguyen, P. M., Van Meirvenne, M., & Cornelis, W. (2021). Introducing a Kriging-based Gaussian Process approach in pedotransfer functions : evaluation for the prediction of soil water retention with temperate and tropical datasets. JOURNAL OF HYDROLOGY, 597. https://doi.org/10.1016/j.jhydrol.2020.125770
Chicago author-date
De Pue, Jan, Yves-Dady Botula, Phuong M. Nguyen, Marc Van Meirvenne, and Wim Cornelis. 2021. “Introducing a Kriging-Based Gaussian Process Approach in Pedotransfer Functions : Evaluation for the Prediction of Soil Water Retention with Temperate and Tropical Datasets.” JOURNAL OF HYDROLOGY 597. https://doi.org/10.1016/j.jhydrol.2020.125770.
Chicago author-date (all authors)
De Pue, Jan, Yves-Dady Botula, Phuong M. Nguyen, Marc Van Meirvenne, and Wim Cornelis. 2021. “Introducing a Kriging-Based Gaussian Process Approach in Pedotransfer Functions : Evaluation for the Prediction of Soil Water Retention with Temperate and Tropical Datasets.” JOURNAL OF HYDROLOGY 597. doi:10.1016/j.jhydrol.2020.125770.
Vancouver
1.
De Pue J, Botula Y-D, Nguyen PM, Van Meirvenne M, Cornelis W. Introducing a Kriging-based Gaussian Process approach in pedotransfer functions : evaluation for the prediction of soil water retention with temperate and tropical datasets. JOURNAL OF HYDROLOGY. 2021;597.
IEEE
[1]
J. De Pue, Y.-D. Botula, P. M. Nguyen, M. Van Meirvenne, and W. Cornelis, “Introducing a Kriging-based Gaussian Process approach in pedotransfer functions : evaluation for the prediction of soil water retention with temperate and tropical datasets,” JOURNAL OF HYDROLOGY, vol. 597, 2021.
@article{8692702,
  abstract     = {{Data mining algorithms such as Artificial Neural Networks (ANN) and k-Nearest Neighbour (kNN) have proven their merits in pedotransfer function modelling. Kriging is a well-known algorithm for spatial interpolation, but in this study it is proposed as an alternative data mining technique. It was compared to kNN as a benchmark pedotransfer function to predict soil water retention for a wide range of datasets, containing soil data from both temperate and tropical regions. The performance of both methods was compared through Monte Carlo cross-validation and the precision of the predictions was assessed with an ensemble procedure. Across all datasets, a significant improvement in prediction bias, accuracy and precision was found with Kriging, compared to kNN. Moreover, it was demonstrated how predictions with Kriging are more robust and insensitive to non-correlated predictor variables, and how the optimized hyperparameters provide additional insight in the training dataset properties. Kriging was found to be a accurate, precise and robust data mining solution for pedotransfer function modelling.}},
  articleno    = {{125770}},
  author       = {{De Pue, Jan and Botula, Yves-Dady and Nguyen, Phuong M. and Van Meirvenne, Marc and Cornelis, Wim}},
  issn         = {{0022-1694}},
  journal      = {{JOURNAL OF HYDROLOGY}},
  keywords     = {{Water Science and Technology,Data mining,Water retention curve,k-Nearest neighbours,Precision,HYDRAULIC PARAMETERS,ENGINEERING DESIGN,SUPPORT}},
  language     = {{eng}},
  pages        = {{10}},
  title        = {{Introducing a Kriging-based Gaussian Process approach in pedotransfer functions : evaluation for the prediction of soil water retention with temperate and tropical datasets}},
  url          = {{http://doi.org/10.1016/j.jhydrol.2020.125770}},
  volume       = {{597}},
  year         = {{2021}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: