Advanced search
1 file | 613.41 KB Add to list

Simple methods for estimating field capacity using Mamdani inference system and regression tree

Author
Organization
Abstract
Using easily measurable soil properties could save time and cost for field capacity (FC) prediction. The objective of this study was to compare Mamdani fuzzy inference system (MFIS) and regression tree (RT) for FC predicting using such properties. One hundred and sixty-five soil samples from Unsaturated Soil hydraulic database data-set and 45 from Hydraulic Properties of European Soils data-set were used for the development and validation of MFIS and RT, respectively. Fuzzy rules and tree diagram based on the relationships between these predictor variables and the response variable FC were defined and 48 rules were written. Results showed a positive linear relevancy in terms of standardized independent variable weight, W*, between clay content and FC and negative linear relevancy between geometric mean particular size diameter (d(g)) and FC. Among predictor variables, d(g) (W*=0.81) and bulk density (BD) (W*=0.49) had the highest and lowest influence on FC, respectively. A tree diagram is presented for the prediction of FC using clay content, dg, and BD. Overall, based on statistical parameters, RT method (R-2=0.78, geometric mean error (GME)=1.02, mean error (ME)=0.01cm(3)cm(-3), and root mean square error (RMSE)=0.04cm(3)cm(-3)) showed a higher performance than MFIS method (R-2=0.72, GME=1.16, ME=0.08cm(3)cm(-3), and RMSE=0.06cm(3)cm(-3)) to predict FC.
Keywords
UNSODA, regression tree, Mamdani fuzzy inference system, field capacity, HYPRES, PEDOTRANSFER FUNCTIONS, WATER-RETENTION, IRAN

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 613.41 KB

Citation

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

MLA
Ostovari, Yaser, Kamran Asgari, Wim Cornelis, et al. “Simple Methods for Estimating Field Capacity Using Mamdani Inference System and Regression Tree.” ARCHIVES OF AGRONOMY AND SOIL SCIENCE 61.6 (2015): 851–864. Print.
APA
Ostovari, Y., Asgari, K., Cornelis, W., & Beigi-Harchegani, H. (2015). Simple methods for estimating field capacity using Mamdani inference system and regression tree. ARCHIVES OF AGRONOMY AND SOIL SCIENCE, 61(6), 851–864.
Chicago author-date
Ostovari, Yaser, Kamran Asgari, Wim Cornelis, and Habib Beigi-Harchegani. 2015. “Simple Methods for Estimating Field Capacity Using Mamdani Inference System and Regression Tree.” Archives of Agronomy and Soil Science 61 (6): 851–864.
Chicago author-date (all authors)
Ostovari, Yaser, Kamran Asgari, Wim Cornelis, and Habib Beigi-Harchegani. 2015. “Simple Methods for Estimating Field Capacity Using Mamdani Inference System and Regression Tree.” Archives of Agronomy and Soil Science 61 (6): 851–864.
Vancouver
1.
Ostovari Y, Asgari K, Cornelis W, Beigi-Harchegani H. Simple methods for estimating field capacity using Mamdani inference system and regression tree. ARCHIVES OF AGRONOMY AND SOIL SCIENCE. 2015;61(6):851–64.
IEEE
[1]
Y. Ostovari, K. Asgari, W. Cornelis, and H. Beigi-Harchegani, “Simple methods for estimating field capacity using Mamdani inference system and regression tree,” ARCHIVES OF AGRONOMY AND SOIL SCIENCE, vol. 61, no. 6, pp. 851–864, 2015.
@article{5833155,
  abstract     = {Using easily measurable soil properties could save time and cost for field capacity (FC) prediction. The objective of this study was to compare Mamdani fuzzy inference system (MFIS) and regression tree (RT) for FC predicting using such properties. One hundred and sixty-five soil samples from Unsaturated Soil hydraulic database data-set and 45 from Hydraulic Properties of European Soils data-set were used for the development and validation of MFIS and RT, respectively. Fuzzy rules and tree diagram based on the relationships between these predictor variables and the response variable FC were defined and 48 rules were written. Results showed a positive linear relevancy in terms of standardized independent variable weight, W*, between clay content and FC and negative linear relevancy between geometric mean particular size diameter (d(g)) and FC. Among predictor variables, d(g) (W*=0.81) and bulk density (BD) (W*=0.49) had the highest and lowest influence on FC, respectively. A tree diagram is presented for the prediction of FC using clay content, dg, and BD. Overall, based on statistical parameters, RT method (R-2=0.78, geometric mean error (GME)=1.02, mean error (ME)=0.01cm(3)cm(-3), and root mean square error (RMSE)=0.04cm(3)cm(-3)) showed a higher performance than MFIS method (R-2=0.72, GME=1.16, ME=0.08cm(3)cm(-3), and RMSE=0.06cm(3)cm(-3)) to predict FC.},
  author       = {Ostovari, Yaser and Asgari, Kamran and Cornelis, Wim and Beigi-Harchegani, Habib},
  issn         = {0365-0340},
  journal      = {ARCHIVES OF AGRONOMY AND SOIL SCIENCE},
  keywords     = {UNSODA,regression tree,Mamdani fuzzy inference system,field capacity,HYPRES,PEDOTRANSFER FUNCTIONS,WATER-RETENTION,IRAN},
  language     = {eng},
  number       = {6},
  pages        = {851--864},
  title        = {Simple methods for estimating field capacity using Mamdani inference system and regression tree},
  url          = {http://dx.doi.org/10.1080/03650340.2014.957687},
  volume       = {61},
  year         = {2015},
}

Altmetric
View in Altmetric
Web of Science
Times cited: