Volume 17, Issue 63 (Spring 2013)                   jwss 2013, 17(63): 215-225 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

M. Arabi, A. Soffianian, M. Tarkesh Esfahani. Determination of Spatial Distribution Pattern of Zn in Surface Soils of Hamadan Province Using Classification and Regression Tree Model. jwss 2013; 17 (63) :215-225
URL: http://jstnar.iut.ac.ir/article-1-2555-en.html
, m.arabi@in.iut.ac.ir
Abstract:   (12410 Views)
Physicochemical characteristics of soil, land cover/use and human activities have effects on heavy metals distribution. In this study, we applied Classification and Regression Tree model (CART) to predict the spatial distribution of zinc in surface soil of Hamadan province under Geographic Information System environment. Two approaches were used to build the model. In the first approach, 10% of total data were randomly selected as test data and residual data were used for building model. In the second approach, all data were used to build and evaluate the CART model. Determination coefficient (R2) and Mean Square Error (MSE) were applied to estimate the accuracy of model. Final model included 51 nodes and 26 terminal nodes (leaf). Calcium carbonate, slope, sand, silt and land use/cover were determined by the CART model to predict spatial distribution of Zn as the most important independent variables. The regions of western Hamadan province had the highest concentration of Zn whereas the lowest concentration of Zn occurred in the regions of northern Hamadan province. The results indicate good accuracy of CART model using R2 and MSE indices.
Full-Text [PDF 317 kb]   (2716 Downloads)    
Type of Study: Research | Subject: Ggeneral
Received: 2013/06/2 | Accepted: 2013/06/2 | Published: 2013/06/2

Add your comments about this article : Your username or Email:
CAPTCHA

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | JWSS - Isfahan University of Technology

Designed & Developed by : Yektaweb