Elsevier

Pedosphere

Volume 25, Issue 4, August 2015, Pages 580-591
Pedosphere

Digital Soil Mapping Using Artificial Neural Networks and Terrain-Related Attributes

https://doi.org/10.1016/S1002-0160(15)30038-2Get rights and content

Abstract

Detailed soil surveys involve costly and time-consuming work and require expert knowledge. Since soil surveys provide information to meet a wide range of needs, new methods are necessary to map soils quickly and accurately. In this study, multilayer perceptron artificial neural networks (ANNs) were developed to map soil units using digital elevation model (DEM) attributes. Several optimal ANNs were produced based on a number of input data and hidden units. The approach used test and validation areas to calculate the accuracy of interpolated and extrapolated data. The results showed that the system and level of soil classification employed had a direct effect on the accuracy of the results. At the lowest level, smaller errors were observed with the World Reference Base (WRB) classification criteria than the Soil Taxonomy (ST) system, but more soil classes could be predicted when using ST (7 soils in the case of ST vs. 5 with WRB). Training errors were below 11% for all the ANN models applied, while the test error (interpolation error) and validation error (extrapolation error) were as high as 50% and 70%, respectively. As expected, soil prediction using a higher level of classification presented a better overall level of accuracy. To obtain better predictions, in addition to DEM attributes, data related to landforms and/or lithology as soil-forming factors, should be used as ANN input data.

References (56)

  • B Khalilmoghadam et al.

    Estimation of surface shear strength in Zagros region of Iran—A comparison of artificial neural networks and multiple-linear regression models

    Geoderma

    (2009)
  • M Kim et al.

    Artificial neural network estimation of soil erosion and nutrient concentrations in runoff from land application areas

    Comput Electron Agr

    (2008)
  • P Licznar et al.

    Artificial neural networks of soil erosion and runoff prediction at the plot scale

    Catena

    (2003)
  • A B McBratney et al.

    On digital soil mapping

    Geoderma

    (2003)
  • N J McKenzie et al.

    Spatial prediction of soil properties using environmental correlation

    Geoderma

    (1999)
  • A Abdollahzadeh et al.

    Predict soil erosion with artificial neural network in Tanakami (Japan)

    WSEAS T Comput

    (2011)
  • F Amegashie et al.

    Using complex permittivity and artificial neural networks to identify and classify copper, zinc, and lead contamination in soil

    Can Geotech J

    (2006)
  • M Amini et al.

    Neural network models to predict cation exchange capacity in arid regions of Iran

    Eur J Soil Sci

    (2005)
  • M Bagheri Bodaghabadi

    Applied Land Evaluation and Land Use Planning (in Persian)

    (2011)
  • S Banu Ikizler et al.

    Prediction of swelling pressures of expansive soils using artificial neural networks

    Adv Eng Softw

    (2010)
  • T Behrens et al.

    Digital soil mapping using artificial neural networks

    J Plant Nutr Soil Sci

    (2005)
  • C Bishop

    Neural Networks for Pattern Recognition

    (1995)
  • R G Congalton et al.

    A quantitative method to test for consistency and correctness in photointerpretation

    Photogramm. Eng Rem Sens

    (1983)
  • T R Forbes et al.

    Guidelines for Evaluating the Adequacy of Soil Resource Inventories

    (1982)
  • M Gahegan

    On the application of inductive machine learning tools to geographical analysis

    Geogr Anal

    (2000)
  • M Gahegan

    Is inductive machine learning just another wild goose (or might it lay the golden egg)?

    Int J Geogr Inf Sci

    (2003)
  • P E Gessler et al.

    Modeling soil-landscape and ecosystem properties using terrain attributes

    Soil Sci Soc Am J

    (2000)
  • Geological Survey and Mineral Exploration of Iran

    Geological Map of Borujen (Sheet No. 6253)

    (2008)
  • Cited by (75)

    • Carbon sequestration potential in croplands in Lesotho

      2022, Ecological Modelling
      Citation Excerpt :

      The regmodel Suite function in R software was used to assess different models and select the best regression method. Ten machine learning approaches were tested:`1 Linear Model (GLM) (Nelder, 1977), Random Forest (RF) (Breiman, 2001), Support Vector Machine (SVM) (Vapnik, 2000), Boosting generalized linear model (BGLM) (), Classification and regression tree with bagging (BCART) (Breiman, 1996), Cubist (Quinlan et al., 1993), Classification and regression tree (CART),(Breiman et al., 1984), Ranger Random Forest (Ranger) (Wright and Ziegler, 2017), quantile regression forest (QRF) (Vaysse and Lagacherie, 2017), and quantitative neural network (QNR) (Bagheri Bodaghabadi et al., 2015). Cubist, RF, QRF, Ranger, CART and BCART are decision tree algorithms that differ based on their ways of dealing with variance reduction (Padarian et al., 2020).

    View all citing articles on Scopus
    View full text