Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@Article{TaghizadehMehrjardi:2016:Geoderma,
  author =       "R. Taghizadeh-Mehrjardi and K. Nabiollahi and 
                 R. Kerry",
  title =        "Digital mapping of soil organic carbon at multiple
                 depths using different data mining techniques in Baneh
                 region, Iran",
  journal =      "Geoderma",
  volume =       "266",
  pages =        "98--110",
  year =         "2016",
  ISSN =         "0016-7061",
  DOI =          "doi:10.1016/j.geoderma.2015.12.003",
  URL =          "http://www.sciencedirect.com/science/article/pii/S0016706115301543",
  abstract =     "This study aimed to map SOC lateral, and vertical
                 variations down to 1 m depth in a semi-arid region in
                 Kurdistan Province, Iran. Six data mining techniques
                 namely; artificial neural networks, support vector
                 regression, k-nearest neighbour, random forests,
                 regression tree models, and genetic programming were
                 combined with equal-area smoothing splines to develop,
                 evaluate and compare their effectiveness in achieving
                 this aim. Using the conditioned Latin hypercube
                 sampling method, 188 soil profiles in the study area
                 were sampled and soil organic carbon content (SOC)
                 measured. Eighteen ancillary data variables derived
                 from a digital elevation model and Landsat 8 images
                 were used to represent predictive soil forming factors
                 in this study area. Findings showed that normalized
                 difference vegetation index and wetness index were the
                 most useful ancillary data for SOC mapping in the upper
                 (0-15 cm) and bottom (60-100 cm) of soil profiles,
                 respectively. According to 5-fold cross-validation,
                 artificial neural networks (ANN) showed the highest
                 performance for prediction of SOC in the four standard
                 depths compared to all other data mining techniques.
                 ANNs resulted in the lowest root mean square error and
                 highest Lin's concordance coefficient which ranged from
                 0.07 to 0.20 log (kg/m3) and 0.68 to 0.41,
                 respectively, with the first value in each range being
                 for the top of the profile and second for the bottom.
                 Furthermore, ANNs increased performance of spatial
                 prediction compared to the other data mining algorithms
                 by up to 36, 23, 21 and 13percent for each soil depth,
                 respectively, starting from the top of the profile.
                 Overall, results showed that prediction of subsurface
                 SOC variation needs improvement and the challenge
                 remains to find appropriate covariates that can explain
                 it.",
  keywords =     "genetic algorithms, genetic programming, Artificial
                 neural network, Support vector regression, k-nearest
                 neighbour, Random forest, Regression tree model",
}

Genetic Programming entries for R Taghizadeh-Mehrjardi K Nabiollahi R Kerry

Citations