A Genetic Programming Approach to Estimate Vegetation Cover in the Context of Soil Erosion Assessment

Created by W.Langdon from gp-bibliography.bib Revision:1.4216

  author =       "Cesar Puente and Gustavo Olague and 
                 Stephen V. Smith and Stephen H. Bullock and 
                 Alejandro Hinojosa-Corona and Miguel Angel Gonzalez-Botello",
  title =        "A Genetic Programming Approach to Estimate Vegetation
                 Cover in the Context of Soil Erosion Assessment",
  journal =      "Photogrammetric Engineering \& Remote Sensing",
  year =         "2011",
  volume =       "77",
  number =       "4",
  pages =        "363--376",
  month =        apr,
  email =        "olague@cicese.mx",
  keywords =     "genetic algorithms, genetic programming, vegetation
                 indices, remote sensing",
  URL =          "http://cienciascomp.cicese.mx/evovision/olague-pers-2011.pdf",
  URL =          "http://digital.ipcprintservices.com/publication/?i=65049&p=65",
  size =         "14 pages",
  abstract =     "This work describes a genetic programming (GP)
                 approach that creates vegetation indices (VI's) to
                 automatically detect the sum of healthy, dry, and dead
                 vegetation. Nowadays, it is acknowledged that VI's are
                 the most popular method for extracting vegetation
                 information from satellite imagery. In particular,
                 erosion models like the ``Revised Universal Soil Loss
                 Equation'' (RUSLE) can use VI's as input to measure the
                 effects of the RUSLE soil cover factor (C). However,
                 the results are generally incomplete, because most
                 indices recognise only healthy vegetation. The aim of
                 this study is to devise a novel approach for designing
                 new VI's that are better - correlated with C, using
                 field and satellite information. Our approach consists
                 on stating the problem in terms of optimisation through
                 GP learning, building novel indices by iteratively
                 recombining a set of numerical operators and spectral
                 channels until the best composite operator is found.
                 Experimental results illustrate the efficiency and
                 reliability of our approach in contrast with
                 traditional indices like those of the NDVI and SAVI
                 family. This study provides evidence that similar
                 problems related to soil erosion assessment could be
                 analysed with our proposed methodology.",
  notes =        "'improved correlation coefficients with C factor field
                 samples, and actually it gives reasonable better
                 performance than widely-used indices such as NDVI and
                 an alternative to RVI, ... RVI4.'

                 Todos Santos watershed in Mexico.

                 0099-1112/11/7704 0363/$3.00/0",

Genetic Programming entries for Cesar Puente Gustavo Olague Stephen V Smith Stephen H Bullock Alejandro Hinojosa Corona Miguel A Gonzalez-Botello