My Account: Log In | Join | Renew
Search
Author
Title
Vol.
Issue
Year
1st Page

Abstract

 

This article in SSSAJ

  1. Vol. 68 No. 3, p. 885-894
     
    Received: Apr 25, 2002
    Published: May, 2004


    * Corresponding author(s): xun.shi@dartmouth.edu
 View
 Download
 Alerts
 Permissions
 Share

doi:10.2136/sssaj2004.8850

A Case-based Reasoning Approach to Fuzzy Soil Mapping

  1. Xun Shi *a,
  2. A-Xing Zhubc,
  3. James E. Burtc,
  4. Feng Qic and
  5. Duane Simonsond
  1. a Dep. of Geography, Dartmouth College, 6017 Fairchild, Hanover, NH 03755
    b State Key Lab of Resources and Environmental Information Systems, Inst. of Geographical Sciences and Natural Resources Res., Chinese Academy of Sciences, Building 917, Datun Road, An Wai, Beijing 100101, China
    c Dep. of Geography, University of Wisconsin-Madison, 550 North Park Street, Madison, WI 53706
    d NRCS-USDA, 1850 Bohmann Drive, Suite C, Richland Center, WI 53581

Abstract

Some problems in traditional soil mapping—high cost, high subjectivity, poor documentation, and low accuracy and precision—have motivated the development of a knowledge-based fuzzy soil mapping system, named SoLIM (Soil Land Inference Model). The rule-based method of the current SoLIM has its limitations. It requires explicit knowledge of the details of soil–environment relationships and it assumes that the environmental variables are independent from each other. This paper presents a case-based reasoning (CBR) approach as an alternative to the rule-based method. Case-based reasoning uses knowledge in the form of specific cases to solve a new problem, and the solution is based on the similarities between the new problem and the available cases. With the CBR method, soil scientists express their knowledge by providing locations (cases) indicating the association between a soil and a landscape or environmental configuration. In this way, the soil scientists avoid the difficulties associated with depicting the details of a soil–environment relationship and assuming the independence of environmental variables. The CBR inference engine computes the similarity between the environmental configuration at a given location and that associated with each case representing a soil type, and then uses these similarity values to approximate the similarity of the local soil at the given location to the given soil type. A case study in southwestern Wisconsin demonstrates that CBR can be an easy and effective way for soil scientists to express their knowledge. For the study area, the result from the CBR inference engine is more accurate than that from the traditional soil mapping process. Case-based reasoning can be a good solution for a knowledge-based fuzzy soil mapping system.

  Please view the pdf by using the Full Text (PDF) link under 'View' to the left.

Copyright © 2004. Soil Science SocietySoil Science Society of America