About Us | Help Videos | Contact Us | Subscriptions
 

Abstract

 

This article in CS

  1. Vol. 38 No. 4, p. 1035-1041
     
    Received: May 15, 1997


    * Corresponding author(s): voigt@kbml.hort.uiuc.edu
 View
 Download
 Alerts
 Permissions
Request Permissions
 Share

doi:10.2135/cropsci1998.0011183X003800040025x

Selecting Kentucky Bluegrass Cultivars

  1. T. B. Voigt ,
  2. T. W. Fermanian and
  3. W. C. Sullivan
  1. Dep. of Natural Resources and Environmental Sciences, Univ. of Illinois at Urbana-Champaign, 1102 S. Goodwin Ave., Urbana, IL 61801

Abstract

Abstract

A computer-aided learning process has been previously developed to identify unique turfgrass cultivar performance levels under specific growing conditions. However, it was not determined if this process was similar to the routine assessments made by turfgrass experts. A survey was sent to 191 turfgrass experts to determine turf cultivar recommendation consistency, to validate a set of computer developed rules of association, and to determine the environmental and management characteristics the experts considered most influential on turfgrass cultivar performance. Seventy completed surveys, mostly from respondents who had worked professionally for at least 10 yr at Land Grant universities, were returned. In the first section of the survey, experts showed a high degree of consistency in recommending Kentucky bluegrass (Poa pratensis L.) cultivars for specific settings. In the second section of the survey, there was inconsistent agreement among survey respondents and machine learning output when presented with rules associating cultivar performance and turf settings. Finally, when asked to indicate which environment or management parameters experts felt most influence performance of specific Kentucky bluegrass cultivars, survey respondents selected mowing height, nitrogen fertilization levels, and irrigation. The computer-aided learning process also identified mowing height and nitrogen fertilization levels as influencing cultivar performance. The machine learning process also selected soil pH and average monthly air temperature as influential. Thus, there was not overall agreement between survey respondents and machine learning output.

Contribution from the Illinois Agric. Exp. Stn. This study was partially supported by the Illinois Turfgrass Foundation.

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

Copyright © .