Re: Accuracy assessment and spatial autocorrelation

From: Phil Nott (pnott@birdpop.org)
Date: Wed May 05 2004 - 17:04:14 PDT

  • Next message: Bob Powell: "Re: Accuracy assessment and spatial autocorrelation"

    Jonathon

    I've been wanting to explore the IKONOS dataset for a while now. Did you
    get hold of data at a reasonable cost?

    Phil

    At 03:34 PM 5/5/04, you wrote:
    >Remote Sensors:
    >
    > Me and a colleague (who shall remain unnamed... We will refer to him as
    >Solomon D.) are having a lively discussion about training/test data with
    >remote sensing and I was hoping to get some additional feedback on this
    >problem. We created a species map with maximum likelihood (using 1m IKONOS
    >imagery), and here's how we created training data (and how we are
    >approaching, in one case, the testing):
    >
    > We have mostly USFS plot data with a known center location and plot
    >boundary, and that has cover values for each species we are after in our
    >classification. We choose pixels from plots with a high percentage of a
    >single species, that are readily identifiable as the species in question
    >(e.g. If we know a plot only contains red fir trees, we manually choose each
    >pixel belonging to a tree within the boundary of the plots). This, of
    >course, is not an optimal way of doing this -- in theory we should have
    >collected individual species in the field, but this was our curse with the
    >data we had.
    >
    > Ok, so now we have a bunch of pixels per class, taken from a limited
    >number of plots (e.g. We may have 1000 red fir pixels, but we took them from
    >10 plots). The questions is, is it "legitimate" to subdivide the 1000
    >pixels into two randomly chosen training and test groups (say 60% train and
    >40% test), and use the 60% to create the map, and validate it with the
    >remaining 40%, OR do we have a problem with spatial autocorrelation problem
    >because, while we have 1000s of pixels, the training and test pixels are all
    >right next to each other in the 10 plots.
    >
    > In my mind the issue is muddled, because we are training based on color,
    >and is does the color (within a class) have a strong enough spatial pattern
    >to warrant a very different training/test setup (e.g. Taking the pixels from
    >6/10 plots for training and 4/10 for testing?) Thoughts?
    >
    >--j
    >
    >--
    >Jonathan Greenberg
    >Graduate Group in Ecology, U.C. Davis
    >http://www.cstars.ucdavis.edu/~jongreen
    >http://www.cstars.ucdavis.edu
    >AIM: jgrn307 or jgrn3007
    >MSN: jgrn307@msn.com or jgrn3007@msn.com

    _________________________________________
    M. Philip Nott, Ph.D.
    Research Ecologist
    The Institute for Bird Populations
    PO Box 1346
    11435 State Route 1, Suite 23
    Point Reyes Station CA 94956-1346

    Voice: (415) 663-2050 Fax: (415) 663-9482

    email: pnott@birdpop.org
    Visit our website www.birdpop.org
    ___________________________________________________________

    "In ancient times they had no statistics
        - so they had to fall back on lies."
                             Stephen Leacock.



    This archive was generated by hypermail 2b29 : Wed May 05 2004 - 17:02:17 PDT