I'm new to GIS. Is machine learning used much in this field, and where?

I'm investigating a job opportunity with a mapping company working on traffic awareness. My background is in supervised machine learning (in text classification) and some use of Hadoop, and they assure me that my skills would be appropriate. I've been interested in GPS and GIS for some time, but I want to make sure that my machine learning skills (which I've invested in heavily -- including an MS degree) would be put to good use.

  • 3
    Can you elaborate a bit more regarding your land-cover and data-mining tags and how they relate to machine learning. Within most remote sensing/GIS applications the method of supervised classification are used for created land-cover coverages. – artwork21 Mar 12 '13 at 17:52
  • I added those tags almost randomly. The 'land-classification' tag was the only one that had the word 'classification', which is related to supervised machine learning. – stackoverflowuser2010 Mar 12 '13 at 19:29
  • 1
    Have you looked into pattern recognition? – Kirk Kuykendall Mar 12 '13 at 20:28

I do not really see the applicability of Machine Learning with GPS data. However, I utilize these type of modeling techniques on spatial/GIS databases for a large variety of applications. I would imagine that, in fact, these skills would be highly valued indeed.

Methods encompassing supervised and unsupervised data mining, machine learning and nonparamertic modeling can be used in a large variety of spatially related questions including: landcover classification, event clustering, nonlinear inference of spatial process, etc... In addition, given your familiarity with these methods, I would not underestimate your capacity for implementing other types of statistical modeling including spatial statistics.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.