Evolving Spatially Aggregated Features from Satellite Imagery for Regional Modeling

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Kriegman:2016:PPSN,
  author =       "Sam Kriegman and Marcin Szubert and 
                 Josh C. Bongard and Christian Skalka",
  title =        "Evolving Spatially Aggregated Features from Satellite
                 Imagery for Regional Modeling",
  booktitle =    "14th International Conference on Parallel Problem
                 Solving from Nature",
  year =         "2016",
  editor =       "Julia Handl and Emma Hart and Peter R. Lewis and 
                 Manuel Lopez-Ibanez and Gabriela Ochoa and 
                 Ben Paechter",
  volume =       "9921",
  series =       "LNCS",
  pages =        "707--716",
  address =      "Edinburgh",
  month =        "17-21 " # sep,
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming, Spatial
                 aggregation, Feature construction, Symbolic
                 regression",
  isbn13 =       "978-3-319-45823-6",
  DOI =          "doi:10.1007/978-3-319-45823-6_66",
  size =         "10 pages",
  abstract =     "Satellite imagery and remote sensing provide
                 explanatory variables at relatively high resolutions
                 for modelling geospatial phenomena, yet regional
                 summaries are often desirable for analysis and
                 actionable insight. In this paper, we propose a novel
                 method of inducing spatial aggregations as a component
                 of the machine learning process, yielding regional
                 model features whose construction is driven by model
                 prediction performance rather than prior assumptions.
                 Our results demonstrate that Genetic Programming is
                 particularly well suited to this type of feature
                 construction because it can automatically synthesize
                 appropriate aggregations, as well as better incorporate
                 them into predictive models compared to other
                 regression methods we tested. In our experiments we
                 consider a specific problem instance and real-world
                 dataset relevant to predicting snow properties in
                 high-mountain Asia.",
  notes =        "snow melt runoff. NASA. Afganistan. PPSN2016
                 http://ppsn2016.org",
}

Genetic Programming entries for Sam Kriegman Marcin Szubert Josh C Bongard Christian Skalka

Citations