Inductive machine learning for improved estimation of catchment-scale snow water equivalent

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "David Buckingham and Christian Skalka and 
                 Josh Bongard",
  title =        "Inductive machine learning for improved estimation of
                 catchment-scale snow water equivalent",
  journal =      "Journal of Hydrology",
  volume =       "524",
  pages =        "311--325",
  year =         "2015",
  ISSN =         "0022-1694",
  DOI =          "doi:10.1016/j.jhydrol.2015.02.042",
  URL =          "",
  abstract =     "Summary Infrastructure for the automatic collection of
                 single-point measurements of snow water equivalent
                 (SWE) is well-established. However, because SWE varies
                 significantly over space, the estimation of SWE at the
                 catchment scale based on a single-point measurement is
                 error-prone. We propose low-cost, lightweight methods
                 for near-real-time estimation of mean catchment-wide
                 SWE using existing infrastructure, wireless sensor
                 networks, and machine learning algorithms. Because
                 snowpack distribution is highly nonlinear, we focus on
                 Genetic Programming (GP), a nonlinear, white-box,
                 inductive machine learning algorithm. Because we did
                 not have access to near-real-time catchment-scale SWE
                 data, we used available data as ground truth for
                 machine learning in a set of experiments that are
                 successive approximations of our goal of catchment-wide
                 SWE estimation. First, we used a history of maritime
                 snowpack data collected by manual snow courses. Second,
                 we used distributed snow depth (HS) data collected
                 automatically by wireless sensor networks. We compared
                 the performance of GP against linear regression (LR),
                 binary regression trees (BT), and a widely used basic
                 method (BM) that naively assumes non-variable snowpack.
                 In the first experiment set, GP and LR models predicted
                 SWE with lower error than BM. In the second experiment
                 set, GP had lower error than LR, but outperformed BT
                 only when we applied a technique that specifically
                 mitigated the possibility of over-fitting.",
  keywords =     "genetic algorithms, genetic programming, Snow water
                 equivalent, Machine learning, Wireless sensor network,
                 Snowpack modelling",

Genetic Programming entries for David Buckingham Christian Skalka Josh C Bongard