Journal cover Journal topic
Earth Surface Dynamics An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 3.765 IF 3.765
  • IF 5-year value: 3.719 IF 5-year
    3.719
  • CiteScore value: 3.83 CiteScore
    3.83
  • SNIP value: 1.281 SNIP 1.281
  • IPP value: 3.61 IPP 3.61
  • SJR value: 1.527 SJR 1.527
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 17 Scimago H
    index 17
  • h5-index value: 18 h5-index 18
Volume 4, issue 2
Earth Surf. Dynam., 4, 445–460, 2016
https://doi.org/10.5194/esurf-4-445-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Special issue: Frontiers in geomorphometry

Earth Surf. Dynam., 4, 445–460, 2016
https://doi.org/10.5194/esurf-4-445-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Review article 30 May 2016

Review article | 30 May 2016

An introduction to learning algorithms and potential applications in geomorphometry and Earth surface dynamics

Andrew Valentine1 and Lara Kalnins2 Andrew Valentine and Lara Kalnins
  • 1Department of Earth Sciences, Universiteit Utrecht, Postbus 80.021, 3508TA Utrecht, the Netherlands
  • 2Department of Earth Sciences, Science Labs, Durham University, Durham, DH1 3LE, UK

Abstract. “Learning algorithms” are a class of computational tool designed to infer information from a data set, and then apply that information predictively. They are particularly well suited to complex pattern recognition, or to situations where a mathematical relationship needs to be modelled but where the underlying processes are not well understood, are too expensive to compute, or where signals are over-printed by other effects. If a representative set of examples of the relationship can be constructed, a learning algorithm can assimilate its behaviour, and may then serve as an efficient, approximate computational implementation thereof. A wide range of applications in geomorphometry and Earth surface dynamics may be envisaged, ranging from classification of landforms through to prediction of erosion characteristics given input forces. Here, we provide a practical overview of the various approaches that lie within this general framework, review existing uses in geomorphology and related applications, and discuss some of the factors that determine whether a learning algorithm approach is suited to any given problem.

Publications Copernicus
Download
Short summary
Learning algorithms are powerful tools for understanding and working with large data sets, particularly in situations where any underlying physical models may be complex and poorly understood. Such situations are common in geomorphology. We provide an accessible overview of the various approaches that fall under the umbrella of "learning algorithms", discuss some potential applications within geomorphometry and/or geomorphology, and offer advice on practical considerations.
Learning algorithms are powerful tools for understanding and working with large data sets,...
Citation