Discovery and analysis of topographic features using learning algorithms: a seamount case study

Journal article

Identifying and cataloging occurrences of particular topographic features are important but time-consuming tasks. Typically, automation is challenging, as simple models do not fully describe the complexities of natural features. We propose a new approach, where a particular class of neural network (the “autoencoder”) is used to assimilate the characteristics of the feature to be cataloged, and then applied to a systematic search for new examples. To demonstrate the feasibility of this method, we construct a network that may be used to find seamounts in global bathymetric data. We show results for two test regions, which compare favorably with results from traditional algorithms.

Authors: Valentine, A; Kalnins, L; Trampert, J

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: American Geophysical Union
• Journal: Geophysical Research Letters
• Volume: 40
• Issue: 12
• Pages: 3048–3054
• Publication date: 2013-06-01
• Edition: Publisher's version
• DOI: doi:10.1002/grl.50615
• EISSN: 1944-8007
• Language: English
• Keywords: data and information discovery; geomorphology; neural networks and machine learning; marine geology and geophysics
• Subjects: Pattern recognition (statistics); Marine geology and geophysics; Earth sciences