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

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.

[1]  J. Hillier,et al.  Seamount detection and isolation with a modified wavelet transform , 2008 .

[2]  P. J. Fox,et al.  Volcanic growth faults and the origin of Pacific abyssal hills , 1996, Nature.

[3]  R. Govindaraju,et al.  Geomorphology-based artificial neural networks (GANNs) for estimation of direct runoff over watersheds , 2003 .

[4]  J. Hillier,et al.  Global distribution of seamounts from ship‐track bathymetry data , 2007 .

[5]  D. Sandwell,et al.  Global distribution of seamounts from Seasat profiles , 1988 .

[6]  P. Wessel,et al.  New global seamount census from altimetry-derived gravity data , 2011 .

[7]  P. Wessel,et al.  Distribution of large Pacific seamounts from Geosat/ERS-1 : Implications for the history of intraplate volcanism , 1997 .

[8]  Deborah K. Smith,et al.  Seamount statistics in the Pacific Ocean , 1988 .

[9]  T. Blaschke,et al.  Automated classification of landform elements using object-based image analysis , 2006 .

[10]  D. Sandwell,et al.  Global seafloor topography from dense satellite altimetry and sparse ship soundings , 1997 .

[11]  Walter H. F. Smith,et al.  Free software helps map and display data , 1991 .

[12]  W. A. Sandham,et al.  Geophysical Applications of Artificial Neural Networks and Fuzzy Logic (Modern Approaches in Geophysics, V. 21) , 2003 .

[13]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[14]  A. Rogers,et al.  The global distribution of seamounts based on 30 arc seconds bathymetry data , 2011 .

[15]  H. W. Menard.  Geology of the pacific sea floor , 1959, Experientia.

[16]  Mirko van der Baan,et al.  Neural networks in geophysical applications , 2000 .

[17]  R. J. Pike,et al.  Automated classifications of topography from DEMs by an unsupervised nested-means algorithm and a three-part geometric signature , 2007 .

[18]  D. Fabre,et al.  Global Bathymetry and Elevation Data at 30 Arc Seconds Resolution: SRTM30_PLUS , 2009 .

[19]  Andrew P. Valentine,et al.  Data space reduction, quality assessment and searching of seismograms: autoencoder networks for waveform data , 2012 .

[20]  L. Ermini,et al.  Artificial Neural Networks applied to landslide susceptibility assessment , 2005 .

[21]  Friedrich Quiel,et al.  A semi-automatic method for analysis of landscape elements using Shuttle Radar Topography Mission and Landsat ETM+ data , 2009, Comput. Geosci..

[22]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[23]  S. Lai,et al.  INFERENCES ON POTENTIAL SEAMOUNT LOCATIONS FROM MID-RESOLUTION BATHYMETRIC DATA , 2015 .

[24]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[25]  T. Pitcher,et al.  Abundance and distribution of seamounts in the Azores , 2008 .

[26]  C.J.H. Mann,et al.  Geophysical Applications of Artificial Neural Networks and Fuzzy Logic , 2006 .