A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies

Several approaches were proposed to describe the geomorphology of drainage networks and the abiotic/biotic factors determining their morphology. There is an intrinsic complexity of the explicit qualification of the morphological variations in response to various types of control factors and the difficulty of expressing the cause-effect links. Traditional methods of drainage network classification are based on the manual extraction of key characteristics, then applied as pattern recognition schemes. These approaches, however, have low predictive and uniform ability. We present a different approach, based on the data-driven supervised learning by images, extended also to extraterrestrial cases. With deep learning models, the extraction and classification phase is integrated within a more objective, analytical, and automatic framework. Despite the initial difficulties, due to the small number of training images available, and the similarity between the different shapes of the drainage samples, we obtained successful results, concluding that deep learning is a valid way for data exploration in geomorphology and related fields.

[1]  A. Quesada-Román,et al.  Geomorphology of the Upper General River Basin, Costa Rica , 2018, Journal of Maps.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  J. Radke,et al.  Tsunamis and rapid coastal remodeling: Linking energy and fractal dimension , 2020 .

[4]  D. Turcotte.  Fractals and Chaos in Geology and Geophysics , 1992 .

[5]  T. Stepinski,et al.  Comparing morphologies of drainage basins on Mars and Earth using integral‐geometry and neural maps , 2004 .

[6]  V. S. Zakharov,et al.  The Fractal Geometry of the River Network and Neotectonics of South Sikhote-Alin , 2020, Russian Journal of Pacific Geology.

[7]  R. Sahoo,et al.  Process inference from topographic fractal characteristics in the tectonically active Northwest Himalaya, India , 2020, Earth Surface Processes and Landforms.

[8]  A. Rinaldo,et al.  Fractal River Basins , 2001 .

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[11]  Lutz Prechelt,et al.  Early Stopping - But When? , 2012, Neural Networks: Tricks of the Trade.

[12]  E. Miccadei,et al.  Fractal dimension in Italy: a geomorphological key to interpretation , 2006 .

[13]  M. Meneghetti,et al.  The search for galaxy cluster members with deep learning of panchromatic HST imaging and extensive spectroscopy , 2020, Astronomy & Astrophysics.

[14]  D. Montgomery,et al.  Geomorphic classification of rivers and streams , 2016 .

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  J. Paul Siebert,et al.  Interactive perception based on Gaussian Process classification for house-hold objects recognition & sorting , 2016, 2016 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[17]  Peng Yue,et al.  A machine learning approach for predicting computational intensity and domain decomposition in parallel geoprocessing , 2020, Int. J. Geogr. Inf. Sci..

[18]  Larry S. Davis,et al.  Objects in Action: An Approach for Combining Action Understanding and Object Perception , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  G. Longo,et al.  Automated physical classification in the SDSS DR10. A catalogue of candidate quasars , 2015, 1504.03857.

[20]  Ling Zhang,et al.  Automatic drainage pattern recognition in river networks , 2013, Int. J. Geogr. Inf. Sci..

[21]  V. N. Shats,et al.  The Classification of Objects Based on a Model of Perception , 2017 .

[22]  Yutaka Satoh,et al.  Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection , 2015, ArXiv.

[23]  Mauro Garofalo,et al.  DAMEWARE: A Web Cyberinfrastructure for Astrophysical Data Mining , 2014, 1406.3538.

[24]  Goro Komatsu,et al.  Fluvial geomorphology on Earth-like planetary surfaces: A review. , 2015, Geomorphology.

[25]  W. Dietrich,et al.  Formation of evenly spaced ridges and valleys , 2009, Nature.

[26]  Florentin Wörgötter,et al.  Part-driven Visual Perception of 3D Objects , 2017, VISIGRAPP.

[27]  F. Magdaleno,et al.  Fractal Dimension of the Hydrographic Pattern of Three Large Rivers in the Mediterranean Morphoclimatic System: Geomorphologic Interpretation of Russian (USA), Ebro (Spain) and Volturno (Italy) Fluvial Geometry , 2015, Pure and Applied Geophysics.

[28]  J. G. Lyon,et al.  Quantitative description and classification of drainage patterns , 1988 .

[29]  Leon F. Palafox,et al.  Automated detection of geological landforms on Mars using Convolutional Neural Networks , 2017, Comput. Geosci..

[30]  James J. DiCarlo,et al.  How Does the Brain Solve Visual Object Recognition? , 2012, Neuron.

[31]  B. Charnay,et al.  Titan global climate model: A new 3-dimensional version of the IPSL Titan GCM , 2012 .

[32]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[33]  Chong Chen,et al.  A comparative study among machine learning and numerical models for simulating groundwater dynamics in the Heihe River Basin, northwestern China , 2020, Scientific Reports.

[34]  Massimo Brescia,et al.  Data Deluge in Astrophysics: Photometric Redshifts as a Template Use Case , 2017, DAMDID/RCDL.

[35]  Lesli J. Wood,et al.  Quantitative geomorphology of the Mars Eberswalde delta , 2006 .

[36]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[37]  Richard M. Iverson,et al.  Prediction in geomorphology , 2003 .

[38]  H. Zebker,et al.  Global drainage patterns and the origins of topographic relief on Earth, Mars, and Titan , 2017, Science.

[40]  J. Kirchner,et al.  Branching geometry of valley networks on Mars and Earth and its implications for early Martian climate , 2018, Science Advances.

[41]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[42]  Evan B. Goldstein,et al.  The use of genetic programming to develop a predictor of swash excursion on sandy beaches , 2017 .

[43]  Michael J. O. Pocock,et al.  Data-derived metrics describing the behaviour of field-based citizen scientists provide insights for project design and modelling bias , 2020, Scientific Reports.

[44]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[45]  Hideitsu Hino,et al.  Classification of volcanic ash particles using a convolutional neural network and probability , 2018, Scientific Reports.

[46]  A. D. Howard.  Drainage Analysis in Geologic Interpretation: A Summation , 1967 .

[47]  Alfonso Mejia,et al.  Identification and characterization of dendritic, parallel, pinnate, rectangular, and trellis networks based on deviations from planform self‐similarity , 2008 .

[48]  T. Parker,et al.  Sequence and relative timing of large lakes in Gale crater (Mars) after the formation of Mount Sharp , 2016 .

[49]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[50]  J. Niemann,et al.  Planform geometry and relief characterization of drainage networks in high-relief environments: An analysis of Chilean Andean basins , 2019, Geomorphology.