Modeling and Classification of Alluvial Fans with DEMs and Machine Learning Methods: A Case Study of Slovenian Torrential Fans

Alluvial (torrential) fans, especially those created from debris-flow activity, often endanger built environments and human life. It is well known that these kinds of territories where human activities are favored are characterized by increasing instability and related hydrological risk; therefore, treating the problem of its assessment and management is becoming strongly relevant. The aim of this study was to analyze and model the geomorphological aspects and the physical processes of alluvial fans in relation to the environmental characteristics of the territory for classification and prediction purposes. The main geomorphometric parameters capable of describing complex properties, such as relative fan position depending on the neighborhood, which can affect their formation or shape, or properties delineating specific parts of fans, were identified and evaluated through digital elevation model (DEM) data. Five machine learning (ML) methods, including a hybrid Euler graph ML method, were compared to analyze the geomorphometric parameters and physical characteristics of alluvial fans. The results obtained in 14 case studies of Slovenian torrential fans, validated with data of the empirical model proposed by Bertrand et al. (2013), confirm the validity of the developed method and the possibility to identify alluvial fans that can be considered as debris-flow prone.

[1]  N. Shah,et al.  Implementing Machine Learning in Health Care - Addressing Ethical Challenges. , 2018, The New England journal of medicine.

[2]  Frank Harary,et al.  Graph Theory , 2016 .

[3]  Ludvik Trauner,et al.  Relationship between the Undrained Shear Strength, Water Content, and Mineralogical Properties of Fine-Grained Soils , 2005 .

[4]  M. Mikoš,et al.  Estimation of magnitudes of debris flows in selected torrential watersheds in Slovenia , 2006 .

[5]  Huiping Zhang,et al.  Geomorphometric features of the alluvial fans around the Chaka-Qinghai Lake in the northeastern Tibetan Plateau , 2014, Journal of Earth Science.

[6]  Matjaž Mikoš,et al.  Case Study: Numerical Simulations of Debris Flow below Stoze, Slovenia , 2006 .

[7]  Challenging Calibration in 3D Rockfall Modelling , 2013 .

[8]  V. Ganti,et al.  Experimental river delta size set by multiple floods and backwater hydrodynamics , 2016, Science Advances.

[9]  H. Piégay,et al.  Debris-flow susceptibility of upland catchments , 2013, Natural Hazards.

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

[11]  Determination of controlled limit value of groundwater level depth and management practice in Xi’an, China , 2020, Scientific reports.

[12]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[13]  S. Clemens,et al.  Combined high- and low-latitude forcing of East Asian monsoon precipitation variability in the Pliocene warm period , 2020, Science Advances.

[14]  Jurij Mihelič,et al.  Complex Network Characterization Using Graph Theory and Fractal Geometry: The Case Study of Lung Cancer DNA Sequences , 2020, Applied Sciences.

[15]  Marko Komac,et al.  Model dovzetnosti za pojavljanje drobirskih tokov v Sloveniji v merilu 1 : 250.000 Debris-flow susceptibility model of Slovenia at scale 1 : 250,000 , 2009 .

[16]  Jonathan L. Mitchell,et al.  Regional patterns of extreme precipitation on Titan consistent with observed alluvial fan distribution , 2017 .

[17]  Manfred F. Buchroithner,et al.  Automated delineation of debris-covered glaciers based on ASTER data , 2007 .

[18]  G. Miliaresis,et al.  Extraction and Delineation of Alluvial Fans from Digital Elevation Models and Landsat Thematic Mapper Images , 2000 .

[19]  Angelos Tzotsos,et al.  AUTOMATIC EXTRACTION OF ALUVIAL FANS FROM ASTER L 1 SATELLITE DATA AND A DIGITAL ELEVATION MODEL USING OBJECT-ORIENTED IMAGE ANALYSIS , 2004 .

[20]  S. Wilson,et al.  Persistence of intense, climate-driven runoff late in Mars history , 2019, Science Advances.

[21]  Mayank Pandey,et al.  Hybrid classification and regression models via particle swarm optimization auto associative neural network based nonlinear PCA , 2013, Int. J. Hybrid Intell. Syst..

[22]  R. Rajar,et al.  Numerical simulation of debris flows triggered from the Strug rock fall source area, W Slovenia , 2006 .

[23]  Lorenzo Marchi,et al.  GIS morphometric indicators for the analysis of sediment dynamics in mountain basins , 2005 .

[24]  Marius Kloft,et al.  Bayesian Nonlinear Support Vector Machines for Big Data , 2017, ECML/PKDD.

[25]  S. Tulaczyk,et al.  Late Quaternary glaciation of the Upper Soča River Region (Southern Julian Alps, NW Slovenia) , 2004 .

[26]  B. Dolinar,et al.  Correlation between surface area and Atterberg Limits of fine-grained soils , 2007 .

[27]  R. French.  Hydraulic Processes on Alluvial Fans , 2012 .

[28]  C. Fragassa,et al.  Surface roughness evaluation in hardened materials by pattern recognition using network theory , 2018, International Journal on Interactive Design and Manufacturing (IJIDeM).

[29]  Tomaž Podobnikar,et al.  Towards the automated geomorphometric extraction of talus slopes in Martian landscapes , 2015 .

[30]  M. Komac.  Geohazard - geolo{ko pogojena nevarnost zaradi procesov pobo~nega premikanja. Primer ob~ine Bovec Estimation of geohazard induced by mass movement processes. The Bovec municipality case study , 2005 .

[31]  S. Leroueil,et al.  The Varnes classification of landslide types, an update , 2014, Landslides.

[32]  K. Oštir,et al.  Monitoring the Potoška planina landslide (NW Slovenia) using UAV photogrammetry and tachymetric measurements , 2017, Landslides.

[33]  Stephan R. Sain.  Analysis and Modelling of Spatial Environmental Data , 2006 .

[34]  M. Komac,et al.  Debris-flowsusceptibilitymodelofSloveniaatscale1:250,000 , 2009 .

[35]  S. Rajendran,et al.  Mapping and accuracy assessment of siltation of recharge dams using remote sensing technique , 2020, Scientific Reports.

[36]  Miha Kovacic,et al.  Prediction of the natural gas consumption in chemical processing facilities with genetic programming , 2016, Genetic Programming and Evolvable Machines.

[37]  G. Sofia.  Combining geomorphometry, feature extraction techniques and Earth-surface processes research: The way forward , 2020 .

[38]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[39]  Saharon Rosset,et al.  Lossless Compression of Random Forests , 2019, Journal of Computer Science and Technology.

[40]  Yue-Hong Chou,et al.  Exploring spatial analysis in geographic information systems , 1997 .

[41]  Václav Snásel,et al.  Metaheuristic design of feedforward neural networks: A review of two decades of research , 2017, Eng. Appl. Artif. Intell..

[42]  Rita Ambu,et al.  New Method for Estimating Fractal Dimension in 3D Space and Its Application to Complex Surfaces , 2019, International Journal on Advanced Science, Engineering and Information Technology.

[43]  J. Tegowski,et al.  Spectral features of dual-frequency multibeam echosounder data for benthic habitat mapping , 2020 .

[44]  Andrej Mrvar,et al.  A New Method for Biostatistical miRNA Pattern Recognition with Topological Properties of Visibility Graphs in 3D Space , 2019, Journal of healthcare engineering.