Automated detection of snow avalanche deposits: segmentation and classification of optical remote sensing imagery

Abstract. Snow avalanches in mountainous areas pose a significant threat to infrastructure (roads, railways, energy transmission corridors), personal property (homes) and recreational areas as well as for lives of people living and moving in alpine terrain. The impacts of snow avalanches range from delays and financial loss through road and railway closures, destruction of property and infrastructure, to loss of life. Avalanche warnings today are mainly based on meteorological information, snow pack information, field observations, historically recorded avalanche events as well as experience and expert knowledge. The ability to automatically identify snow avalanches using Very High Resolution (VHR) optical remote sensing imagery has the potential to assist in the development of accurate, spatially widespread, detailed maps of zones prone to avalanches as well as to build up data bases of past avalanche events in poorly accessible regions. This would provide decision makers with improved knowledge of the frequency and size distributions of avalanches in such areas. We used an object–oriented image interpretation approach, which employs segmentation and classification methodologies, to detect recent snow avalanche deposits within VHR panchromatic optical remote sensing imagery. This produces avalanche deposit maps, which can be integrated with other spatial mapping and terrain data. The object-oriented approach has been tested and validated against manually generated maps in which avalanches are visually recognized and digitized. The accuracy (both users and producers) are over 0.9 with errors of commission less than 0.05. Future research is directed to widespread testing of the algorithm on data generated by various sensors and improvement of the algorithm in high noise regions as well as the mapping of avalanche paths alongside their deposits.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[3]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[4]  D. Mcclung,et al.  The Avalanche Handbook , 1993 .

[5]  Benjamin Zweifel,et al.  New trends of recreational avalanche accidents in Switzerland , 2008 .

[6]  Faith R. Kearns,et al.  Classification of the wildland-urban interface: A comparison of pixel- and object-based classifications using high-resolution aerial photography , 2008, Comput. Environ. Urban Syst..

[7]  Teng Wang,et al.  Time-Series InSAR Applications Over Urban Areas in China , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  M Edwin.  “Avalanche risk assessment a multi temporal approach, results from Galtür, Austria“, de M. Keiler, R. Sailer, P. Jörg, C. Weber, S. Fuchs, A. Zischg, and S. Sauermoser , 1970 .

[9]  A Model of Initial Failure in Slab-Avalanche Release , 1989 .

[10]  Andreas Paul Zischg,et al.  Avalanche risk assessment – a multi-temporal approach, results from Galtür, Austria , 2006 .

[11]  Moncef Gabbouj,et al.  Rock Texture Retrieval Using Gray Level Co-occurrence Matrix , 2002 .

[12]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

[13]  Marc Christen,et al.  RAMMS: numerical simulation of dense snow avalanches in three-dimensional terrain , 2010 .

[14]  Santiago Beguería,et al.  Validation and Evaluation of Predictive Models in Hazard Assessment and Risk Management , 2006 .

[15]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[16]  J. McKean,et al.  Objective landslide detection and surface morphology mapping using high-resolution airborne laser altimetry , 2004 .

[17]  D. J. Hutchinson,et al.  Evaluating roadside rockmasses for rockfall hazards using LiDAR data: optimizing data collection and processing protocols , 2010, Natural Hazards.

[18]  C. Melchiorre,et al.  Spatial and temporal variations of Norwegian geohazards in a changing climate, the GeoExtreme Project , 2008 .

[19]  Peter Sampl,et al.  Avalanche simulation with SAMOS , 2004, Annals of Glaciology.

[20]  Markus Christen,et al.  Automated detection and mapping of avalanche deposits using airborne optical remote sensing data , 2009 .

[21]  Andreas Kääb,et al.  Monitoring topographic changes in a periglacial high‐mountain face using high‐resolution DTMs, Monte Rosa East Face, Italian Alps , 2011 .

[22]  F. Mantovani,et al.  Remote sensing techniques for landslide studies and hazard zonation in Europe , 1996 .

[23]  J. Jamieson,et al.  Forcing the snow-cover model SNOWPACK with forecasted weather data , 2011 .

[24]  K. Itten,et al.  Rapid mapping with remote sensing data during flooding 2005 in Switzerland by object- based methods - a case study , 2006 .

[25]  Jürg Schweizer,et al.  Snow avalanche formation and dynamics , 2008 .

[26]  C. Kerans,et al.  Digital Outcrop Models: Applications of Terrestrial Scanning Lidar Technology in Stratigraphic Modeling , 2005 .

[27]  B. Sanders.  Evaluation of on-line DEMs for flood inundation modeling , 2007 .

[28]  Christian Ginzler,et al.  High Resolution DEM Generation in High‐Alpine Terrain Using Airborne Remote Sensing Techniques , 2012, Trans. GIS.

[29]  R. Colombo,et al.  Integration of remote sensing data and GIS for accurate mapping of flooded areas , 2002 .

[30]  Gao Yan,et al.  Pixel based and object oriented image analysis for coal fire research , 2003 .

[31]  Yves Bühler,et al.  Sensitivity of snow avalanche simulations to digital elevation model quality and resolution , 2011, Annals of Glaciology.

[32]  G. Willhauck,et al.  Comparison of object oriented classification techniques and standard image analysis for the use of change detection between SPOT multispectral satellite images and aerial photos. , 2000 .