Artificial neural network‐based modeling of snow properties using field data and hyperspectral imagery

This study attempts to model snow wetness and snow density of Himalayan snow cover using a combination of Hyperspectral image processing and Artificial Neural Network (ANN). Initially, a total of 300 spectral signature measurements, synchronized with snow wetness and snow density, were collected in the field. The spectral reflectance of snow was then modeled as a function of snow properties using ANN. Four snow wetness and three snow density models were developed. A strong correlation was observed in near‐infrared and shortwave‐infrared region. The correlation analysis of ANN modeled snow density and snow wetness showed a strong linear relationship with field‐based data values ranging from 0.87–0.90 and 0.88–0.91, respectively. Our results indicate that an Artificial Intelligence (AI) approach, using a combination of Hyperspectral image processing and ANN, can be efficiently used to predict snow properties (wetness and density) in the Himalayan region.

[1]  Satchidananda Dehuri,et al.  Artificial Neural Network , 2020, Encyclopedia of GIS.

[2]  H. S. Negi,et al.  Hyper-spectral data based investigations for snow wetness mapping , 2019 .

[3]  Zolkafle Buntat,et al.  Support vector regression and neural networks analytical models for gas sensor based on molybdenum disulfide , 2018, Microsystem Technologies.

[4]  I. Reusen,et al.  Atmospheric correction of Landsat-8/OLI and Sentinel-2/MSI data using iCOR algorithm: validation for coastal and inland waters , 2018 .

[5]  Dong Xiao,et al.  A Multiple Hidden Layers Extreme Learning Machine Method and Its Application , 2017 .

[6]  Sen Jia,et al.  Convolutional neural networks for hyperspectral image classification , 2017, Neurocomputing.

[7]  Sudarson Jena,et al.  Improved artificial neural network for dimension reduction in medical data classification , 2016, 2016 International Conference on Computing Communication Control and automation (ICCUBEA).

[8]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Xiaogang Wang,et al.  Multi-Bias Non-linear Activation in Deep Neural Networks , 2016, ICML.

[10]  P. Datt,et al.  Experimental investigation of dielectric properties of seasonal snow at field observatories in the northwest Himalaya , 2016, Annals of Glaciology.

[11]  S. K. Singh,et al.  Snow and Glacier Investigations Using Hyperspectral Data in the Himalaya , 2015 .

[12]  M. A. Haq.  COMPARATIVE ANALYSIS OF HYPERSPECTRAL AND MULTISPECTRAL DATA FOR MAPPING SNOW COVER AND SNOW GRAIN SIZE , 2014 .

[13]  K. Jain,et al.  Modelling of Gangotri glacier thickness and volume using an artificial neural network , 2014 .

[14]  M. Babel,et al.  An artificial neural network-based snow cover predictive modeling in the higher Himalayas , 2014, Journal of Mountain Science.

[15]  John Odindi,et al.  A comparison of Normalised Difference Snow Index (NDSI) and Normalised Difference Principal Component Snow Index (NDPCSI) techniques in distinguishing snow from related land cover types , 2014 .

[16]  Snehmani,et al.  Snow-cover characteristics using Hyperion data for the Himalayan region , 2013 .

[17]  Zhaojun Wang,et al.  Snow Grain-Size Estimation Using Hyperion Imagery in a Typical Area of the Heihe River Basin, China , 2013, Remote. Sens..

[18]  E. Hreinsson,et al.  The potential impact of climate change on seasonal snow in New Zealand: part II—industry vulnerability and future snowmaking potential , 2012, Theoretical and Applied Climatology.

[19]  Krista,et al.  A dual-spectrometer approach to reflectance measurements under sub-optimal sky conditions. , 2012, Optics express.

[20]  Mahdi Bashiri,et al.  TUNING THE PARAMETERS OF AN ARTIFICIAL NEURAL NETWORK USING CENTRAL COMPOSITE DESIGN AND GENETIC ALGORITHM , 2011 .

[21]  Christoph Schneider,et al.  Spatio‐temporal prediction of snow cover in the Black Forest mountain range using remote sensing and a recurrent neural network , 2010 .

[22]  A. Kokhanovsky,et al.  Retrieval of snow albedo and grain size using reflectance measurements in Himalayan basin , 2010 .

[23]  Hossein Tabari,et al.  Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran , 2010, Neural Computing and Applications.

[24]  Thomas H. Painter,et al.  Interpretation of snow properties from imaging spectrometry , 2009 .

[25]  Alexei Lyapustin,et al.  Retrieval of snow grain size over Greenland from MODIS. , 2009 .

[26]  Yongjian Ding,et al.  The application of artificial neural networks to simulate meltwater runoff of Keqikaer Glacier, south slope of Mt. Tuomuer, western China , 2009 .

[27]  Thian Yew Gan,et al.  Comparison of snow water equivalent retrieved from SSM/I passive microwave data using artificial neural network, projection pursuit and nonlinear regressions , 2009 .

[28]  Thomas H. Painter,et al.  Retrieval of subpixel snow covered area, grain size, and albedo from MODIS , 2009 .

[29]  E. Berthier,et al.  Neural Networks Applied to Estimating Subglacial Topography and Glacier Volume , 2009 .

[30]  V. Estellés,et al.  Performance of a FieldSpec spectroradiometer for aerosol optical depth retrieval: method and preliminary results. , 2009, Applied optics.

[31]  T. Sauter,et al.  Simulation and analysis of runoff from a partly glaciated meso‐scale catchment area in Patagonia using an artificial neural network , 2009 .

[32]  S. M. Jong,et al.  Large-scale monitoring of snow cover and runoff simulation in Himalayan river basins using remote sensing , 2009 .

[33]  T. Painter,et al.  MODIS-based Mosaic of Antarctica (MOA) data sets: Continent-wide surface morphology and snow grain size , 2007 .

[34]  C. Woodcock,et al.  Scaling Field Data to Calibrate and Validate Moderate Spatial Resolution Remote Sensing Models , 2007 .

[35]  M. Hantel,et al.  Sensitivity of Alpine snow cover to European temperature , 2007 .

[36]  Tshilidzi Marwala,et al.  Machine and component residual life estimation through the application of neural networks , 2007, Reliab. Eng. Syst. Saf..

[37]  Thomas H. Painter,et al.  Measuring the expressed abundance of the three phases of water with an imaging spectrometer over melting snow , 2006 .

[38]  B. Jamieson.  Formation of refrozen snowpack layers and their role in slab avalanche release , 2006 .

[39]  O. Kisi,et al.  Comparison of three back-propagation training algorithms for two case studies , 2005 .

[40]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[41]  Thomas H. Painter,et al.  MULTISPECTRAL AND HYPERSPECTRAL REMOTE SENSING OF ALPINE SNOW PROPERTIES , 2004 .

[42]  J. Dozier,et al.  A Hyperspectral Method for Remotely Sensing the Grain Size of Snow , 2000 .

[43]  Betty L. Hickman,et al.  SPOT Panchromatic Imagery and Neural Networks for Information Extraction in a Complex Mountain Environment , 1999 .

[44]  H. Guterman,et al.  Knowledge extraction from artificial neural network models , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[45]  Martin T. Hagan,et al.  Neural network design , 1995 .

[46]  Jeff Dozier,et al.  Estimating snow grain size using AVIRIS data , 1993 .

[47]  J. Dozier.  Spectral Signature of Alpine Snow Cover from the Landsat Thematic Mapper , 1989 .

[48]  S. Warren,et al.  A Model for the Spectral Albedo of Snow. I: Pure Snow , 1980 .

[49]  S. Warren,et al.  A Model for the Spectral Albedo of Snow. II: Snow Containing Atmospheric Aerosols , 1980 .

[50]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[51]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[52]  S. Dash,et al.  First and Second Order Training Algorithms for Artificial Neural Networks to Detect the Cardiac State , 2017 .

[53]  W. Leeuwen,et al.  Fractional snow cover estimation in complex alpine-forested environments using an artificial neural network , 2015 .

[54]  Mahesh Panchal,et al.  Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network , 2014 .

[55]  P. S. Heyns,et al.  Machine and component residual life estimation through the application of neural networks , 2007, Reliab. Eng. Syst. Saf..

[56]  A. Klein,et al.  Artificial Neural Networks Approach to Fractional Snow Cover Mapping , 2009 .

[57]  Daniel Steiner,et al.  19th century glacier representations and fluctuations in the central and western European Alps: An interdisciplinary approach , 2008 .

[58]  R. Alley,et al.  Antarctic sea ice: a self-organizing map-based perspective , 2007, Annals of Glaciology.

[59]  D. Basak,et al.  Support Vector Regression , 2008 .

[60]  D. A. Moldestad.  Characterisation of liquid water content and snow density in a cross-country race ski track , 2005 .

[61]  A. Walter,et al.  The application of a non-linear back-propagation neural network to study the mass balance of Grosse Aletschgletscher, Switzerland , 2005, Journal of Glaciology.

[62]  M. Tedescoa,et al.  Artificial neural network-based techniques for the retrieval of SWE and snow depth from SSM / I data , 2004 .

[63]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[64]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[65]  Ice.  The international classification for seasonal snow on the ground , 1990 .

[66]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .