Support vector regression snow-depth retrieval algorithm using passive microwave remote sensing data

Snow cover is an informative indicator of climate change because it can affect local and regional surface energy and water balance, hydrological processes and climate, and ecosystem function. Passive microwave (PM) remote sensing data have long been used to retrieve snow depth and snow water equivalent with large uncertainties. The objective of this study is to develop snow-depth retrieval algorithm based on support vector regression (SVR) technique using PM remote sensing data and other auxiliary data. Ground-based daily snow depth data from 1223 stations across Eurasian continent were used to construct and validate the snow-depth retrieval algorithm. This SVR snow-depth retrieval algorithm partitioned three snow cover stages, and four land cover types then generated twelve snow-depth models for each phases. A non-linear regression method based on support vector regression (SVR) was used to retrieve snow depth with PM brightness temperatures, location (latitude and longitude), and terrain parameters (elevation) as input data and land cover as auxiliary data. In addition, we compared the performance of the SVR snow-depth retrieval algorithm with four alternative algorithms: the Chang algorithm, the Spectral Polarization Difference (SPD) algorithm, the Artificial/Neural Networks (ANN) and, an algorithm based on linear regression. Comparing results obtained from these five snow-depth retrieval algorithms against the ground-based daily snow depth data, the SVR snow-depth retrieval algorithm performs much superior with reduced uncertainties. We report the results aimed at evaluating the impact of the variation of snow cover stages and land cover types. The preliminary results suggest that the SVR snow-depth algorithm could detect deep snow with high accuracy and decrease the impact of saturation effects. These results suggest that the SVR snow-depth retrieval algorithm integrating PM remote sensing data and other auxiliary data (land cover types, location, terrain, snow cover stage with indirectly considering grain size variation) can be a more efficient and effective algorithm for retrieving snow depth and snow water equivalent over various scales.

[1]  Liyun Dai,et al.  Inter-Calibrating SMMR, SSM/I and SSMI/S Data to Improve the Consistency of Snow-Depth Products in China , 2015, Remote. Sens..

[2]  Parag S. Narvekar,et al.  Assessment of the NASA AMSR-E SWE Product , 2010, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[3]  Alfred T. C. Chang,et al.  Quantifying the uncertainty in passive microwave snow water equivalent observations , 2005 .

[4]  Dorothy K. Hall,et al.  Comparison of snow mass estimates from a prototype passive microwave snow algorithm, a revised algorithm and a snow depth climatology , 1997 .

[5]  Chunlin Huang,et al.  Snow Cover Variations and Controlling Factors at Upper Heihe River Basin, Northwestern China , 2015, Remote. Sens..

[6]  Leung Tsang,et al.  A prototype AMSR-E global snow area and snow depth algorithm , 2003, IEEE Trans. Geosci. Remote. Sens..

[7]  C. Derksen,et al.  Remote sensing of snow depth and snow water equivalent , 2014 .

[8]  Frank J. Wentz,et al.  SSM/I Version-7 Calibration Report , 2012 .

[9]  H. Akaike.  A new look at the statistical model identification , 1974 .

[10]  Dorothy K. Hall,et al.  Influence of depth hoar on microwave emission from snow in northern Alaska , 1987 .

[11]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[12]  David A. Robinson,et al.  Northern Hemisphere spring snow cover variability and change over 1922–2010 including an assessment of uncertainty , 2010 .

[13]  Fuzhong Weng,et al.  Evaluation of Special Sensor Microwave Imager/Sounder (SSMIS) Environmental Data Records , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Norman C. Grody,et al.  Anomalous microwave spectra of snow cover observed from Special Sensor Microwave/Imager measurements , 2000 .

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

[16]  David A. Robinson,et al.  Seasonal Variability of Northern Hemisphere Snow Extent Using Visible Satellite Data , 2000 .

[17]  E. J. Langham,et al.  Determination of snow water equivalent on the Canadian prairies using microwave radiometry , 1986 .

[18]  L. Buydens,et al.  Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel , 2006 .

[19]  Philip W. Mote,et al.  The Response of Northern Hemisphere Snow Cover to a Changing Climate , 2008 .

[20]  Naoki Mizukami,et al.  Towards improved snow water equivalent retrieval algorithms for satellite passive microwave data over the mountainous basins of western USA , 2012 .

[21]  Dan Tarpley,et al.  Enhanced algorithm for estimating snow depth from geostationary satellites , 2007 .

[22]  Ryan Shaun Joazeiro de Baker,et al.  Coarse-grained detection of student frustration in an introductory programming course , 2009, ICER '09.

[23]  R. Armstrong,et al.  Snow depth derived from passive microwave remote-sensing data in China , 2008, Annals of Glaciology.

[24]  Rolf Reichle,et al.  Using a Support Vector Machine and a Land Surface Model to Estimate Large-Scale Passive Microwave Brightness Temperatures Over Snow-Covered Land in North America , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[26]  M. Sturm,et al.  The evidence for shrub expansion in Northern Alaska and the Pan‐Arctic , 2006 .

[27]  Thian Yew Gan,et al.  Retrieval of Snow Water Equivalent Using Passive Microwave Brightness Temperature Data , 2000 .

[28]  Liyun Dai,et al.  Estimation of snow depth from passive microwave brightness temperature data in forest regions of northeast China , 2016 .

[29]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[30]  Richard Kelly,et al.  The AMSR-E Snow Depth Algorithm: Description and Initial Results , 2009 .

[31]  Paolo Bonato,et al.  Using wearable sensors to measure motor abilities following stroke , 2006, International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06).

[32]  Barry E. Goodison,et al.  Discrimination of a wet snowcover using passive microwave satellite data , 1993 .

[33]  Edward G. Josberger,et al.  Siberia snow depth climatology derived from SSM/I data using a combined dynamic and static algorithm , 2004 .

[34]  B. E. Goodison,et al.  Algorithm development for the estimation of snow water equivalent in the boreal forest using passive microwave data , 2003 .

[35]  L. Buydens,et al.  Determination of optimal support vector regression parameters by genetic algorithms and simplex optimization , 2005 .

[36]  Knut Stamnes,et al.  Influence of the depth hoar layer of the seasonal snow cover on the ground thermal regime , 1996 .

[37]  Dara Entekhabi,et al.  Hemispheric-scale climate response to Northern Eurasia land surface characteristics and snow anomalies , 2007 .

[38]  Roger G. Barry,et al.  Changes in North American snowpacks for 1979–2007 detected from the snow water equivalent data of SMMR and SSM/I passive microwave and related climatic factors , 2010 .

[39]  Ian H. Witten,et al.  WEKA: a machine learning workbench , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.

[40]  Martti Hallikainen,et al.  Microwave radiometry of snow , 1989 .

[41]  Chris Derksen,et al.  Influence of Sensor Overpass Time on Passive Microwave-Derived Snow Cover Parameters , 2000 .

[42]  Mary Jo Brodzik,et al.  Hemispheric-scale comparison and evaluation of passive-microwave snow algorithms , 2002, Annals of Glaciology.

[43]  M. Bierkens,et al.  Climate Change Will Affect the Asian Water Towers , 2010, Science.

[44]  B. Forman,et al.  Comparison of passive microwave brightness temperature prediction sensitivities over snow-covered land in North America using machine learning algorithms and the Advanced Microwave Scanning Radiometer , 2015 .

[45]  J. Welker,et al.  Winter Biological Processes Could Help Convert Arctic Tundra to Shrubland , 2005 .

[46]  S. Sathiya Keerthi,et al.  Improvements to the SMO algorithm for SVM regression , 2000, IEEE Trans. Neural Networks Learn. Syst..

[47]  Hongjie Xie,et al.  Spatio-Temporal Change of Snow Cover and Its Response to Climate over the Tibetan Plateau Based on an Improved Daily Cloud-Free Snow Cover Product , 2014, Remote. Sens..

[48]  Tingjun Zhang.  Influence of the seasonal snow cover on the ground thermal regime: An overview , 2005 .

[49]  Jian Wang,et al.  Snow depth and snow water equivalent estimation from AMSR-E data based on a priori snow characteristics in Xinjiang, China , 2012 .

[50]  Mary Jo Brodzik,et al.  An earth-gridded SSM/I data set for cryospheric studies and global change monitoring , 1995 .

[51]  B. Bookhagen,et al.  Assessing uncertainty and sensor biases in passive microwave data across High Mountain Asia , 2016 .

[52]  Dorothy K. Hall,et al.  Remote sensing of snow extent , 2014 .

[53]  Chris Derksen,et al.  The contribution of AMSR-E 18.7 and 10.7 GHz measurements to improved boreal forest snow water equivalent retrievals , 2008 .

[54]  Chris Derksen,et al.  Estimating northern hemisphere snow water equivalent for climate research through assimilation of space-borne radiometer data and ground-based measurements , 2011 .

[55]  A. Strahler.  MODIS Land Cover Product Algorithm Theoretical Basis Document (ATBD) Version 5.0 , 1994 .

[56]  Emmanuel Cosme,et al.  On the assimilation of optical reflectances and snow depth observations into a detailed snowpack model , 2015 .

[57]  L. E. Goodrich,et al.  The influence of snow cover on the ground thermal regime , 1982 .

[58]  Chunlin Huang,et al.  Representativeness errors of point-scale ground-based solar radiation measurements in the validation of remote sensing products , 2016 .

[59]  Wang Lei.  Temporal and Spatial Distribution of Xinjiang Snow Density and Its Consequence , 2007 .

[60]  Hongyi Li,et al.  Downscaling Snow Cover Fraction Data in Mountainous Regions Based on Simulated Inhomogeneous Snow Ablation , 2015, Remote. Sens..

[61]  O. Bulygina,et al.  Changes in snow cover characteristics over Northern Eurasia since 1966 , 2011 .

[62]  Chunlin Huang,et al.  Assimilating passive microwave remote sensing data into a land surface model to improve the estimation of snow depth , 2014 .

[63]  Edward G. Josberger,et al.  A passive microwave snow depth algorithm with a proxy for snow metamorphism , 2002 .

[64]  Tingjun Zhang,et al.  Snow density climatology across the former USSR , 2013 .

[65]  A. B. Tait,et al.  Estimation of Snow Water Equivalent Using Passive Microwave Radiation Data , 1998 .

[66]  J. Townshend,et al.  Global Percent Tree Cover at a Spatial Resolution of 500 Meters: First Results of the MODIS Vegetation Continuous Fields Algorithm , 2003 .

[67]  Dorothy K. Hall,et al.  Effects of snow crystal shape on the scattering of passive microwave radiation , 1999, IEEE Trans. Geosci. Remote. Sens..

[68]  Cesar Azorin-Molina,et al.  Topographic control of snowpack distribution in a small catchment in the central Spanish Pyrenees: intra- and inter-annual persistence , 2014 .

[69]  Norman C. Grody,et al.  Global identification of snowcover using SSM/I measurements , 1996, IEEE Trans. Geosci. Remote. Sens..

[70]  Ian H. Witten,et al.  Data mining in bioinformatics using Weka , 2004, Bioinform..

[71]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[72]  Edward J. Kim,et al.  The effect of spatial variability on the sensitivity of passive microwave measurements to snow water equivalent , 2013 .

[73]  Clement Atzberger,et al.  Object Based Image Analysis and Data Mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas , 2012 .

[74]  Dorothy K. Hall,et al.  Nimbus-7 SMMR derived global snow cover parameters , 1987 .

[75]  J. Schimel,et al.  Increased snow depth affects microbial activity and nitrogen mineralization in two Arctic tundra communities , 2004 .

[76]  Ruhollah Taghizadeh-Mehrjardi,et al.  Comparison of artificial neural network and decision tree models in estimating spatial distribution of snow depth in a semi-arid region of Iran , 2016 .

[77]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[78]  Mary J. Brodzik,et al.  Atmospheric corrections for improved satellite passive microwave snow cover retrievals over the Tibet Plateau. , 2009 .

[79]  M. H. Jones,et al.  Annual CO2 Flux in Dry and Moist Arctic Tundra: Field Responses to Increases in Summer Temperatures and Winter Snow Depth , 2000 .

[80]  Jun Li,et al.  Improved snow depth retrieval by integrating microwave brightness temperature and visible/infrared reflectance , 2015 .

[81]  H. Rott,et al.  On the use of satellite microwave radiometers for large-scale hydrology , 1989 .

[82]  Chris Derksen,et al.  Evaluation of passive microwave snow water equivalent retrievals across the boreal forest/tundra transition of western Canada , 2005 .

[83]  Guangya Zhang,et al.  Support vector machine with a Pearson VII function kernel for discriminating halophilic and non-halophilic proteins , 2013, Comput. Biol. Chem..

[84]  Chris Derksen,et al.  Estimating Snow Water Equivalent Using Snow Depth Data and Climate Classes , 2010 .

[85]  Eric D. Soulis,et al.  Modeling Mackenzie Basin Surface Water Balance during CAGES with the Canadian Regional Climate Model , 2003 .

[86]  Hongjie Xie,et al.  A new approach of dynamic monitoring of 5‐day snow cover extent and snow depth based on MODIS and AMSR‐E data from Northern Xinjiang region , 2012 .

[87]  D. Entekhabi,et al.  The influence of snow cover on northern hemisphere climate variability , 2001 .