Improved snow depth retrieval by integrating microwave brightness temperature and visible/infrared reflectance

Abstract The accuracy of snow depth retrieval by remote sensing depends heavily on the characteristics of the snow, and both passive microwave and visible/infrared sensors can contribute to the acquisition of this information. A method integrating these two remotely sensed data sets is presented in this study. Snow depth retrieval is performed using microwave brightness temperature at 19 and 37 GHz from the Special Sensor Microwave/Imager (SSM/I) and the Special Sensor Microwave Image/Sounder (SSMI/S), and visible/infrared surface reflectance from Moderate Resolution Imaging Spectroadiometer (MODIS) products. Microwave brightness temperature provides information about the volume of snow pack, and visible/infrared surface reflectance can indicate snow presence and surface grain size. With these two remote sensing data sets, snow depth is retrieved by a nonlinear data mining technique, the modified sequential minimal optimization (SMO) algorithm for support vector machine (SVM) regression. The proposed method is tested by using 16,329 records of dry snow measured at 54 meteorological stations in Xinjiang, China over an area of 1.6 million km2 from 2000 to 2009. The root mean square error (RMSE), relative RMSE and the correlation coefficient of our method are 6.21 cm, 0.64 and 0.87, respectively. These results are better than those obtained using only brightness temperature data (8.80 cm, 0.90 and 0.73), the traditional spectral polarization difference (SPD) algorithm (15.07 cm, 1.54 and 0.58), a modified Chang algorithm in WESTDC (9.80 cm, 1.00 and 0.62), or the multilayer perceptron classifier of artificial neural networks (ANN) (9.23 cm, 0.94 and 0.72). The daily snow water equivalent (SWE) retrieved by this method has an RMSE of 8.05 mm and a correlation of 0.84, which are better than those of NASA NSIDC (32.87 mm and 0.47) or Globsnow (19.07 mm and 0.59). This study demonstrates that the combination of visible/infrared surface reflectance and microwave brightness temperature via an SVM regression can provide a more accurate retrieval of snow depth.

[1]  Manuela Grippa,et al.  Comparison between the interannual variability of snow parameters derived from SSM/I and the Ob river discharge , 2005 .

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

[3]  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 .

[4]  Matthias Rychetsky,et al.  Algorithms and architectures for machine learning based on regularized neural netwoks and support vector approaches , 2001 .

[5]  Albert Rango,et al.  Algorithm Theoretical Basis Document (ATBD) for the AMSR-E Snow Water Equivalent Algorithm , 2000 .

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

[7]  T. Barnett,et al.  Potential impacts of a warming climate on water availability in snow-dominated regions , 2005, Nature.

[8]  Jian Wang,et al.  Toward an improved data stewardship and service for environmental and ecological science data in West China , 2011, Int. J. Digit. Earth.

[9]  Yinsuo Zhang,et al.  Impact of snow cover on soil temperature and its simulation in a boreal aspen forest , 2008 .

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

[11]  T. Painter,et al.  Retrieval of subpixel snow-covered area and grain size from imaging spectrometer data , 2003 .

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

[13]  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.

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

[15]  D. Lettenmaier,et al.  Assimilating remotely sensed snow observations into a macroscale hydrology model , 2006 .

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

[17]  Riccardo Scalenghe,et al.  Changes in the seasonal snow cover of alpine regions and its effect on soil processes: A review , 2007 .

[18]  J. Pulliainen.  Retrieval of Regional Snow Water Equivalent from Space-Borne Passive Microwave Observations , 2001 .

[19]  Steven A. Margulis,et al.  Correcting first‐order errors in snow water equivalent estimates using a multifrequency, multiscale radiometric data assimilation scheme , 2007 .

[20]  Bo-Cai Gao,et al.  Effect of ice crystal shape and effective size on snow bidirectional reflectance , 2006 .

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

[22]  Chris Derksen,et al.  Assessment of spring snow cover duration variability over northern Canada from satellite datasets , 2007 .

[23]  Roberto Salzano,et al.  Correlation between the specific surface area and the short wave infrared (SWIR) reflectance of snow , 2006 .

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

[25]  Leung Tsang,et al.  Dense media radiative transfer theory based on quasicrystalline approximation with applications to passive microwave remote sensing of snow , 2000 .

[26]  C. M. DeChant,et al.  Radiance data assimilation for operational snow and streamflow forecasting , 2011 .

[27]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[28]  Hongjie Xie,et al.  Toward improved daily snow cover mapping with advanced combination of MODIS and AMSR-E measurements , 2008 .

[29]  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 .

[30]  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 .

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

[32]  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 .

[33]  Desheng Liu,et al.  The need for prior information in characterizing snow water equivalent from microwave brightness temperatures , 2012 .

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

[35]  Jenq-Neng Hwang,et al.  Retrieval of snow parameters by iterative inversion of a neural network , 1993, IEEE Trans. Geosci. Remote. Sens..

[36]  Hongjie Xie,et al.  Evaluation of MODIS snow cover and cloud mask and its application in Northern Xinjiang, China , 2008 .

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

[38]  Dara Entekhabi,et al.  Eurasian snow cover variability and northern hemisphere climate predictability , 1999 .

[39]  Helmut Rott,et al.  Microwave emission of snow-covered and snow-free terrain from satellite measurements , 1989 .