Retrieval of Melt Ponds on Arctic Multiyear Sea Ice in Summer from TerraSAR-X Dual-Polarization Data Using Machine Learning Approaches: A Case Study in the Chukchi Sea with Mid-Incidence Angle Data

Melt ponds, a common feature on Arctic sea ice, absorb most of the incoming solar radiation and have a large effect on the melting rate of sea ice, which significantly influences climate change. Therefore, it is very important to monitor melt ponds in order to better understand the sea ice-climate interaction. In this study, melt pond retrieval models were developed using the TerraSAR-X dual-polarization synthetic aperture radar (SAR) data with mid-incidence angle obtained in a summer multiyear sea ice area in the Chukchi Sea, the Western Arctic, based on two rule-based machine learning approaches—decision trees (DT) and random forest (RF)—in order to derive melt pond statistics at high spatial resolution and to identify key polarimetric parameters for melt pond detection. Melt ponds, sea ice and open water were delineated from the airborne SAR images (0.3-m resolution), which were used as a reference dataset. A total of eight polarimetric parameters (HH and VV backscattering coefficients, co-polarization ratio, co-polarization phase difference, co-polarization correlation coefficient, alpha angle, entropy and anisotropy) were derived from the TerraSAR-X dual-polarization data and then used as input variables for the machine learning models. The DT and RF models could not effectively discriminate melt ponds from open water when using only the polarimetric parameters. This is because melt ponds showed similar polarimetric signatures to open water. The average and standard deviation of the polarimetric parameters based on a 15 × 15 pixel window were supplemented to the input variables in order to consider the difference between the spatial texture of melt ponds and open water. Both the DT and RF models using the polarimetric parameters and their texture features produced improved performance for the retrieval of melt ponds, and RF was superior to DT. The HH backscattering coefficient was identified as the variable contributing the most, and its spatial standard deviation was the next most contributing one to the classification of open water, sea ice and melt ponds in the RF model. The average of the co-polarization phase difference and the alpha angle in a mid-incidence angle were also identified as the important variables in the RF model. The melt pond fraction and sea ice concentration retrieved from the RF-derived melt pond map showed root mean square deviations of 2.4% and 4.9%, respectively, compared to those from the reference melt pond maps. This indicates that there is potential to accurately monitor melt ponds on multiyear sea ice in the summer season at a local scale using high-resolution dual-polarization SAR data.

[1]  J. Rhee,et al.  Relationship between land cover patterns and surface temperature in urban areas , 2014 .

[2]  Rolf Werninghaus,et al.  The TerraSAR-X Mission and System Design , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Abbas Bahroudi,et al.  Support vector machine for multi-classification of mineral prospectivity areas , 2012, Comput. Geosci..

[4]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[5]  Fernando Vicente-Guijalba,et al.  Polarimetric Response of Rice Fields at C-Band: Analysis and Phenology Retrieval , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[6]  S. Ha,et al.  Machine learning approaches to coastal water quality monitoring using GOCI satellite data , 2014 .

[7]  David G. Barber,et al.  The physical, radiative and microwave scattering characteristics of melt ponds on Arctic landfast sea ice , 1999 .

[8]  L. Kaleschke,et al.  Intercomparison of passive microwave sea ice concentration retrievals over the high-concentration Arctic sea ice , 2007 .

[9]  J. Maslanik,et al.  Derivation of melt pond coverage on Arctic sea ice using MODIS observations , 2008 .

[10]  Xin Niu,et al.  Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach , 2013 .

[11]  Janet K. Pitman,et al.  Assessment of Undiscovered Oil and Gas in the Arctic , 2009, Science.

[12]  Stephen E. L. Howell,et al.  Surface-Based Polarimetric C-Band Scatterometer for Field Measurements of Sea Ice , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Jungho Im,et al.  Detection of Convective Initiation Using Meteorological Imager Onboard Communication, Ocean, and Meteorological Satellite Based on Machine Learning Approaches , 2015, Remote. Sens..

[14]  S. Vavrus,et al.  Evidence linking Arctic amplification to extreme weather in mid‐latitudes , 2012 .

[15]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[16]  Marika M. Holland,et al.  Inter‐annual to multi‐decadal Arctic sea ice extent trends in a warming world , 2011 .

[17]  Ola M. Johannessen,et al.  Two decades of microwave satellite observations of arctic sea ice variability and trends , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[18]  David G. Barber,et al.  Melt ponds on sea ice in the Canadian Archipelago: 2. On the use of RADARSAT‐1 synthetic aperture radar for geophysical inversion , 2000 .

[19]  D. Cavalieri,et al.  Antarctic sea ice variability and trends, 1979-2010 , 2012 .

[20]  L. Kaleschke,et al.  Comparison of different retrieval techniques for melt ponds on Arctic sea ice from Landsat and MODIS satellite data , 2011, Annals of Glaciology.

[21]  Shane R. Cloude,et al.  The Dual Polarization Entropy/Alpha Decomposition: A PALSAR Case Study , 2007 .

[22]  Tim Appelhans,et al.  Improving the accuracy of rainfall rates from optical satellite sensors with machine learning — A random forests-based approach applied to MSG SEVIRI , 2014 .

[23]  R. Horton,et al.  Revisiting the potential of melt pond fraction as a predictor for the seasonal Arctic sea ice extent minimum , 2015 .

[24]  Timo Vihma,et al.  Effects of Arctic Sea Ice Decline on Weather and Climate: A Review , 2014, Surveys in Geophysics.

[25]  Edgar Erdfelder,et al.  G*Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences , 2007, Behavior research methods.

[26]  B. Haack,et al.  Classification of California agriculture using quad polarization radar data and Landsat Thematic Mapper data , 2013 .

[27]  K. Moffett,et al.  Remote Sens , 2015 .

[28]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[29]  L. Kaleschke,et al.  Exceptional melt pond occurrence in the years 2007 and 2011 on the Arctic sea ice revealed from MODIS satellite data , 2012 .

[30]  Fuzhong Weng,et al.  A New Sea-Ice Concentration Algorithm Based on Microwave Surface Emissivities—Application to AMSU Measurements , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[32]  Francesca Bovolo,et al.  Updating Land-Cover Maps by Classification of Image Time Series: A Novel Change-Detection-Driven Transfer Learning Approach , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Anthony M. Filippi,et al.  River-flow boundary delineation from digital aerial photography and ancillary images using Support Vector Machines , 2013 .

[34]  Le Wang,et al.  An object-based SVM method incorporating optimal segmentation scale estimation using Bhattacharyya Distance for mapping salt cedar (Tamarisk spp.) with QuickBird imagery , 2015 .

[35]  Marko Mäkynen,et al.  On the Estimation of Melt Pond Fraction on the Arctic Sea Ice With ENVISAT WSM Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[36]  L. Kaleschke,et al.  Melt ponds on Arctic sea ice determined from MODIS satellite data using an artificial neural network , 2011 .

[37]  Donald K. Perovich,et al.  Sunlight, water, and ice: Extreme Arctic sea ice melt during the summer of 2007 , 2008 .

[38]  Arjun Sheoran,et al.  Land Use/Cover Mapping with Quad-polarization Radar and Derived Texture Measures near Wad Madani, Sudan , 2010 .

[39]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .

[40]  A. Kalra,et al.  Estimating soil moisture using remote sensing data: A machine learning approach , 2010 .

[41]  Caiyun Zhang,et al.  Fusing lidar and digital aerial photography for object-based forest mapping in the Florida Everglades , 2013 .

[42]  Walter B. Tucker,et al.  Aerial observations of the evolution of ice surface conditions during summer , 2002 .

[43]  Jong-Sen Lee,et al.  Polarimetric SAR speckle filtering and its implication for classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[44]  Duk-jin Kim,et al.  Melt Pond Mapping With High-Resolution SAR: The First View , 2013, Proceedings of the IEEE.

[45]  C. Deser,et al.  Atmospheric impacts of Arctic sea-ice loss, 1979–2009: separating forced change from atmospheric internal variability , 2013, Climate Dynamics.

[46]  M. Holland,et al.  Trends in Arctic sea ice extent from CMIP5, CMIP3 and observations , 2012 .

[47]  Jungho Im,et al.  Landfast sea ice monitoring using multisensor fusion in the Antarctic , 2015 .

[48]  Eleonora P. Zege,et al.  Melt pond fraction and spectral sea ice albedo retrieval from MERIS data – Part 1: Validation against in situ, aerial, and ship cruise data , 2015 .

[49]  D. Barber,et al.  First-year sea ice melt pond fraction estimation from dual-polarisation C-band SAR - Part 1: In situ observations , 2014 .

[50]  Son V. Nghiem,et al.  Polarimetric signatures of sea ice. 1: Theoretical model , 1995 .

[51]  John J. Yackel,et al.  Evaluation of C-band SAR polarimetric parameters for discrimination of first-year sea ice types , 2012 .

[52]  Weiqi Zhou,et al.  Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery , 2014, Remote Sensing.

[53]  Weifeng Li,et al.  Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery , 2014, Remote. Sens..

[54]  Dustin Isleifson,et al.  Geophysical controls on C band polarimetric backscatter from melt pond covered Arctic first‐year sea ice: Assessment using high‐resolution scatterometry , 2012 .

[55]  Eric Pottier,et al.  An entropy based classification scheme for land applications of polarimetric SAR , 1997, IEEE Trans. Geosci. Remote. Sens..

[56]  F. Gao,et al.  Improved forest change detection with terrain illumination corrected Landsat images , 2013 .

[57]  Daniel L. Feltham,et al.  Incorporation of a physically based melt pond scheme into the sea ice component of a climate model , 2010 .

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

[59]  B. Sæther,et al.  Climate Events Synchronize the Dynamics of a Resident Vertebrate Community in the High Arctic , 2013, Science.

[60]  Jinlong Chao,et al.  Estimation of sea ice thickness in the Bohai Sea using a combination of VIS/NIR and SAR images , 2015 .

[61]  Hajo Eicken,et al.  Hydraulic controls of summer Arctic pack ice albedo , 2004 .

[62]  Matthew J. Cracknell,et al.  Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information , 2014, Comput. Geosci..

[63]  Helko Breit,et al.  TerraSAR-X SAR Processing and Products , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[64]  D. Lu,et al.  A comparative analysis of approaches for successional vegetation classification in the Brazilian Amazon , 2014 .

[65]  Lucy Marshall,et al.  Object-oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest , 2013 .

[66]  R. Lawrence Rule-Based Classification Systems Using Classification and Regression Tree (CART) Analysis , 2001 .

[67]  J. Im,et al.  Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest , 2013 .

[68]  Dharmendra Singh,et al.  A Statistical-Measure-Based Adaptive Land Cover Classification Algorithm by Efficient Utilization of Polarimetric SAR Observables , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[69]  David Schröder,et al.  September Arctic sea-ice minimum predicted by spring melt-pond fraction , 2014 .

[70]  Donald J. Cavalieri,et al.  Antarctic sea ice variability and trends, 1979-2010 , 2012 .

[71]  Caiyun Zhang,et al.  Combining object-based texture measures with a neural network for vegetation mapping in the Everglades from hyperspectral imagery , 2012 .

[72]  Josefino C. Comiso,et al.  Large Decadal Decline of the Arctic Multiyear Ice Cover , 2012 .

[73]  Donald K. Perovich,et al.  Seasonal evolution of the albedo of multiyear Arctic sea ice , 2002 .

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

[75]  Torsten Geldsetzer,et al.  Sensitivity of C-band synthetic aperture radar polarimetric parameters to snow thickness over landfast smooth first-year sea ice , 2015 .

[76]  Eleonora P. Zege,et al.  Algorithm to retrieve the melt pond fraction and the spectral albedo of Arctic summer ice from satellite optical data , 2015 .

[77]  Aaron E. Maxwell,et al.  Comparison of NAIP orthophotography and RapidEye satellite imagery for mapping of mining and mine reclamation , 2014 .

[78]  Christine Wesche,et al.  C-Band Radar Polarimetry—Useful for Detection of Icebergs in Sea Ice? , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[79]  David G. Barber,et al.  First-year sea ice melt pond fraction estimation from dual-polarisation C-band SAR – Part 2: Scaling in situ to Radarsat-2 , 2014 .

[80]  Thorsten Markus,et al.  Comparison of aerial video and Landsat 7 data over ponded sea ice , 2003 .

[81]  David A. Clausi,et al.  Unsupervised segmentation of synthetic aperture Radar sea ice imagery using a novel Markov random field model , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[82]  Bardan Ghimire,et al.  An Evaluation of Bagging, Boosting, and Random Forests for Land-Cover Classification in Cape Cod, Massachusetts, USA , 2012 .

[83]  L. Kaleschke,et al.  Effect of sea ice morphology during Arctic summer on atmospheric drag coefficients used in climate models , 2012 .

[84]  Florence Fetterer,et al.  Observations of melt ponds on Arctic sea ice , 1998 .