A co-training, mutual learning approach towards mapping snow cover from multi-temporal high-spatial resolution satellite imagery

Abstract High-spatial and -temporal resolution snow cover maps for mountain areas are needed for hydrological applications and snow hazard monitoring. The Chinese GF-1 satellite is potential to provide such information with a spatial resolution of 8 m and a revisit of 4 days. The main challenge for the extraction of multi-temporal snow cover from high-spatial resolution images is that the observed spectral signature of snow and snow-free areas is non-stationary in both spatial and temporal domains. As a result, successful extraction requires adequate labelled samples for each image, which is difficult to be achieved. To solve this problem, a semi-supervised multi-temporal classification method for snow cover extraction (MSCE) is proposed. This method extends the co-training based algorithms from single image classification to multi-temporal ones. Multi-temporal images in MSCE are treated as different descriptions of the same land surface, and consequently, each pixel has multiple sets of features. Independent classifiers are trained on each feature set using a few labelled samples, and then, they are iteratively re-trained in a mutual learning way using a great number of unlabelled samples. The main principle behind MSCE is that the multi-temporal difference of land surface in spectral space can be the source of mutual learning inspired by the co-training paradigm, providing a new strategy to deal with multi-temporal image classification. The experimental findings of multi-temporal GF-1 images confirm the effectiveness of the proposed method.

[1]  R. Harris,et al.  Extracting biophysical parameters from remotely sensed radar data: a review of the water cloud model , 2003 .

[2]  Y. Arnaud,et al.  Subpixel monitoring of the seasonal snow cover with MODIS at 250 m spatial resolution in the Southern Alps of New Zealand: Methodology and accuracy assessment , 2009 .

[3]  Thomas H. Painter,et al.  The Effect of Grain Size on Spectral Mixture Analysis of Snow-Covered Area from AVIRIS Data , 1998 .

[4]  Anil V. Kulkarni,et al.  Estimation of snow cover distribution in Beas basin, Indian Himalaya using satellite data and ground measurements , 2009 .

[5]  M. Bauer,et al.  Multitemporal snow cover mapping in mountainous terrain for Landsat climate data record development , 2013 .

[6]  Francesca Bovolo,et al.  A Novel Domain Adaptation Bayesian Classifier for Updating Land-Cover Maps With Class Differences in Source and Target Domains , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[7]  D. Selkowitz,et al.  Automated mapping of persistent ice and snow cover across the western U.S. with Landsat , 2016 .

[8]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[9]  André Stumpf,et al.  Hierarchical extraction of landslides from multiresolution remotely sensed optical images , 2014 .

[10]  Fabio Pacifici,et al.  Understanding angular effects in VHR imagery and their significance for urban land-cover model portability: A study of two multi-angle in-track image sequences , 2015 .

[11]  V. Salomonson,et al.  Estimating fractional snow cover from MODIS using the normalized difference snow index , 2004 .

[12]  Zhaoguang,et al.  GF-1 Satellite——The First Satellite of CHEOS , 2013 .

[13]  Vince Salomonson,et al.  Development of the Aqua MODIS NDSI fractional snow cover algorithm and validation results , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Zhi-Hua Zhou,et al.  CoTrade: Confident Co-Training With Data Editing , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  Ulf Brefeld,et al.  Co-EM support vector learning , 2004, ICML.

[16]  David A. Landgrebe,et al.  The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon , 1994, IEEE Trans. Geosci. Remote. Sens..

[17]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

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

[19]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[20]  David L. Olson,et al.  Advanced Data Mining Techniques , 2008 .

[21]  Jeff Dozier,et al.  Automated Mapping of Montane Snow Cover at Subpixel Resolution from the Landsat Thematic Mapper , 1996 .

[22]  Zhi-Hua Zhou,et al.  Tri-training: exploiting unlabeled data using three classifiers , 2005, IEEE Transactions on Knowledge and Data Engineering.

[23]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[24]  Sanjoy Dasgupta,et al.  PAC Generalization Bounds for Co-training , 2001, NIPS.

[25]  Birger Ulf Hansen,et al.  Detection of spatial, temporal, and spectral surface changes in the Ny-Ålesund area 79° N, Svalbard, using a low cost multispectral camera in combination with spectroradiometer measurements , 2003 .

[26]  Palma Blonda,et al.  Three different unsupervised methods for change detection: an application , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[27]  Stephen G. Warren,et al.  Optical Properties of Snow , 1982 .

[28]  D. Hall,et al.  Development of methods for mapping global snow cover using moderate resolution imaging spectroradiometer data , 1995 .

[29]  Qiong Jackson,et al.  An adaptive classifier design for high-dimensional data analysis with a limited training data set , 2001, IEEE Trans. Geosci. Remote. Sens..

[30]  A. Klein,et al.  Fractional snow cover mapping through artificial neural network analysis of MODIS surface reflectance , 2011 .

[31]  Lorenzo Bruzzone,et al.  A Novel Transductive SVM for Semisupervised Classification of Remote-Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Jean-Michel Friedt,et al.  Monitoring seasonal snow dynamics using ground based high resolution photography ( Austre Lovenbreen , Svalbard , 79 N ) , 2012 .

[33]  C. Woodcock,et al.  Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images , 2015 .

[34]  Zhi-Hua Zhou.  When semi-supervised learning meets ensemble learning , 2011 .

[35]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[36]  Zhi-Hua Zhou,et al.  Analyzing Co-training Style Algorithms , 2007, ECML.

[37]  Xia Li,et al.  Domain adaptation for land use classification: A spatio-temporal knowledge reusing method , 2014 .

[38]  Chenghu Zhou,et al.  The oasis expansion and eco-environment change over the last 50 years in Manas River Valley, Xinjiang , 2006 .

[39]  Lorenzo Bruzzone,et al.  Toward the Automatic Updating of Land-Cover Maps by a Domain-Adaptation SVM Classifier and a Circular Validation Strategy , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[40]  N. DiGirolamo,et al.  MODIS snow-cover products , 2002 .

[41]  Gérard Dedieu,et al.  A multi-temporal method for cloud detection, applied to FORMOSAT-2, VENµS, LANDSAT and SENTINEL-2 images , 2010 .

[42]  Xueliang Zhang,et al.  Support vector machine-based decision tree for snow cover extraction in mountain areas using high spatial resolution remote sensing image , 2014 .

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

[44]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[45]  Vittorio Castelli,et al.  The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameter , 1996, IEEE Trans. Inf. Theory.

[46]  Qian Du,et al.  An efficient semi-supervised classification approach for hyperspectral imagery , 2014 .

[47]  Rayid Ghani,et al.  Analyzing the effectiveness and applicability of co-training , 2000, CIKM '00.

[48]  Dorothy K. Hall,et al.  A snow index for the Landsat Thematic Mapper and Moderate Resolution Imaging Spectroradiometer , 1994, Proceedings of IGARSS '94 - 1994 IEEE International Geoscience and Remote Sensing Symposium.

[49]  Gustavo Camps-Valls,et al.  Semi-Supervised Graph-Based Hyperspectral Image Classification , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[50]  Birger Ulf Hansen,et al.  Automatic snow cover monitoring at high temporal and spatial resolution, using images taken by a standard digital camera , 2002 .

[51]  James J. Simpson,et al.  A recurrent neural network classifier for improved retrievals of areal extent of snow cover , 2001, IEEE Trans. Geosci. Remote. Sens..

[52]  Josef Kittler,et al.  Minimum error thresholding , 1986, Pattern Recognit..

[53]  Thomas H. Painter,et al.  Assessment of methods for mapping snow cover from MODIS , 2011 .

[54]  Michele Dalponte,et al.  Semi-supervised SVM for individual tree crown species classification , 2015 .