Forest type identification by random forest classification combined with SPOT and multitemporal SAR data

AbstractWe developed a forest type classification technology for the Daxing′an Mountains of northeast China using multisource remote sensing data. A SPOT-5 image and two temporal images of RADARSAT-2 full-polarization SAR were used to identify forest types in the Pangu Forest Farm of the Daxing′an Mountains. Forest types were identified using random forest (RF) classification with the following data combination types: SPOT-5 alone, SPOT-5 and SAR images in August or November, and SPOT-5 and two temporal SAR images. We identified many forest types using a combination of multitemporal SAR and SPOT-5 images, including Betula platyphylla, Larix gmelinii, Pinus sylvestris and Picea koraiensis forests. The accuracy of classification exceeded 88% and improved by 12% when compared to the classification results obtained using SPOT data alone. RF classification using a combination of multisource remote sensing data improved classification accuracy compared to that achieved using single-source remote sensing data.

[1]  Hiroyoshi Yamada,et al.  A four-component decomposition of POLSAR images based on the coherency matrix , 2006, IEEE Geoscience and Remote Sensing Letters.

[2]  Evlyn Márcia Leão de Moraes Novo,et al.  Dual-season and full-polarimetric C band SAR assessment for vegetation mapping in the Amazon várzea wetlands. , 2016 .

[3]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[4]  Christoph Hütt,et al.  Best Accuracy Land Use/Land Cover (LULC) Classification to Derive Crop Types Using Multitemporal, Multisensor, and Multi-Polarization SAR Satellite Images , 2016, Remote. Sens..

[5]  Yasser Maghsoudi,et al.  Radarsat-2 Polarimetric SAR Data for Boreal Forest Classification Using SVM and a Wrapper Feature Selector , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  Aleksandra Pizurica,et al.  Supervised feature-based classification of multi-channel SAR images , 2006, Pattern Recognit. Lett..

[7]  D. Evans,et al.  Radar polarimetry: analysis tools and applications , 1988 .

[8]  Yasser Maghsoudi,et al.  Forest classification using extracted PolSAR features from Compact Polarimetry data , 2016 .

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

[10]  S. Hubbell,et al.  Demographic spatial genetic structure of the Neotropical tree, Jacaranda copaia , 2006, Molecular ecology.

[11]  Torbjørn Eltoft,et al.  Fusion of optical and multifrequency polsar data for forest classification , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[12]  Serkan Kiranyaz,et al.  Integrating Color Features in Polarimetric SAR Image Classification , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Q. Wang,et al.  Comparison of ALOS PALSAR RVI and Landsat TM NDVI for forest area mapping , 2009, 2009 2nd Asian-Pacific Conference on Synthetic Aperture Radar.

[14]  J. Huynen.  Phenomenological theory of radar targets , 1970 .

[15]  Stephen L. Durden,et al.  A three-component scattering model for polarimetric SAR data , 1998, IEEE Trans. Geosci. Remote. Sens..

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

[17]  W. Holm,et al.  On radar polarization mixed target state decomposition techniques , 1988, Proceedings of the 1988 IEEE National Radar Conference.

[18]  Josaphat Tetuko Sri Sumantyo,et al.  Mapping tropical forest cover and deforestation using synthetic aperture radar (SAR) images , 2010 .

[19]  Claudia Notarnicola,et al.  Discrimination of vegetation types in alpine sites with ALOS PALSAR-, RADARSAT-2-, and lidar-derived information , 2013 .

[20]  Thomas L. Ainsworth,et al.  Unsupervised classification using polarimetric decomposition and the complex Wishart classifier , 1999, IEEE Trans. Geosci. Remote. Sens..

[21]  Ridha Touzi,et al.  Forest type discrimination using calibrated C-band polarimetric SAR data , 2004 .

[22]  Xin Li,et al.  A study on vegetation cover extraction using a Wishart H-α classifier based on fully polarimetric Radarsat-2 data , 2016 .

[23]  Cédric Lardeux,et al.  Synergy Between LiDAR, RADARSAT-2, and Spot-5 Images for the Detection and Mapping of Wetland Vegetation in the Danube Delta , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[24]  Yasser Maghsoudi,et al.  Classification of Polarimetric SAR Images Based on Modeling Contextual Information and Using Texture Features , 2016, IEEE Transactions on Geoscience and Remote Sensing.