Sea Ice Type Classification with Optical Remote Sensing Data

Optical remote sensing sensors provide visually more familiar images than radar images. However, it is difficult to discriminate sea ice types in optical images using spectral information based machine learning algorithms. This study addresses two topics. First, we propose a semantic segmentation which is a part of the state-of-the-art deep learning algorithms to identify ice types by learning hierarchical and spatial features of sea ice. Second, we propose a new approach by combining of semi-supervised and active learning to obtain accurate and meaningful labels from unlabeled or unseen images to improve the performance of supervised classification for multiple images. Therefore, we successfully added new labels from unlabeled data to automatically update the semantic segmentation model. This should be noted that an operational system to generate ice type products from optical remote sensing data may be possible in the near future.

[1]  E. Carmack,et al.  The role of sea ice and other fresh water in the Arctic circulation , 1989 .

[2]  Nikhil Ketkar,et al.  Deep Learning with Python , 2017 .

[3]  Bo Du,et al.  Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art , 2016, IEEE Geoscience and Remote Sensing Magazine.

[4]  Xiaorui Ma,et al.  Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning , 2016 .

[5]  Dorothy K. Hall,et al.  Assessment of AMSR-E Antarctic Winter Sea-Ice Concentrations Using Aqua MODIS , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[6]  L. Kaleschke,et al.  Sea ice remote sensing using AMSR‐E 89‐GHz channels , 2008 .

[7]  Judith A. Curry,et al.  Interpretation of recent Antarctic sea ice variability , 2004 .

[8]  Melba M. Crawford,et al.  Spectral and Spatial Proximity-Based Manifold Alignment for Multitemporal Hyperspectral Image Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Susanne Lehner,et al.  A Neural Network-Based Classification for Sea Ice Types on X-Band SAR Images , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[10]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  William J. Emery,et al.  Active Learning Methods for Remote Sensing Image Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Junhwa Chi,et al.  Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network , 2017, Remote. Sens..

[15]  Lorenzo Bruzzone,et al.  Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images , 2001, IEEE Trans. Geosci. Remote. Sens..

[16]  Jie Zhang,et al.  Sea ice type classification based on random forest machine learning with Cryosat-2 altimeter data , 2017, 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP).

[17]  Dorothy K. Hall,et al.  Assessment of EOS Aqua AMSR-E Arctic Sea Ice Concentrations Using Landsat-7 and Airborne Microwave Imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  S. Vavrus,et al.  The impact of sea-ice dynamics on the Arctic climate system , 2003 .

[20]  Thomas Lavergne,et al.  Use of C-Band Scatterometer for Sea Ice Edge Identification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

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

[23]  Giles M. Foody,et al.  Training set size requirements for the classification of a specific class , 2006 .

[24]  Natalia Ivanova,et al.  Retrieval of Arctic Sea Ice Parameters by Satellite Passive Microwave Sensors: A Comparison of Eleven Sea Ice Concentration Algorithms , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[25]  William J. Emery,et al.  Using active learning to adapt remote sensing image classifiers , 2011 .

[26]  Melba M. Crawford,et al.  Active Learning: Any Value for Classification of Remotely Sensed Data? , 2013, Proceedings of the IEEE.