Oceanic Data Analysis with Deep Learning Models

With advanced observation instruments, such as satellite radars and altimeters, huge amounts of oceanic data can be measured and saved everyday. How to extract effective information from these raw data becomes an urgent problem in the research of ocean science. In this chapter, we review the data representation learning algorithms, which try to learn effective features from raw data and deliver high prediction accuracy for the unseen data. Particularly, we describe two pieces of work to show how the state-of-the-art deep learning models can be applied to oceanic data analysis. That is how the deep convolutional neural networks (CNNs) are used for ocean front recognition and how the long short term memory (LSTM) networks are employed for sea surface temperature prediction. We believe that these two pieces of work are interesting to the researchers in both the machine learning and the ocean science areas, and many machine learning algorithms will be adopted in the ocean science applications.

[1]  Guoqiang Zhong,et al.  Classification of photographed document images based on deep-learning features , 2017, International Conference on Graphic and Image Processing.

[2]  Wu-Jun Li,et al.  Gaussian Process Latent Random Field , 2010, AAAI.

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Neil D. Lawrence,et al.  Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models , 2005, J. Mach. Learn. Res..

[5]  Mohamed Cheriet,et al.  Manifold learning for the shape-based recognition of historical arabic documents , 2013 .

[6]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[7]  Shuicheng Yan,et al.  Graph Embedding and Extensions: A General Framework for Dimensionality Reduction , 2007 .

[8]  Junyu Dong,et al.  Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks , 2017, Remote. Sens..

[9]  I. Jolliffe.  Principal Component Analysis , 2002 .

[10]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[11]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[12]  Junyu Dong,et al.  Natural image illuminant estimation via deep non-negative matrix factorisation , 2018, IET Image Process..

[13]  Marc'Aurelio Ranzato,et al.  Large Scale Distributed Deep Networks , 2012, NIPS.

[14]  Guoqiang Zhong,et al.  A deep-learning model for the amplitude inversion of internal waves based on optical remote-sensing images , 2018 .

[15]  Peter Cornillon,et al.  SST fronts of the Pacific coastal and marginal seas , 2003 .

[16]  Kaizhu Huang,et al.  Reducing and Stretching Deep Convolutional Activation Features for Accurate Image Classification , 2018, Cognitive Computation.

[17]  Byunghan Lee,et al.  Deep learning in bioinformatics , 2016, Briefings Bioinform..

[18]  Jong-Seong Kug,et al.  A statistical approach to Indian Ocean sea surface temperature prediction using a dynamical ENSO prediction , 2004 .

[19]  Huiyu Zhou,et al.  Merging Neurons for Structure Compression of Deep Networks , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[20]  Cong Liu,et al.  Underwater image colour constancy based on DSNMF , 2017, IET Image Process..

[21]  Peter Cornillon,et al.  Edge Detection Algorithm for SST Images , 1992 .

[22]  William W. Hsieh,et al.  Machine Learning Methods in the Environmental Sciences: Neural Networks and Kernels , 2009 .

[23]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Cheng-Lin Liu,et al.  Error-correcting output codes based ensemble feature extraction , 2013, Pattern Recognit..

[25]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[26]  Mohamed Cheriet,et al.  Tensor representation learning based image patch analysis for text identification and recognition , 2015, Pattern Recognit..

[27]  Peter I. Miller,et al.  Seasonal shelf-sea front mapping using satellite ocean colour and temperature to support development of a marine protected area network , 2015 .

[28]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[29]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[30]  Ambedkar Dukkipati,et al.  Learning by Stretching Deep Networks , 2014, ICML.

[31]  Guoqiang Zhong,et al.  Low-Rank Tensor Learning with Discriminant Analysis for Action Classification and Image Recovery , 2014, AAAI.

[32]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[33]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[34]  Mohamed Cheriet,et al.  Tandem hidden Markov models using deep belief networks for offline handwriting recognition , 2017, Frontiers of Information Technology & Electronic Engineering.

[35]  Nadav Cohen,et al.  On the Expressive Power of Deep Learning: A Tensor Analysis , 2015, COLT 2016.

[36]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[37]  Junyu Dong,et al.  Deep Error-Correcting Output Codes , 2017, Algorithms.

[38]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[39]  Samy Bengio,et al.  Large Scale Online Learning of Image Similarity Through Ranking , 2009, J. Mach. Learn. Res..

[40]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[41]  Junyu Dong,et al.  Deep hashing learning networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[42]  Mohamed Cheriet,et al.  Low Rank Tensor Manifold Learning , 2014, Low-Rank and Sparse Modeling for Visual Analysis.

[43]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[44]  Junyu Dong,et al.  Learning and Transferring Convolutional Neural Network Knowledge to Ocean Front Recognition , 2017, IEEE Geoscience and Remote Sensing Letters.

[45]  Yun Fu,et al.  Scalable large margin online metric learning , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[46]  Kaizhu Huang,et al.  Is DeCAF Good Enough for Accurate Image Classification? , 2015, ICONIP.

[47]  Makarand Deo,et al.  Prediction of Sea Surface Temperature by Combining Numerical and Neural Techniques , 2016 .

[48]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[49]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[50]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[51]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Junyu Dong,et al.  Prediction of Sea Surface Temperature Using Long Short-Term Memory , 2017, IEEE Geoscience and Remote Sensing Letters.

[53]  Zhengming Ding,et al.  Latent Tensor Transfer Learning for RGB-D Action Recognition , 2014, ACM Multimedia.

[54]  Geoffrey E. Hinton,et al.  Stochastic Neighbor Embedding , 2002, NIPS.

[55]  Alex Graves,et al.  Grid Long Short-Term Memory , 2015, ICLR.

[56]  Junyu Dong,et al.  Stretching deep architectures for text recognition , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[57]  Ying Gao,et al.  Perception driven texture generation , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[58]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[59]  G. Baudat,et al.  Generalized Discriminant Analysis Using a Kernel Approach , 2000, Neural Computation.

[60]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[61]  R. Khanna,et al.  Support Vector Regression , 2015 .

[62]  Mohamed Cheriet,et al.  Relational Fisher Analysis: A general framework for dimensionality reduction , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[63]  Ohad Shamir,et al.  The Power of Depth for Feedforward Neural Networks , 2015, COLT.

[64]  Mohamed Cheriet,et al.  Image patches analysis for text block identification , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[65]  William W. Hsieh.  Machine Learning Methods in the Environmental Sciences: Contents , 2009 .

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

[67]  Junyu Dong,et al.  Visual Texture Perception with Feature Learning Models and Deep Architectures , 2014, CCPR.

[68]  Yan Zheng,et al.  Convolutional Discriminant Analysis , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[69]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[70]  Yun Fu,et al.  SLMOML: Online Metric Learning With Global Convergence , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[71]  Xiao Li,et al.  Machine Learning Paradigms for Speech Recognition: An Overview , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[72]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[73]  Guoqiang Zhong,et al.  From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures , 2019, WIREs Data Mining Knowl. Discov..

[74]  Junyu Dong,et al.  Ocean Front Detection From Instant Remote Sensing SST Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[75]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[76]  Junyu Dong,et al.  An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning , 2016, ArXiv.

[77]  Mohamed Cheriet,et al.  Large Margin Low Rank Tensor Analysis , 2013, Neural Computation.

[78]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[79]  Guoqiang Zhong,et al.  The Necessary and Sufficient Conditions for the Existence of the Optimal Solution of Trace Ratio Problems , 2016, CCPR.

[80]  Mohamed Cheriet,et al.  Adaptive Error-Correcting Output Codes , 2013, IJCAI.

[81]  Guoqiang Zhong,et al.  A novel model of estimating sea state bias based on multi-layer neural network and multi-source altimeter data , 2018 .

[82]  Kaizhu Huang,et al.  Low Rank Metric Learning with Manifold Regularization , 2011, 2011 IEEE 11th International Conference on Data Mining.

[83]  Nicholas G. Polson,et al.  Deep Learning in Finance , 2016, ArXiv.

[84]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.