DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn

Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is represented by the Sentinel-2 mission, which provides images at high spatial resolution (up to 10m) with high temporal revisit period (every 5 days), which can be organized in Satellite Image Time Series (SITS). While the use of SITS has been proved to be beneficial in the context of Land Use/Land Cover (LULC) map generation, unfortunately, machine learning approaches commonly leveraged in remote sensing field fail to take advantage of spatio-temporal dependencies present in such data. Recently, new generation deep learning methods allowed to significantly advance research in this field. These approaches have generally focused on a single type of neural network, i.e., Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), which model different but complementary information: spatial autocorrelation (CNNs) and temporal dependencies (RNNs). In this work, we propose the first deep learning architecture for the analysis of SITS data, namely \method{} (DUal view Point deep Learning architecture for time series classificatiOn), that combines Convolutional and Recurrent neural networks to exploit their complementarity. Our hypothesis is that, since CNNs and RNNs capture different aspects of the data, a combination of both models would produce a more diverse and complete representation of the information for the underlying land cover classification task. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the \textit{Gard} site in France and the \textit{Reunion Island} in the Indian Ocean), demonstrate the significance of our proposal.

[1]  Xu Liu,et al.  DualNet: Learn Complementary Features for Image Recognition , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Lichao Mou,et al.  Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection , 2016, Remote. Sens..

[5]  Dino Ienco,et al.  MRFusion: A Deep Learning architecture to fuse PAN and MS imagery for land cover mapping , 2018, ArXiv.

[6]  Xiao Xiang Zhu,et al.  Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Michele Volpi,et al.  Dense Semantic Labeling of Subdecimeter Resolution Images With Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Qingshan Liu,et al.  Learning Multiscale Deep Features for High-Resolution Satellite Image Scene Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Emile Ndikumana,et al.  Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France , 2018, Remote. Sens..

[11]  Patrick van der Smagt,et al.  Two-stream RNN/CNN for action recognition in 3D videos , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  Marc Rußwurm,et al.  Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders , 2018, ISPRS Int. J. Geo Inf..

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  Wenzhong Guo,et al.  Land-Use Classification via Extreme Learning Classifier Based on Deep Convolutional Features , 2017, IEEE Geoscience and Remote Sensing Letters.

[16]  Qingshan Liu,et al.  Cascaded Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Jin Zhao,et al.  Deep Multiple Instance Learning-Based Spatial–Spectral Classification for PAN and MS Imagery , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Stéphane Dupuy,et al.  A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM) , 2017, Remote. Sens..

[19]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[20]  Shigetoshi Nara,et al.  Simultaneous Multichannel Signal Transfers via Chaos in a Recurrent Neural Network , 2015, Neural Computation.

[21]  Gérard Dedieu,et al.  A Multi-Temporal and Multi-Spectral Method to Estimate Aerosol Optical Thickness over Land, for the Atmospheric Correction of FormoSat-2, LandSat, VENμS and Sentinel-2 Images , 2015, Remote. Sens..

[22]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[23]  Danny Lo Seen,et al.  A Remote Sensing Approach for Regional-Scale Mapping of Agricultural Land-Use Systems Based on NDVI Time Series , 2017, Remote. Sens..

[24]  Dino Ienco,et al.  Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks , 2017, IEEE Geoscience and Remote Sensing Letters.

[25]  Xiao Xiang Zhu,et al.  Deep Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Denny Britz,et al.  Efficient Attention using a Fixed-Size Memory Representation , 2017, EMNLP.

[27]  Christian Ginzler,et al.  Regional Scale Mapping of Grassland Mowing Frequency with Sentinel-2 Time Series , 2018, Remote. Sens..

[28]  Xiaobin Zhang,et al.  A Combination of RNN and CNN for Attention-based Relation Classification , 2018 .

[29]  Maguelonne Teisseire,et al.  Object-oriented satellite image time series analysis using a graph-based representation , 2018, Ecol. Informatics.

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

[31]  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.

[32]  Xiao Xiang Zhu,et al.  Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources , 2017, IEEE Geoscience and Remote Sensing Magazine.

[33]  Chengyi Wang,et al.  Long Short-Term Memory Neural Networks for Online Disturbance Detection in Satellite Image Time Series , 2018, Remote. Sens..

[34]  Jun Cai,et al.  Dynamic monitoring of wetland cover changes using time-series remote sensing imagery , 2014, Ecol. Informatics.

[35]  Thomas Jagdhuber,et al.  Classification and Monitoring of Reed Belts Using Dual-Polarimetric TerraSAR-X Time Series , 2016, Remote. Sens..

[36]  Nataliia Kussul,et al.  Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[37]  Bing Liu,et al.  Supervised Deep Feature Extraction for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[38]  David Morin,et al.  Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series , 2017, Remote. Sens..

[39]  Maguelonne Teisseire,et al.  A graph-based approach to detect spatiotemporal dynamics in satellite image time series , 2017 .

[40]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[41]  Michael A. Wulder,et al.  Landsat continuity: Issues and opportunities for land cover monitoring , 2008 .

[42]  Damien Arvor,et al.  Remote Sensing and Cropping Practices: A Review , 2018, Remote. Sens..

[43]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[44]  Ruggero G. Pensa,et al.  M3Fusion: A Deep Learning Architecture for Multi-{Scale/Modal/Temporal} satellite data fusion , 2018, ArXiv.

[45]  Renato Fontes Guimarães,et al.  Comparative Analysis of MODIS Time-Series Classification Using Support Vector Machines and Methods Based upon Distance and Similarity Measures in the Brazilian Cerrado-Caatinga Boundary , 2015, Remote. Sens..

[46]  Emmanuel Dupoux,et al.  Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies , 2016, TACL.

[47]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[48]  Dino Ienco,et al.  Deep Recurrent Neural Networks for Winter Vegetation Quality Mapping via Multitemporal SAR Sentinel-1 , 2018, IEEE Geoscience and Remote Sensing Letters.

[49]  Mathieu Fauvel,et al.  Analysis of Multitemporal Classification Techniques for Forecasting Image Time Series , 2015, IEEE Geoscience and Remote Sensing Letters.

[50]  Bodo Bookhagen,et al.  Mapping Damage-Affected Areas after Natural Hazard Events Using Sentinel-1 Coherence Time Series , 2018, Remote. Sens..