End-to-end Learning of Deep Spatio-temporal Representations for Satellite Image Time Series Classification

In this paper we describe our first-place solution to the discovery challenge on time series land cover classification (TiSeLaC), organized in conjunction of ECML PKDD 2017. The challenge consists in predicting the Land Cover class of a set of pixels given their image time series data acquired by the satellites. We propose an end-to-end learning approach employing both temporal and spatial information and requiring very little data preprocessing and feature engineering. In this report we detail the architecture that ranked first—out of 21 teams—comprising modules using dense multi-layer perceptrons and one-dimensional convolutional neural networks. We discuss this architecture properties in detail as well as several possible enhancements.

[1]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Donato Malerba,et al.  Transductive hyperspectral image classification: toward integrating spectral and relational features via an iterative ensemble system , 2016, Machine Learning.

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

[4]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Dino Ienco,et al.  Land Cover Classification via Multi-temporal Spatial Data by Recurrent Neural Networks , 2017, ArXiv.

[6]  Steven Verstockt,et al.  Hyperspectral Image Classification with Convolutional Neural Networks , 2015, ACM Multimedia.

[7]  Jon Atli Benediktsson,et al.  Recent Advances in Techniques for Hyperspectral Image Processing , 2009 .

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

[9]  Annalisa Appice,et al.  Iterative Hyperspectral Image Classification Using Spectral–Spatial Relational Features , 2015, IEEE Transactions on Geoscience and Remote Sensing.

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

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[12]  Yi Zheng,et al.  Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks , 2014, WAIM.