Nowadays, modern earth observation programs produce huge volumes of satellite images time series (SITS) that can be useful to monitor geographical areas through time. How to efficiently analyze such kind of information is still an open question in the remote sensing field. Recently, deep learning methods proved suitable to deal with remote sensing data mainly for scene classification (i.e. Convolutional Neural Networks -CNNs -on single images) while only very few studies exist involving temporal deep learning approaches (i.e Recurrent Neural Networks -RNNs) to deal with remote sensing time series.In this letter we evaluate the ability of Recurrent Neural Networks, in particular the Long-Short Term Memory (LSTM) model, to perform land cover classification considering multi-temporal spatial data derived from a time series of satellite images. We carried out experiments on two different datasets considering both pixel-based and object-based classification. The obtained results show that Recurrent Neural Networks are competitive compared to state-of-the-art classifiers, and may outperform classical approaches in presence of low represented and/or highly mixed classes. We also show that using the alternative feature representation generated by LSTM can improve the performances of standard classifiers.

No abstract

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 rent 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 DuP LO (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 Gard site in France and the Reunion Island in the Indian Ocean), demonstrate the significance of our proposal.Classification, Sentinel-2 toring and land management planning [1,2,3,4,5,6,7,8,9]. In the context of Land Use/Land Cover (LULC) classification, exploiting SITS can be fruitful to discriminate among classes that exhibit different temporal behaviors [10], i.e., with the respect to the results that can be obtained using a single image. In [7], the authors propose to exploit SITS data to extract homogeneous land units in terms of phenological patterns and, later, for the automatic classification of land units according to their land-cover. The effectiveness of Sentinel-2 SITS to produce land cover maps at country scale has been showed in [8], demonstrating the practical interest of such data source. In [9], the authors combine multi-source optical (Landsat-8) and radar (Sentinel-1) SITS in order to improve land cover maps on the agricultural domain. Another example is supplied in [3] where optical SITS are leveraged to characterize grassland area as proxy indicator for biodiversity, food production, and global carbon cycle.Despite the usefulness of temporal trends that can be derived from remote sensing time series, most of the strategies proposed for SITS analysis tasks [11,12,8,7], directly apply standard machine learning approaches (i.e. Random Forest, SVM) on the stacked images, thus ignoring any temporal dependencies that may be discovered in the data. Indeed, such algorithms make the assumption that the infor...

Modern Earth Observation systems provide sensing data at different temporal and spatial resolutions. Among optical sensors, today the Sentinel-2 program supplies high-resolution temporal (every 5 days) and high spatial resolution (10m) images that can be useful to monitor land cover dynamics. On the other hand, Very High Spatial Resolution images (VHSR) are still an essential tool to figure out land cover mapping characterized by fine spatial patterns. Understand how to efficiently leverage these complementary sources of information together to deal with land cover mapping is still challenging.With the aim to tackle land cover mapping through the fusion of multi-temporal High Spatial Resolution and Very High Spatial Resolution satellite images, we propose an End-to-End Deep Learning framework, named M 3 F usion, able to leverage simultaneously the temporal knowledge contained in time series data as well as the fine spatial information available in VHSR information. Experiments carried out on the Reunion Island study area asses the quality of our proposal considering both quantitative and qualitative aspects.