Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series
Top Cited Papers
Open Access
- 4 March 2019
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 11 (5) , 523
Abstract
Latest remote sensing sensors are capable of acquiring high spatial and spectral Satellite Image Time Series (SITS) of the world. These image series are a key component of classification systems that aim at obtaining up-to-date and accurate land cover maps of the Earth’s surfaces. More specifically, current SITS combine high temporal, spectral and spatial resolutions, which makes it possible to closely monitor vegetation dynamics. Although traditional classification algorithms, such as Random Forest (RF), have been successfully applied to create land cover maps from SITS, these algorithms do not make the most of the temporal domain. This paper proposes a comprehensive study of Temporal Convolutional Neural Networks (TempCNNs), a deep learning approach which applies convolutions in the temporal dimension in order to automatically learn temporal (and spectral) features. The goal of this paper is to quantitatively and qualitatively evaluate the contribution of TempCNNs for SITS classification, as compared to RF and Recurrent Neural Networks (RNNs) —a standard deep learning approach that is particularly suited to temporal data. We carry out experiments on Formosat-2 scene with 46 images and one million labelled time series. The experimental results show that TempCNNs are more accurate than the current state of the art for SITS classification. We provide some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size; we also draw out some differences with standard results in computer vision (e.g., about pooling layers). Finally, we assess the visual quality of the land cover maps produced by TempCNNs.Keywords
All Related Versions
Funding Information
- Australian Research Council (DE170100037)
- Air Force Office of Scientific Research (FA2386-18-1-4030)
This publication has 62 references indexed in Scilit:
- Assessment of an Operational System for Crop Type Map Production Using High Temporal and Spatial Resolution Satellite Optical ImageryRemote Sensing, 2015
- 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 ImagesRemote Sensing, 2015
- Land Cover Classification of Landsat Data with Phenological Features Extracted from Time Series MODIS NDVI DataRemote Sensing, 2014
- The Concept of Essential Climate Variables in Support of Climate Research, Applications, and PolicyBulletin of the American Meteorological Society, 2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational ServicesRemote Sensing of Environment, 2012
- Estimating Global Cropland Extent with Multi-year MODIS DataRemote Sensing, 2010
- The Importance of Land-Cover Change in Simulating Future ClimatesScience, 2005
- Bagging predictorsMachine Learning, 1996
- The use of the Normalized Difference Water Index (NDWI) in the delineation of open water featuresInternational Journal of Remote Sensing, 1996