Crop Mapping from Sentinel-1 Polarimetric Time-Series with a Deep Neural Network
Open Access
- 3 August 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (15) , 2493
Abstract
Timely and accurate agricultural information is essential for food security assessment and agricultural management. Synthetic aperture radar (SAR) systems are increasingly available in crop mapping, as they provide all-weather imagery. In particular, the Sentinel-1 sensor provides dense time-series data, thus offering a unique opportunity for crop mapping. However, in most studies, the Sentinel-1 complex backscatter coefficient was used directly which limits the potential of the Sentinel-1 in crop mapping. Meanwhile, most of the existing methods may not be tailored for the task of crop classification in time-series polarimetric SAR data. To solve the above problem, we present a novel deep learning strategy in this research. To be specific, we collected Sentinel-1 time-series data in two study areas. The Sentinel-1 image covariance matrix is used as an input to maintain the integrity of polarimetric information. Then, a depthwise separable convolution recurrent neural network (DSCRNN) architecture is proposed to characterize crop types from multiple perspectives and achieve better classification results. The experimental results indicate that the proposed method achieves better accuracy in complex agricultural areas than other classical methods. Additionally, the variable importance provided by the random forest (RF) illustrated that the covariance vector has a far greater influence than the backscatter coefficient. Consequently, the strategy proposed in this research is effective and promising for crop mapping.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFC1508903)
- Fundamental Research Funds for the Central Universities (2018NTST01)
This publication has 42 references indexed in Scilit:
- Random forest classification of crop type using multi-temporal TerraSAR-X dual-polarimetric dataRemote Sensing Letters, 2014
- Random Forests as a tool for estimating uncertainty at pixel-level in SAR image classificationInternational Journal of Applied Earth Observation and Geoinformation, 2012
- Phenology-based Crop Classification Algorithm and its Implications on Agricultural Water Use Assessments in California’s Central ValleyPhotogrammetric Engineering & Remote Sensing, 2012
- Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer ProgramGeocarto International, 2011
- Food Security: The Challenge of Feeding 9 Billion PeopleScience, 2010
- Conditional variable importance for random forestsBMC Bioinformatics, 2008
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- A three-component scattering model for polarimetric SAR dataIEEE Transactions on Geoscience and Remote Sensing, 1998
- Long Short-Term MemoryNeural Computation, 1997
- An entropy based classification scheme for land applications of polarimetric SARIEEE Transactions on Geoscience and Remote Sensing, 1997