Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 2; p. 321
• Main Authors: Guo, Jiao, Li, Henghui, Ning, Jifeng, Han, Wenting, Zhang, Weitao, Zhou, Zheng-Shu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-01-2020
• Subjects: Accuracy; Algorithms; Artificial neural networks; Classification; Coders; convolutional neural network (cnn); crop classification; Crops; Decomposition; Deep learning; Disasters; Feature extraction; Incoherent scattering; Long short-term memory; multi-temporal; Neural networks; polarimetric synthetic aperture radar (polsar); Principal components analysis; Radar polarimetry; Reduction; Remote sensing; S parameters; Satellites; stacked sparse auto-encoder (s-sae); Synthetic aperture radar; Training
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12020321

Crop classification in agriculture is one of important applications for polarimetric synthetic aperture radar (PolSAR) data. For agricultural crop discrimination, compared with single-temporal data, multi-temporal data can dramatically increase crop classification accuracies since the same crop shows different external phenomena as it grows up. In practice, the utilization of multi-temporal data encounters a serious problem known as a “dimension disaster”. Aiming to solve this problem and raise the classification accuracy, this study developed a feature dimension reduction method using stacked sparse auto-encoders (S-SAEs) for crop classification. First, various incoherent scattering decomposition algorithms were employed to extract a variety of detailed and quantitative parameters from multi-temporal PolSAR data. Second, based on analyzing the configuration and main parameters for constructing an S-SAE, a three-hidden-layer S-SAE network was built to reduce the dimensionality and extract effective features to manage the “dimension disaster” caused by excessive scattering parameters, especially for multi-temporal, quad-pol SAR images. Third, a convolutional neural network (CNN) was constructed and employed to further enhance the crop classification performance. Finally, the performances of the proposed strategy were assessed with the simulated multi-temporal Sentinel-1 data for two experimental sites established by the European Space Agency (ESA). The experimental results showed that the overall accuracy with the proposed method was raised by at least 17% compared with the long short-term memory (LSTM) method in the case of a 1% training ratio. Meanwhile, for a CNN classifier, the overall accuracy was almost 4% higher than those of the principle component analysis (PCA) and locally linear embedded (LLE) methods. The comparison studies clearly demonstrated the advantage of the proposed multi-temporal crop classification methodology in terms of classification accuracy, even with small training ratios.