Rice Mapping Using a BiLSTM-Attention Model from Multitemporal Sentinel-1 Data

Abstract

Timely and accurate rice distribution information is needed to ensure the sustainable development of food production and food security. With its unique advantages, synthetic aperture radar (SAR) can monitor the rice distribution in tropical and subtropical areas under any type of weather condition. This study proposes an accurate rice extraction and mapping framework that can solve the issues of low sample production efficiency and fragmented rice plots when prior information on rice distribution is insufficient. The experiment was carried out using multitemporal Sentinel-1A Data in Zhanjiang, China. First, the temporal characteristic map was used for the visualization of rice distribution to improve the efficiency of rice sample production. Second, rice classification was carried out based on the BiLSTM-Attention model, which focuses on learning the key information of rice and non-rice in the backscattering coefficient curve and gives different types of attention to rice and non-rice features. Finally, the rice classification results were optimized based on the high-precision global land cover classification map. The experimental results showed that the classification accuracy of the proposed framework on the test dataset was 0.9351, the kappa coefficient was 0.8703, and the extracted plots maintained good integrity. Compared with the statistical data, the consistency reached 94.6%. Therefore, the framework proposed in this study can be used to extract rice distribution information accurately and efficiently.

Improved LSTM Model for Boreal Forest Height Mapping Using Sentinel-1 Time Series

“…It should be noted that, similar to our models, all these methods operate on a pixel-level considering only temporal features. The following methodologies are included for comparison: [33,52], are also included as baseline models for comparison. Bidirectional LSTM (BiLSTM) consists of two LSTMs with the same structure but opposite directions.…”

“…Furthermore, with the self-attention mechanism, attention weights establish the correlations between timestamps, which reportedly can better address the gradient vanishing problem and obtain long-term correlations [53]. Attn-BiLSTM combines both features and has been introduced into SAR remote sensing tasks [33].…”

“…LSTMs were previously demonstrated in several remote sensing applications, particularly land cover mapping and crop monitoring [26][27][28][29][30][31][32][33][34]. However, to date, the use of LSTMs in forest attribute prediction utilising Earth Observation (EO) data was limited if at all reported with SAR image time series.…”

Rice Mapping in a Subtropical Hilly Region Based on Sentinel-1 Time Series Feature Analysis and the Dual Branch BiLSTM Model

“…VH polarization timing features are often used. The VH polarization time series characteristics of rice in these study areas show clear flooding period signals at the early stage of rice transplanting, primarily in the form of a "bell curve" [21,38]. However, the rice planting area in the hilly region of southeast China is small and scattered, and the time series curve of the VH polarization data has no strong signal during the flooding period.…”

“…Sun et al used the attention mechanism with the bi-directional long short-term memory (BiLSTM) model to extract the distribution of rice in Zhanjiang, China, using the VH polarization of multitemporal Sentinel-1A data. Experimental results achieved an overall accuracy of 0.9351, which was better than that of the LSTM and RF classifiers [38]. Liu et al proposed a hybrid structure of the CNN and attentional LSTM to map the rotation cultivation of crops in the river plains of Hunan Province, China, with time series SAR and optical data [39].…”