Paddy Rice Mapping in Thailand Using Time-Series Sentinel-1 Data and Deep Learning Model

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

Timely and accurate information on rice cultivation makes important contributions to the profound reform of the global food and agricultural system, and promotes the development of global sustainable agriculture. With all-day and all-weather observing ability, synthetic aperture radar (SAR) can monitor the distribution of rice in tropical and subtropical areas. To solve the problem of misclassification of rice with no marked signal during the flooding period in subtropical hilly areas, this paper proposes a new feature combination and dual branch bi-directional long short-term memory (DB-BiLSTM) model to achieve high-precision rice mapping using Sentinel-1 time series data. Based on field investigation data, the backscatter time series curves of the rice area were analyzed, and a characteristic index (VV − VH)/(VV + VH) (VV: vertical emission and vertical receipt of polarization, VH: vertical emission and horizontal receipt of polarization) for small areas of hilly land was proposed to effectively distinguish rice and non-rice crops with no marked flooding period. The DB-BiLSTM model was designed, ensuring the independent learning of multiple features and effectively combining the time series information of both (VV − VH)/(VV + VH) and VH features. The city of Shanwei, Guangdong Province, China, was selected as the study area. Experimental results showed that the overall accuracy of the rice mapping results was 97.29%, and the kappa coefficient reached 0.9424. Compared to other methods, the rice mapping results obtained by the proposed method maintained good integrity and had less misclassification, which demonstrated the proposed method’s practical value in accurate and effective rice mapping tasks.

High-Resolution Mapping of Paddy Rice Extent and Growth Stages across Peninsular Malaysia Using a Fusion of Sentinel-1 and 2 Time Series Data in Google Earth Engine

Rice is the staple crop for more than half the world’s population, but there is a lack of high-resolution maps outlining rice areas and their growth stages. Most remote sensing studies map the rice extent; however, in tropical regions, rice is grown throughout the year with variable planting dates and cropping frequency. Thus, mapping rice growth stages is more useful than mapping only the extent. This study addressed this challenge by developing a phenology-based method. The hypothesis was that the unsupervised classification (k-means clustering) of Sentinel-1 and 2 time-series data could identify rice fields and growth stages, because (1) the presence of flooding during transplanting can be identified by Sentinel-1 VH backscatter; and (2) changes in the canopy of rice fields during growth stages (vegetative, generative, and ripening phases) up to the point of harvesting can be identified by Normalized Difference Vegetation Index (NDVI) time series. Using the proposed method, this study mapped rice field extent and cropping calendars across Peninsular Malaysia (131,598 km2) on the Google Earth Engine (GEE) platform. The Sentinel-1 and 2 monthly time series data from January 2019 to December 2020 were classified using k-means clustering to identify areas with similar phenological patterns. This approach resulted in 10-meter resolution maps of rice field extent, intensity, and cropping calendars. Validation using very high-resolution street view images from Google Earth showed that the predicted map had an overall accuracy of 95.95%, with a kappa coefficient of 0.92. In addition, the predicted crop calendars agreed well with the local government’s granary data. The results show that the proposed phenology-based method is cost-effective and can accurately map rice fields and growth stages over large areas. The information will be helpful in measuring the achievement of self-sufficiency in rice production and estimates of methane emissions from rice cultivation.

Identification of Crop Type Based on C-AENN Using Time Series Sentinel-1A SAR Data

Crop type identification is the initial stage and an important part of the agricultural monitoring system. It is well known that synthetic aperture radar (SAR) Sentinel-1A imagery provides a reliable data source for crop type identification. However, a single-temporal SAR image does not contain enough features, and the unique physical characteristics of radar images are relatively lacking, which limits its potential in crop mapping. In addition, current methods may not be applicable for time -series SAR data. To address the above issues, a new crop type identification method was proposed. Specifically, a farmland mask was firstly generated by the object Markov random field (OMRF) model to remove the interference of non-farmland factors. Then, the features of the standard backscatter coefficient, Sigma-naught (σ0), and the normalized backscatter coefficient by the incident angle, Gamma-naught (γ0), were extracted for each type of crop, and the optimal feature combination was found from time -series SAR images by means of Jeffries-Matusita (J-M) distance analysis. Finally, to make efficient utilization of optimal multi-temporal feature combination, a new network, the convolutional-autoencoder neural network (C-AENN), was developed for the crop type identification task. In order to prove the effectiveness of the method, several classical machine learning methods such as support vector machine (SVM), random forest (RF), etc., and deep learning methods such as one dimensional convolutional neural network (1D-CNN) and stacked auto-encoder (SAE), etc., were used for comparison. In terms of quantitative assessment, the proposed method achieved the highest accuracy, with a macro-F1 score of 0.9825, an overall accuracy (OA) score of 0.9794, and a Kappa coefficient (Kappa) score of 0.9705. In terms of qualitative assessment, four typical regions were chosen for intuitive comparison with the sample maps, and the identification result covering the study area was compared with a contemporaneous optical image, which indicated the high accuracy of the proposed method. In short, this study enables the effective identification of crop types, which demonstrates the importance of multi-temporal radar images in feature combination and the necessity of deep learning networks to extract complex features.