Rice Crop Detection Using LSTM, Bi-LSTM, and Machine Learning Models from Sentinel-1 Time Series

Abstract

The Synthetic Aperture Radar (SAR) time series allows describing the rice phenological cycle by the backscattering time signature. Therefore, the advent of the Copernicus Sentinel-1 program expands studies of radar data (C-band) for rice monitoring at regional scales, due to the high temporal resolution and free data distribution. Recurrent Neural Network (RNN) model has reached state-of-the-art in the pattern recognition of time-sequenced data, obtaining a significant advantage at crop classification on the remote sensing images. One of the most used approaches in the RNN model is the Long Short-Term Memory (LSTM) model and its improvements, such as Bidirectional LSTM (Bi-LSTM). Bi-LSTM models are more effective as their output depends on the previous and the next segment, in contrast to the unidirectional LSTM models. The present research aims to map rice crops from Sentinel-1 time series (band C) using LSTM and Bi-LSTM models in West Rio Grande do Sul (Brazil). We compared the results with traditional Machine Learning techniques: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), and Normal Bayes (NB). The developed methodology can be subdivided into the following steps: (a) acquisition of the Sentinel time series over two years; (b) data pre-processing and minimizing noise from 3D spatial-temporal filters and smoothing with Savitzky-Golay filter; (c) time series classification procedures; (d) accuracy analysis and comparison among the methods. The results show high overall accuracy and Kappa (>97% for all methods and metrics). Bi-LSTM was the best model, presenting statistical differences in the McNemar test with a significance of 0.05. However, LSTM and Traditional Machine Learning models also achieved high accuracy values. The study establishes an adequate methodology for mapping the rice crops in West Rio Grande do Sul.

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

“…The best model occurs in S6, which means that the bi-directional architecture performs better than the single directional architecture for two-day-ahead forecasting after hyperparameter optimisation. The outperformance of the bi-directional architecture has been claimed by many studies [52,53,60,66] in other domains and is still supported by this research when applying to runoff forecasting.…”

“…The combination of several layers of the basic LSTM or GRU cells may enhance the model's ability when learning the nonlinear relationships and provide a better prediction accuracy [53,60]. The typical structure of a stacked GRU network with two layers is shown in Figure 3.…”

Instance Segmentation for Large, Multi-Channel Remote Sensing Imagery Using Mask-RCNN and a Mosaicking Approach

“…DL enables pattern recognition in different data abstraction levels, varying from low-level information (corners and edges), up to high-level information (full objects) [4]. This approach achieves state-of-the-art results in different applications in remote sensing digital image processing [5]: pan-sharpening [6][7][8][9]; image registration [10][11][12][13], change detection [14][15][16][17], object detection [18][19][20][21], semantic segmentation [22][23][24][25], and time series analysis [26][27][28][29]. The classification algorithms applied in remote sensing imagery uses spatial, spectral, and temporal information to extract characteristics from the targets, where a wide variety of targets show significant results: clouds [30][31][32][33], dust-related air pollutant [34][35][36][37] land-cover/land-use [38][39][40][41], urban features [42][43][44][45], and ocean [46][47]…”

Understanding Dense Time Series of Sentinel-1 Backscatter from Rice Fields: Case Study in a Province of the Mekong Delta, Vietnam

“…The first category uses supervised classification algorithms which require a large number of training samples of the same rice season. Machine learning techniques such as Random Forest or Support-Vector Machines have been used for rice mapping in India [8], in Myanmar [9], in Vietnam [10], in France [11], in China [12], and in Brazil [13]). More classical methods such as K-means have also been used, for example in India [14] and in China [15].…”