Rice Crop Detection Using LSTM, Bi-LSTM, and Machine Learning Models from Sentinel-1 Time Series
Top Cited Papers
Open Access
- 18 August 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (16), 2655
- https://doi.org/10.3390/rs12162655
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.Keywords
This publication has 128 references indexed in Scilit:
- Remotely Sensed Rice Yield Prediction Using Multi-Temporal NDVI Data Derived from NOAA's-AVHRRPLOS ONE, 2013
- Mapping the irrigated rice cropping patterns of the Mekong delta, Vietnam, through hyper-temporal SPOT NDVI image analysisInternational Journal of Remote Sensing, 2011
- Speckle reduction for the forest mapping analysis of multi-temporal Radarsat-1 imagesInternational Journal of Remote Sensing, 2011
- On the Suitability of MODIS Time Series Metrics to Map Vegetation Types in Dry Savanna Ecosystems: A Case Study in the Kalahari of NE NamibiaRemote Sensing, 2009
- Mapping rice field anopheline breeding habitats in Mali, West Africa, using Landsat ETM+ sensor dataInternational Journal of Remote Sensing, 2004
- Estimation of rice-planted area in the tropical zone using a combination of optical and microwave satellite sensor dataInternational Journal of Remote Sensing, 1999
- Rice crop area estimation of an administrative division in China using remote sensing dataInternational Journal of Remote Sensing, 1998
- Classification of multi-temporal SPOT-XS satellite data for mapping rice fields on a West African floodplainInternational Journal of Remote Sensing, 1998
- The identification of rice fields using multi-temporal ERS-1 C band SAR dataInternational Journal of Remote Sensing, 1997
- Early estimation of rice area using temporal ERS-1 synthetic aperture radar data a case study for the Howrah and Hughly districts of West Bengal, IndiaInternational Journal of Remote Sensing, 1997