• Home
  • Search
  • Rice Crop Detection Using LSTM, Bi-LSTM, and Machine Learning Models from Sentinel-1 Time Series
  • Open Access IconOpen Access
  • Cite Icon194
  • https://doi.org/10.3390/rs12162655Copy DOI Icon

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

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
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.

Loading PDF

Similar Papers
  • Research Article

Evaluating the Effectiveness of CNN, LSTM, and Bi-LSTM Models in Classifying Twitter Sentiments

  • Mar 04, 2025
  • Journal of Information Systems Engineering and Management
  • Naveen P
  • Conference Article
  • Citations1543

The Performance of LSTM and BiLSTM in Forecasting Time Series

  • Dec 01, 2019
  • Sima Siami-Namini +2
  • Conference Article

Neural Network-based Approach to Predict Protein Secondary Structure

  • May 04, 2023
  • Arifur Rahman +2
  • Book Chapter
  • Citations9

CHAPTER 3 - Recurrent neural network: application in facies classification

  • Jan 01, 2022
  • Advances in Subsurface Data Analytics
  • Miao Tian +1
  • PDF
  • Research Article
  • Citations2

Deep Learning with Bidirectional Long Short-Term Memory for traffic flow Prediction

  • Jul 01, 2021
  • Journal of Physics: Conference Series
  • Song Xue +3
  • Conference Article
  • Citations310

Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model

  • Oct 24, 2020
  • Md Arif Istiake Sunny +2
  • Research Article
  • Citations1

Advanced sentiment analysis in online shopping: Implementing LSTM models analyzing E-commerce user sentiments

  • Jul 30, 2025
  • Nonlinear Engineering
  • Liyuan Lu
  • PDF
  • Research Article

An Evaluation of Bidirectional Long Short-Term Memory Model for Estimating Monthly Rainfall in India

  • Apr 24, 2024
  • Indian Journal of Science and Technology
  • Chawngthu Zoremsanga +1
  • Research Article
  • Citations4

Stock Price prediction with LSTM Based Deep Learning Techniques

  • Aug 29, 2021
  • Zenodo (CERN European Organization for Nuclear Research)
  • Sailesh Sathish +1
  • PDF
  • Research Article

Forecasting Stock Prices via Deep Learning During COVID-19: A Case Study from an Emerging Economy

  • Jan 01, 2024
  • European Journal of Theoretical and Applied Sciences
  • Yasemin Ulu
  • Book Chapter
  • Citations1

Gujarati Task Oriented Dialogue Slot Tagging Using Deep Neural Network Models

  • Jan 01, 2021
  • Rachana Parikh +1
  • PDF
  • Research Article
  • Citations78

Clinical Relation Extraction Toward Drug Safety Surveillance Using Electronic Health Record Narratives: Classical Learning Versus Deep Learning

  • Apr 25, 2018
  • JMIR Public Health and Surveillance
  • Tsendsuren Munkhdalai +2
  • Research Article
  • Citations9

Detection of communicable and non-communicable diseases using hyperparameter optimization with Bi-LSTM model in pathology images

  • Mar 22, 2022
  • International Journal of Intelligent Computing and Cybernetics
  • Shiva Sumanth Reddy +1
  • PDF
  • Research Article
  • Citations58

Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals.

  • Jun 01, 2023
  • Diagnostics
  • Bishwajit Roy +6
  • Research Article
  • Citations87

Driver distraction detection based on vehicle dynamics using naturalistic driving data

  • Jan 24, 2022
  • Transportation Research Part C: Emerging Technologies
  • Xuesong Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.