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

Abstract

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.

Characterization of Vegetation and Prediction of Biomass Production in Silage Corn Crop Based on Satellite Images

“…The variation of the NDMI index in relation to time (t, days) was described by equation (10) under conditions of R 2 =0.934, p<0.001, F=47.18. The variation of the NDVI index in relation to time (t, days) was described by equation (11) under conditions of R 2 =0.941, p<0.001, F=53.92. The variation of the NBR index in relation to time (t, days) during the study period was described by equation (12), under conditions of R 2 =0.961, p<0.001, F=83.225.…”

“…In general, high levels of statistical accuracy were communicated in estimating production based on remote sensing techniques, due to the fact that the vegetation reflects well through the status of the plants, the chlorophyll content, or other representative physiological indices, the vegetation conditions, the technological level of the process of production, and these aspects are well and correctly captured in the satellite images, as data in the form of spectral information (Guo et al, 2022). For example, Amankulova et al ( 2023) have reported very high accuracy (RMSE with values between 121.9 and 284.5 kg ha -1 ) in the prediction of sunflower production, based on satellite images in the Sentinel-2 system.…”

Optimal feature extraction from multidimensional remote sensing data for orchard identification based on deep learning methods

“…31 Additionally, in the field of image classification, convolutional neural networks (CNNs) have gained widespread acceptance due to their proficiency in effectively extracting spatial-temporal features. 32 For instance, Guo et al 33 introduced a convolutional-autoencoder neural network (C-AENN), which combined 1D-CNN and SAE techniques. When compared to traditional machine learning methods, the results demonstrated that C-AENN outperformed them in the task of crop classification, even with limited training data.…”

A New Intrusion Detection System for the Internet of Things via Deep Convolutional Neural Network and Feature Engineering

“…Several researchers have worked on IDSs in which machine learning (ML) and deep learning (DL) models play a key role [ 10 ]. ML and DL techniques are widely used in different fields, such as in agriculture [ 11 ], medical [ 12 ], and automobile industries [ 13 , 14 ]. DL is a branch of ML, and it is generalizable to new problems with complicated and high-dimensional data.…”