Abstract

Abstract. Crop classification is an important task in many crop monitoring applications. Satellite remote sensing has provided easy, reliable, and fast approaches to crop classification task. In this study, a comparative analysis is made on the performances of various deep neural network (DNN) models for crop classification task using polarimetric synthetic aperture radar (PolSAR) and optical satellite data. For PolSAR data, Sentinel 1 dual pol SAR data is used. Sentinel 2 multispectral data is used as optical data. Five land cover classes including two crop classes of the season are taken. Time series data over the period of one crop cycle is used. Training and testing samples are measured and collected directly from the ground over the study region. Various convolutional neural network (CNN) and long short-term memory (LSTM) models are implemented, analysed, evaluated, and compared. Models are evaluated on the basis of classification accuracy and generalization performance.

Highlights

  • AND RELATED WORKCrop classification is an important task in many crop monitoring applications such as generation of crop maps, crop yield estimation, crop rotation records, and soil productivity (Löw et al 2013)

  • The convolutional neural network (CNN) model is applied on the data for crop classification

  • 3.6 Convolutional long short-term memory (LSTM) (ConvLSTM) models. These models are a hybrid of convolutional models and LSTM models explained in the previous sections

Read more

Summary

Introduction

AND RELATED WORKCrop classification is an important task in many crop monitoring applications such as generation of crop maps, crop yield estimation, crop rotation records, and soil productivity (Löw et al 2013). SAR and optical satellite image data complement each other in agricultural applications like crop classification (Blaes, Vanhalle, and Defourny 2005). Since the inception of CNNs into image processing scientific community, they have been the “state of the art” in many image classification applications especially when the dimension of image increases. This property of CNNs made them suitable for various remote sensing applications (Zhu et al 2017). CNNs learn features from data instead of “hand-engineering” them. This aspect makes the algorithm faster and less “pre-processing” intensive. The architectural and functional components of CNNs are described in the following sub-sections

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call