Synchronous Response Analysis of Features for Remote Sensing Crop Classification Based on Optical and SAR Time-Series Data.

Yingwei Sun,Xiaodong Hu,Tianjun Wu,Ya’Nan Zhou,Yingpin Yang,Jiancheng Luo,Wei Liu,Zhongfa Zhou,Lijing Gao,Wen Dong,Lingyu Wang,Hao Liu

doi:10.3390/s19194227

Abstract

Accurate crop classification is the basis of agricultural research, and remote sensing is the only effective measuring technique to classify crops over large areas. Optical remote sensing is effective in regions with good illumination; however, it usually fails to meet requirements for highly accurate crop classification in cloud-covered areas and rainy regions. Synthetic aperture radar (SAR) can achieve active data acquisition by transmitting signals; thus, it has strong resistance to cloud and rain interference. In this study, we designed an improved crop planting structure mapping framework for cloudy and rainy regions by combining optical data and SAR data, and we revealed the synchronous-response relationship of these two data types. First, we extracted geo-parcels from optical images with high spatial resolution. Second, we built a recurrent neural network (RNN)-based classifier suitable for remote sensing images on the geo-parcel scale. Third, we classified crops based on the two datasets and established the network. Fourth, we analyzed the synchronous response relationships of crops based on the results of the two classification schemes. This work is the basis for the application of remote sensing data for the fine mapping and growth monitoring of crop planting structures in cloudy and rainy areas in the future.

Highlights

Reliable agricultural information is an important basis for ensuring regional food security, and it has always been valued by countries worldwide
This paper conducted a preliminary study for the established research system, and we explored the synchronous response relationships for crops in Zhongning County between Landsat-8 time-series data and Sentinel-1 time-series data at the geo-parcel scale
This paper demonstrates the research framework we developed for crop planting structure mapping in cloudy and rainy areas based on the synchronous-response mechanism of optical data and Synthetic aperture radar (SAR) data, and we have revealed the preliminary research results, but there is still much work to be done

Summary

Introduction

Reliable agricultural information is an important basis for ensuring regional food security, and it has always been valued by countries worldwide. Remote sensing technology can be used to obtain information on the planting areas and types of crops in a timely and rapid manner. With the development of remote sensing technology, remote sensing is becoming an important way to obtain farmland information, and it represents an important data source for crop species identification, growth analysis, and area measurement. Crop classification and planting area measurements are the main components of agricultural monitoring, and they represent two of the main topics of remote sensing research. In the optical remote sensing domain, high-resolution images can provide rich spatial and spectral information [2,3] and vegetation indices, such as normalized differential crop index (NDVI) time-series data, to improve the efficiency of crop classification [4]. Based on time-series optical data, previous studies have effectively identified soybeans, rice, corn, and other major crops, and the use of this type of data has improved the efficiency of crop classification [5,6,7,8]

Methods

Results

Discussion

Conclusion