Parcel level staple crop type identification based on newly defined red-edge vegetation indices and ORNN

Abstract

It is of strategic importance for early estimating planting area and crop yield to identify staple crop types on parcel level in a remotely sensed way. Limited by remote sensor imaging mechanism and current sensor technology, remote sensing images usually cannot be of high resolution in both spatial and spectral aspects. So, it has been found in many studies that supplementary data or features such as synthetic aperture radar data or temporal characteristic of time series data are usually integrated for crop type identification, which demands lots of data and overlooks the most typical spectral characteristics. Thanks to the expanded detecting bands of several moderate resolution optical satellites, the red-edge bands reflecting specific spectral features of crops are available for precise classification. Nevertheless, only a few studies have concentrated on these bands and the potential value of red-edge bands has not been sufficiently stretched in practical use. In this study, two newly defined red-edge vegetation indices (REVIs) and their time series data have been used for distinguishing different crops efficiently. Firstly, according to the reflectance characteristics in optical images and the data distribution of crops in feature space, two kinds of variants of REVIs based on green band and red-edge band, namely, ReG_RVI and ReG_NDVI have been proposed. Then, the time series data of REVIs can be generated from remote sensing images and be fed into the recurrent neural network (RNN) as training data for crop type classification. Finally, object based image analysis and RNN are combined with the idea of majority voting to achieve accurate crop type identification on cultivated land parcel level. The experimental results of two study areas using time series images captured by Gaofen 6 wide field of view sensor show an overall accuracy of above 90 % in identifying crop types, which proves the effectiveness of the newly defined REVIs and the feasibility of the proposed methodology. The predicted model based on ReG_RVI time series data performed more stable. In addition, the proposed REVIs have been transferred to other satellite sensor images captured by Sentinel 2 to testify 16 crop types and the experimental results indicate that the proposed indices also had general applicability to a certain extent. In summary, the contribution of this article is that the newly defined REVIs exploit red-edge information more sufficiently and the proposed methodology provides an effective solution for accurate identification and mapping of crop types in large areas at the cultivated land parcel scale.