UAV Remote Sensing Estimation of Rice Yield Based on Adaptive Spectral Endmembers and Bilinear Mixing Model

Ningge Yuan,Xianting Wu,Shenghui Fang,Renshan Zhu,Bo Duan,Kaili Yang,Yating Liu,Yan Gong

doi:10.3390/rs13112190

Abstract

The accurate estimation of rice yield using remote sensing (RS) technology is crucially important for agricultural decision-making. The rice yield estimation model based on the vegetation index (VI) is commonly used when working with RS methods, however, it is affected by irrelevant organs and background especially at heading stage. The spectral mixture analysis (SMA) can quantitatively obtain the abundance information and mitigate the impacts. Furthermore, according to the spectral variability and information complexity caused by the rice cropping system and canopy characteristics of reflection and scattering, in this study, the multi-endmember extraction by the pure pixel index (PPI) and the nonlinear unmixing method based on the bandwise generalized bilinear mixing model (NU-BGBM) were applied for SMA, and the VIE (VIs recalculated from endmember spectra) was integrated with abundance data to establish the yield estimation model at heading stage. In two paddy fields of different cultivation settings, multispectral images were collected by an unmanned aerial vehicle (UAV) at booting and heading stage. The correlation of several widely-used VIs and rice yield was tested and weaker at heading stage. In order to improve the yield estimation accuracy of rice at heading stage, the VIE and foreground abundances from SMA were combined to develop a linear yield estimation model. The results showed that VIE incorporated with abundances exhibited a better estimation ability than VI alone or the product of VI and abundances. In addition, when the structural difference of plants was obvious, the addition of the product of VIF (VIs recalculated from bilinear endmember spectra) and the corresponding bilinear abundances to the original product of VIE and abundances, enhanced model reliability. VIs using the near-infrared bands improved more significantly with the estimation error below 8.1%. This study verified the validation of the targeted SMA strategy while estimating crop yield by remotely sensed VI, especially for objects with obvious different spectra and complex structures.

Highlights

Introductionvegetation index (VI) have exhibited good potential in remote estimation of crop yield especially at large scales [8,9]
We developed a full unmanned aerial vehicle (UAV)-based approach to improve the estimation of rice yield at heading stage using the vegetation index and abundance of multi-endmembers, with consideration of second-order scattering in paddy plots
The pure pixel index (PPI) was calculated to extract multiple endmembers and the NU-BGBM was applied to acquire the abundances of the foreground which were more approximate to the true value

Summary

Introduction

VIs have exhibited good potential in remote estimation of crop yield especially at large scales [8,9]. Parametric regression models based on VIs are by far the oldest and largest group of variable estimation approaches [10], including simple linear functions and complex non-linear functions in general [11]. Linear regression between VIs and yield has been proposed to accurately estimate the yield of many cash crops, such as wheat [12], cotton [13], maize [14], rapeseed [15] etc. Swain [16] developed a linear regression model of normalized difference vegetation index (NDVI) of UAV images and rice yield with a

Methods

Results

Discussion

Conclusion