Grain Yield Estimation in Rice Breeding Using Phenological Data and Vegetation Indices Derived from UAV Images

Haixiao Ge,Fei Ma,Changwen Du,Zhenwang Li

doi:10.3390/agronomy11122439

Abstract

The accurate estimation of grain yield in rice breeding is crucial for breeders to screen and select qualified cultivars. In this study, a low-cost unmanned aerial vehicle (UAV) platform mounted with an RGB camera was carried out to capture high-spatial resolution images of rice canopy in rice breeding. The random forest (RF) regression techniques were used to establish yield models by using (1) only color vegetation indices (VIs), (2) only phenological data, and (3) fusion of VIs and phenological data as inputs, respectively. Then, the performances of RF models were compared with the manual observation and CERES-Rice model. The results indicated that the RF model using VIs only performed poorly for estimating yield; the optimized RF model that combined the use of phenological data and color VIs performed much better, which demonstrated that the phenological data significantly improved the model performance. Furthermore, the yield estimation accuracy of 21 rice cultivars that were continuously planted over three years in the optimal RF model had no significant difference (p > 0.05) with that of the CERES-Rice model. These findings demonstrate that the RF model, by combining phenological data and color Vis, is a potential and cost-effective way to estimate yield in rice breeding.

Highlights

Rice (Oryza sativa L.), one of the most important food crops in the world, is consumed by more than half of the global population [1], especially in East Asia and Southeast Asia
14 vegetation indices (VIs) derived from unmanned aerial vehicle (UAV)-based images and phenological data were used to estimate grain yield in rice breeding from 2017 to 2019
Three random forest (RF) models based on VIs and phenological variables were constructed for yield estimation

Summary

Introduction

Rice (Oryza sativa L.), one of the most important food crops in the world, is consumed by more than half of the global population [1], especially in East Asia and Southeast Asia. Satellite imagery-based remote sensing (RS) data have been widely used for monitoring crop growth status and nutritional conditions [5,6]. Yield prediction models were established based on meteorological factors and an RS vegetation index (VI) using the multiple linear regression technique [7], and it was found that the inclusion of remote sensing data could significantly improve the yield prediction accuracy. The enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) data derived from the moderate resolution imaging spectroradiometer (MODIS) were compared for estimating rice yield, and the result indicated that the EVI-based models were slightly more accurate than the NDVI-based models [1]. Satellite imagery had conflict between spatial and temporal resolutions, and the quality of RS data was considerably affected by atmospheric interference [8,9]. Synthetic aperture radar (SAR) techniques that could penetrate vegetation canopies were not influenced by clouds [10,11], it was difficult to exactly extract crop information due to the small size of farmlands in the south of China

Objectives

Methods

Results

Discussion

Conclusion