Main content area

Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery

Zheng, Hengbiao, Cheng, Tao, Zhou, Meng, Li, Dong, Yao, Xia, Tian, Yongchao, Cao, Weixing, Zhu, Yan
Precision agriculture 2019 v.20 no.3 pp. 611-629
aboveground biomass, altitude, cameras, canopy, crop management, crop yield, crops, cultivars, forests, growing season, heading, nitrogen, plant breeding, plant density, regression analysis, rice, soil, spectral analysis, texture, unmanned aerial vehicles, vegetation index, yield forecasting
Crop aboveground biomass (AGB) is one of the most important indicators in crop breeding and crop management, and can be used for crop yield prediction. A number of vegetation indices (VIs) have been proposed to estimate crop biomass, but they perform poorly at high biomass levels and are easily affected by background materials. Texture analysis has been proved to be an efficient approach in forest biomass estimation, but has never been applied to crops with low-altitude unmanned aerial vehicle (UAV) images. The objective of this study was to improve rice AGB estimation by combining textural and spectral analysis of UAV imagery. A two-year rice experiment was conducted in 2015 and 2016, involving different nitrogen (N) rates, planting densities and rice cultivars with three replicates. A six-band multispectral (MS) camera was mounted on a UAV to acquire rice canopy images at critical stages during the rice growing seasons and concurrent field samplings were taken. Simple regression and stepwise multiple linear regression models were developed between biomass data from the two-year experiment and image parameters derived from four different types of feature sets. These features represented commonly used VIs, texture parameters, normalization of texture measurements (normalized difference texture index, NDTI) and combinations of VIs and NDTIs. Finally, all the regression models were evaluated by cross-validation over pooled data with the coefficient of determination (R²) and the root mean square error (RMSE). Results demonstrated that the optimized soil adjusted vegetation index (OSAVI) exhibited the best relationship with AGB for the whole season (R² = 0.63) and post-heading stages (R² = 0.65). Red-edge-based indices yielded best performance (R² > 0.70) only for the growth stages before heading. The texture measurement mean (MEA) from the NIR band was the best among the eight candidates in AGB estimation. Texture index (NDTI (MEA₈₀₀, MEA₅₅₀)) was superior to all the evaluated VIs in estimating AGB for the whole season (R² = 0.75) and pre-heading stages (R² = 0.84). Further improvement was obtained across the whole season by combining NDTIs and VIs through a multiple linear regression. This multivariate model produced the highest estimation accuracy for all stages (R² = 0.78 and RMSE = 1.84 t ha⁻¹) and different stage groups (R² = 0.84 and RMSE = 1.06 t ha⁻¹ for pre-heading stages and R² = 0.65 and RMSE = 1.94 t ha⁻¹ for post-heading stages). The findings imply that the integration of textural information with spectral information significantly improves the accuracy for rice biomass estimation compared to the use of spectral information alone.