Diagnosis of winter-wheat water stress based on UAV-borne multispectral image texture and vegetation indices

• Published in: Agricultural water management Vol. 256; p. 107076
• Main Authors: Zhou, Yongcai, Lao, Congcong, Yang, Yalong, Zhang, Zhitao, Chen, Haiying, Chen, Yinwen, Chen, Junying, Ning, Jifeng, Yang, Ning
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2021
• Subjects: Image texture; Stomatal conductance; Unmanned aerial vehicle; Vegetation indices; Water stress; Image texture; Unmanned aerial vehicle; Water stress; Vegetation indices; Stomatal conductance
• ISSN: 0378-3774; 1873-2283
• DOI: 10.1016/j.agwat.2021.107076

Timely and accurate detection of crop water stress is vital for precision irrigation. Whether the accuracy of the prevailing diagnosis of crop water stress using vegetation indices (VIs) and spectral reflectance can be improved still remains to be investigated. The crop surface characteristics such as grayscale or color vary under different water stress, so in this study one more variable, image texture, was utilized together to diagnose water stress. For this end, the canopy image of winter wheat in bloom was obtained by unmanned aerial vehicle (UAV) equipped with multispectral sensor, and the effect of soil background was eliminated using vegetation index threshold method. On this basis, Grey level co-occurrence matrix (GLCM) was used to calculate the mean (MEA), variance (VAR), homogeneity (HOM), contrast (CON), dissimilarity (DIS), entropy (ENT), second moment (SEC) and correlation (COR) of the image texture under different spatial resolutions (0.008 m, 0.01 m, 0.02 m, 0.05 m, 0.1 m and 0.2 m). Next, the canopy vegetation indices were obtained by mathematical transformation of canopy reflectance, and then sensitive image texture and vegetation indices by full subset regression method. Finally, Cubist, BPNN (Back Propagation Neural Network) and ELM (Extreme Learning Machine) methods were adopted to build the estimation models of the stomatal conductance (Gs) of winter wheat (between the sensitive image texture and Gs, and between vegetation index and Gs), and the water stress map was plotted based on the optimal Gs estimation model. The result showed: (i) the image texture obtained from the high-resolution multispectral image had a high correlation with Gs, and the image texture (VAR, HOM, CON, DIS, ENT and SEC) at 550 nm had the most significant correlation; (ii) the higher the ground resolution, the higher the correlation between the Gs and the image texture, the vegetation indices, respectively. The image texture with a ground resolution of 0.008 m combined with VIs and Gs had the highest correlation, and combining image texture and vegetation index can significantly improve the estimation accuracy of winter wheat Gs; (iii) Among the three estimation models, the BPNN model constructed by combining the image texture and VIs (MEA, VAR, ENT, DWSI and EXG) had the best estimation performance (Calibration:Rc2 = 0.899, RMSEc = 0.01, MAEc = 0.006; Validation:Rc2 = 0.834, RMSEv =;0.018, MAEv = 0.014), and an accurate estimation could even be achieved at a lower Gs value. Compared with the BPNN model solely based on VIs or image texture, the Rc2 of the BPNN model based on the combined variables increased by 24% and 22.48%, respectively. Therefore, combining UAV multispectral image texture and VIs to estimate Gs provides a feasible and accurate method for water stress diagnosis of winter wheat. •The incorporation of texture improved the accuracy of water stress diagnoses with VIs.•BPNN model with VIs and texture provided the highest accuracy of Gs estimation.•UAV provides a feasible and accurate method for water stress diagnosis of winter wheat.•Removing soil background and screening methods improve the quality of remote sensing data.