Nondestructive estimation of leaf chlorophyll content in banana based on unmanned aerial vehicle hyperspectral images using image feature combination methods

Weiping Kong ^1,2* Lingling Ma ² Huichun Ye ² Jingjing Wang ³ Chaojia Nie ² Xianfeng Zhou ⁴ Wenjiang Huang ² Zikun Fan ²

• ¹ Chinese Academy of Sciences (CAS), Beijing, China
• ² Aerospace Information Research Institute, Chinese Academy of Sciences (CAS), Beijing, Beijing, China
• ³ School of Forestry, Hainan University, Haikou, China
• ⁴ College of Life Information Science and Instrument Engineering, Hangzhou Dianzi University, Hangzhou, Jiangsu Province, China

Nondestructive quantification of leaf chlorophyll content (LCC) of banana and its spatial distribution across growth stages from remotely sensed data provide an effective avenue to diagnose nutritional deficiency and guide management practices. Unmanned aerial vehicle (UAV) hyperspectral imagery can document abundant texture features (TFs) and spectral information in field experiment due to the high spatial and spectral resolutions. However, the benefits of using the fine spatial resolution accessible from UAV data for estimating LCC for banana have not been adequately quantified. In this study, two types of image features including vegetation indices (VIs) and TFs extracted from the first three principal component analyzed images (TFs-PC1, TFs-PC2, TFs-PC3) were employed. We proposed two methods of image feature combination for banana LCC inversion, which are a two-pair feature combination and a multivariable feature combination based on four machine learning algorithms (MLRAs). The results indicated that compared to conventionally used VIs alone, the banana LCC estimated with both proposed VI and TF combination methods were all significantly improved. Comprehensive analyses of the linear relationships between all constructed two-pair feature combinations and LCC indicated that the ratio of Mean to Modified red-edge sample ratio index (MEA/MSRre) stood out (R2=0.745, RMSE=2.17). For multivariable feature combinations, four MLRAs using original or two selected VIs and TFs-PC1 combination groups resulted in better LCC estimation than other input variables. We concluded that the nonlinear Gaussian process regression model with the VIs and TFs-PC1 combination selected by maximal information coefficient as input achieved the highest accuracy in LCC prediction for banana, with the highest R2 of 0.776 and lowest RMSE of 2.04. This study highlights the potential of the proposed image feature combination method for deriving high resolution maps of banana LCC fundamental for precise nutritional diagnosing and operational agriculture management.