A convolution neural network for forest leaf chlorophyll and carotenoid estimation using hyperspectral reflectance

Forest leaf chlorophyll (C-ab) and carotenoid (C-xc) are key functional indicators for the state of the forest ecosystem. Current machine learning models based on hyperspectral reflectance are widely applied to estimate leaf C-ab and C-xc contents at leaf scale. However, these models have certain accuracy for non-independent datasets but have poor generalization for independent datasets when they are used to estimate leaf C-ab and C-xc contents. This fact limits that hyperspectral remote sensing completely replaces destructive measurements for leaf C-ab and C-xc contents. Thus, the development of an estimation model with high accuracy and satisfactory generalization is necessary. Convolutional neural networks (CNNs) have certain accuracy and generalization in many domains, and have the potential to solve above-mentioned problem. Therefore, this study developed a CNN using onedimensional hyperspectral reflectance, which aimed to improve the model's accuracy and generalization in leaf C-ab and C-xc content estimation at leaf scale. The proposed CNN was developed by three steps. First, in consideration of the correlation between leaf C-ab and C-xc contents in natural leaves, 2500 physical data with leaf reflectance and corresponding C-ab and C-xc contents were generated by leaf radiative transfer model and multi variable gaussian distribution function. Then, the proposed CNN was built by five strategies based on the architecture of the AlexNet. Finally, five-fold cross validation was performed with 70% of the physical data to determine the best strategy to develop the proposed CNN. These were executed to ensure the proposed CNN with the maximum accuracy and generalization. In addition, the accuracy and generalization of the proposed CNN were tested using a non-independent dataset and an independent dataset, respectively. The proposed CNN was also compared with back propagation neural network (BPNN), support vector regression (SVR) and gaussian process regression (GPR). Results showed that the best CNN could be developed with one input, five convolutional, three max-pooling and three fully-connected layers. Comprehensively considering the model's accuracy and generalization, the proposed CNN was the best model for leaf C-ab and C-xc content estimation compared with BPNN, SVR and GPR. This study provides a development strategy of CNN estimation model using onedimensional hyperspectral reflectance at leaf scale. The proposed CNN could further promote the practical application of hyperspectral remote sensing in leaf C-ab and C-xc content estimation.