High?throughput phenotyping of two plant?size traits of Eucalyptus species using neural networks

• 作 者: Marcus Vinicius Vieira Borges Janielle de Oliveira Garcia Tays Silva Batista Alexsandra Nogueira Martins Silva Fabio Henrique Rojo Baio Carlos Ant?nio da Silva Junior Gileno Brito de Azevedo Glauce Ta
• 机 构: Federal University of Mato Grosso Do Sul(UFMS), Chapad?o Do Sul,Mato Grosso Do Sul 79560000,Brazil;D
• 出 处: 林业研究（英文版）
• 发表日期: 2022年2期
• 关键词: Computational intelligence Diameter at breast height Forest inventory Remote sen

In forest modeling to estimate the volume of wood, artificial intelligence has been shown to be quite effi-cient, especially using artificial neural networks (ANNs). Here we tested whether diameter at breast height (DBH) and the total plant height (Ht) of eucalyptus can be pre-dicted at the stand level using spectral bands measured by an unmanned aerial vehicle (UAV) multispectral sensor and vegetation indices. To do so, using the data obtained by the UAV as input variables, we tested different configurations (number of hidden layers and number of neurons in each layer) of ANNs for predicting DBH and Ht at stand level for different Eucalyptus species. The experimental design was randomized blocks with four replicates, with 20 trees in each experimental plot. The treatments comprised five Eucalyptus species (E. camaldulensis, E. uroplylla, E. saligna, E. gran-dis, and E. urograndis) and Corymbria citriodora. DBH and Ht for each plot at the stand level were measured seven times in separate overflights by the UAV, so that the multispectral sensor could obtain spectral bands to calculate vegetation indices (VIs). ANNs were then constructed using spectral bands and VIs as input layers, in addition to the categorical variable (species), to predict DBH and Ht at the stand level simultaneously. This report represents one of the first appli-cations of high-throughput phenotyping for plant size traits in Eucalyptus species. In general, ANNs containing three hidden layers gave better statistical performance (higher esti-mated r, lower estimated root mean squared error–RMSE) due to their greater capacity for self-learning. Among these ANNs, the best contained eight neurons in the first layer, seven in the second, and five in the third (8 ? 7 ? 5). The results reported here reveal the potential of using the gener-ated models to perform accurate forest inventories based on spectral bands and VIs obtained with a UAV multispectral sensor and ANNs, reducing labor and time.