Deep chemometrics for nondestructive photosynthetic pigments prediction using leaf reflectance spectra  

作　　者：Kestrilia Rega Prilianti Edi Setiyono Oesman Hendra Kelana Tatas Hardo Panintingjati Brotosudarmo 

机构地区：[1]Department of Informatics Engineering,Universitas Ma Chung,Villa Puncak Tidar N-01,Malang 65151,Indonesia [2]Ma Chung Research Center for Photosynthetic Pigments,Villa Puncak Tidar N-01,Malang 65151,Indonesia

出　　处：《Information Processing in Agriculture》2021年第1期194-204,共11页农业信息处理（英文）

基　　金：This work was funded by the Ministry of Research,Technology,and Higher Education of the Republic of Indonesia under Penelitian Dasar Unggulan Perguruan Tinggi(PDUPT)Scheme,(Grant No.058/SP2H/LT/MONO/L7/2019).

摘　　要：The need for the rapid assessment of the photosynthetic pigment contents in plants has encouraged the development of studies to produce nondestructive quantification methods.This need is driven by the fact that data on the photosynthetic pigment contents can provide a variety of important information that is related to plant conditions.Using deep chemometrics,we developed a novel one-dimensional convolutional neural network(CNN)model to predict the photosynthetic pigment contents in a nondestructive and real-time manner.Intact leaf reflectance spectra from spectroscopic measurements were used as the inputs.The prediction was simultaneously carried out for three main photosynthetic pigments,i.e.,chlorophyll,carotenoid and anthocyanin.The experimental results show that the prediction accuracy is very satisfying,with a mean absolute error(MAE)=0.0122±0.0004 for training and 0.0321±0.0022 for validation(data range of 0–1).

关 键 词：Convolutional neural network Deep chemometrics Leaf reflectance Nondestructive method Photosynthetic pigments 

分 类 号：Q94[生物学—植物学] TP183[自动化与计算机技术—控制理论与控制工程]