Abstract

An inversion method based on a neural network was used to estimate water and dry matter contents on plant leaves, from transmittance and reflectance measurements, using light emitting diodes (LEDs) at specific wavelengths in NIR and FIR. The preliminary results for the predicted water content by the neural network method showed a RMSE value of $0.0027\mathrm{g}/{\mathrm{cm}}^2$ and $|\sigma |$ value of approximately 3.53%, computed on 127 plant leaf samples over 51 species. Dry matter estimation also was performed, which showed potential implementation after future improvements. We believe this inversion method could be implemented in a portable system based on any silicon platform with the capability to perform in situ measurements on plant tissue.

© 2015 Optical Society of America

Biophotonic in situ sensor for plant leaves

Elian Conejo, Jean-Pierre Frangi, and Gilles de Rosny
Appl. Opt. 49(10) 1687-1697 (2010)

Effect of different regression algorithms on the estimating leaf parameters based on selected characteristic wavelengths by using the PROSPECT model

Yangyang Zhang, Jian Yang, Xiuguo Liu, Lin Du, Shuo Shi, Jia Sun, and Biwu Chen
Appl. Opt. 58(36) 9904-9913 (2019)

Nondestructive nitrogen content estimation in tomato plant leaves by Vis-NIR hyperspectral imaging and regression data models

Razieh Pourdarbani, Sajad Sabzi, Mohammad H. Rohban, Ginés García-Mateos, and Juan I. Arribas
Appl. Opt. 60(30) 9560-9569 (2021)

Speckle correlation photography for the study of water content and sap flow in plant leaves

Mohammad R. Riahi, Hamid Latifi, and Mohsen Sajjadi
Appl. Opt. 45(29) 7674-7678 (2006)

Neural network method to correct bidirectional effects in water-leaving radiance

Yongzhen Fan, Wei Li, Kenneth J. Voss, Charles K. Gatebe, and Knut Stamnes
Appl. Opt. 55(1) 10-21 (2016)