Hyperspectral Models for Estimating Chlorophyll Content of Young Apple Tree Leaves

Abstract

A hyperspectral-based chlorophyll content estimating model for young apple tree leaves is proposed in this paper. It aims to have a contribution to modernized production and scientific management. The study takes the trees, which are two years old as the research objects. The young apple tree leaves are picked in autumn when they stop growing, and the spectral data and the chlorophyll content in the leaves of young apple trees are measured. First derivative (FD) is used to process the spectral data, and choose sensitive parameters. Hyperspectral models for estimating chlorophyll content in the leaves of young apple trees are established by a single variable (use one variable to establish models) and partial least square (PLS) methods. Four sensitive parameters are chosen to establish hyperspectral estimating models using partial least square. The model has the highest R² (coefficient of determination), lower RMSE (root mean square error) and RE% (relative error). The partial least square model is more appropriate for estimating chlorophyll content in the leaves of young apple tree.

Keywords::

• The leaves of young apple trees
• Hyperspectral characteristics
• Chlorophyll content
• Estimating model

Additional information

Notes on contributors

Zhuoyuan Wang

Z. Y. Wang received B.S degree in Geographic Information Systems from Shandong Agricultural University, China in 2012, and now is working on his Master degree in Land Resource Management at Shandong Agricultural University. His current research interest is using hyperspectral of apple leaves to monitoring the growth of the apple trees.

Xicun Zhu

X. C. Zhu received Ph.D. degree in Soil Science from the Shandong Agricultural University, China. He is an associate professor in College of Resources and Environment Shandong Agricultural University. His research interests include the applications of agricultural remote sensing and information technology. He has published over 20 papers in many periodicals. He is the corresponding author of this paper.

Xianyi Fang

X.Y. Fang received B.S. degree from Shandong Agricultural University, China in 2012. Currently he is working on his master degree in college of resources and environment at Shandong Agricultural University. His research interests include hyperspectrum, plant diseases and space remote sensing.

Yan-an Wang

Y. A. Wang received B.Sc. degree in Biology from Shandong Normal University, and the Ph.D. degree in Pomology from the Shandong Agricultural University, China. He is a professor in College of Life Science Shandong Agricultural University, State Key Laboratory of Crop Biology, and the National Research Center for Apple Engineering and Technology. His research interests include the application modeling of plant growth physiological processes and intelligent control technology, the construction of digital orchard and precision agriculture technology. He has published over 30 papers in many periodicals.