[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Current Issue :: Archive :: Search :: Submit :: Contact ::
:: Volume 4, Issue 2 (11-2014) ::
JGST 2014, 4(2): 167-177 Back to browse issues page
Estimation of Chlorophyll in Pistachio Trees Using Hyperspectral Data
D. Panahi *, A. Esmaili, R. Darvishzadeh, F. Naseri
Abstract:   (8589 Views)
Accurate quantitative estimation of vegetation biochemical and biophysical characteristics is necessary for a large variety of agricultural, ecological and meteorological applications. Among agricultural products in Iran, strategic and economical importance of Pistachio highlights the essential planning for improvement and increase of its production. The aim of this study is to compare the utility of statistical multivariate calibration techniques, including Stepwise Multiple Linear Regression (SMLR) and Partial Least Squares Regression (PLSR) with univariate techniques such as narrow band vegetation indices using hyperspectral data for estimating chlorophyll content of Pistachio trees. Pistachio leaves were collected in different growth stage. Spectral and chemical measurements were obtained from the collected samples at the laboratory, using ASD Field Spectrometer III, SPAD measurements and wet chemical analysis. Narrow band indices derived from all possible two-band combinations of reflectance and first derivative data were assessed and the best band combinations with the highest R^2 values were selected and used in linear regressions to predict the studied parameters. Among studied indices, the narrow band RVI index with wavelengths 670 nm and 734 nm using first derivative were recognized as the best index for predicting chlorophyll (R2cv = 0.72، RRMSEcv = 0.25). The results of multivariate analysis showed that PLSR and SMLR techniques using first derivative data are better than narrow band indices in chlorophyll prediction, respectively (R2cv = 0.79 and RRMSEcv = 0.21). In a nutshell this study showed that multivariate calibration techniques increase the accuracy of predicting chlorophyll content in Pistachio leaves comparing to univariate techniques. Also first derivative transformation would increase the accuracy of predicted parameters compared to reflectance values. The results highlight the benefits of using hyperspectral measurements in assessing the biochemical parameters of Pistachios trees and therefore are recommended for analysis of health and growth status of agricultural products.
Keywords: Hyperspectral, Pistachio leaves, Chlorophyll, Partial Least Squares Regression, Stepwise Multiple Linear Regression, Narrow band vegetation index
Full-Text [PDF 283 kb]   (2843 Downloads)    
Type of Study: Research | Subject: Photo&RS
Send email to the article author

Add your comments about this article
Your username or Email:


XML   Persian Abstract   Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

D. Panahi, A. Esmaili, R. Darvishzadeh, F. Naseri. Estimation of Chlorophyll in Pistachio Trees Using Hyperspectral Data. JGST 2014; 4 (2) :167-177
URL: http://jgst.issge.ir/article-1-252-en.html

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 4, Issue 2 (11-2014) Back to browse issues page
نشریه علمی علوم و فنون نقشه برداری Journal of Geomatics Science and Technology