Abstract
Chlorophyll content is one of the essential parameters to assess the growth process of the fruit trees. This present study developed a model for estimation of canopy averaged chlorophyll content (CACC) of pear trees using the convolutional autoencoder (CAE) features of hyperspectral (HS) data. This study also demonstrated the inspection of anomaly among the trees by employing multidimensional scaling on the CAE features and detected outlier trees prior to fit nonlinear regression models. These outlier trees were excluded from the further experiments that helped in improving the prediction performance of CACC. Gaussian process regression (GPR) and support vector regression (SVR) techniques were investigated as nonlinear regression models and used for prediction of CACC. The CAE features were proven to be providing better prediction of CACC when compared with the direct use of HS bands or vegetation indices as predictors. The CACC prediction performance was improved with the exclusion of the outlier trees during training of the regression models. It was evident from the experiments that GPR could predict the CACC with better accuracy compared to SVR. In addition, the reliability of the tree canopy masks, which were utilized for averaging the features' values for a particular tree, was also evaluated.
Highlights
G LOBAL food demand is rising rapidly with an increase in population
We have proposed the use of convolutional autoencoder (CAE) features, derived from HS data, for canopy averaged chlorophyll content (CACC) modeling of pear trees
The CAE features were proven to be more effective in CACC modeling compared to the HS bands
Summary
G LOBAL food demand is rising rapidly with an increase in population. In order to meet the increasing demand, foodManuscript received December 6, 2019; revised February 1, 2020, February 28, 2020, and March 9, 2020; accepted March 17, 2020. Continuous health monitoring of plants or crops during their growing period can help in maximizing food production or yield by identifying diseases, stress conditions or any other issues and taking necessary steps to resolve those issues [1]–[3]. Maturity of crops or vegetation and prediction of primary production or yield can be assessed with the estimation of chlorophyll content [8], [9]. Chlorophyll content can be estimated using chlorophyll content meter, optical contact sensor such as soil plant analysis development (SPAD) 502 of Minolta, images of airborne cameras, and multispectral and hyperspectral (HS) images [1]. In-field chlorophyll content estimation techniques are labor intensive, time consuming, expensive and do not provide real-time monitoring. Remote sensing data can be considered as a reliable solution for continuous spatial and temporal monitoring of chlorophyll content
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.