Mapping Rubber Tree Stand Age Using Pléiades Satellite Imagery: A Case Study in Talang District, Phuket, Thailand
Keywords:rubber tree, Hevea brasiliensis, remote sensing, age classification, feature selection
The rubber stand age information is an important variable for determining the distribution of carbon pools and fluxes in rubber plantation ecosystems as well as for production management. This study demonstrates the capability of high spatial resolution satellite imagery with the help of feature selection (i.e., Sequential Forward Floating Selection) to improve the accuracy of rubber stand age mapping. It was found that the Pléiades imagery with the help of Sequential Forward Floating Selection can successfully classify rubber stands age. The total testing accuracy was improved from 94.07% to 94.92% and 96.61% after applying the Principal Component and the Sequential Forward Floating Selection algorithms, respectively. Since the methodology proposed in this study can accurately classify 3 classes of rubber stand age, it is anticipated that this methodology can be used as a guideline for rubber tree stand age mapping in other study areas.
Authors who publish with Engineering Journal agree to transfer all copyright rights in and to the above work to the Engineering Journal (EJ)'s Editorial Board so that EJ's Editorial Board shall have the right to publish the work for nonprofit use in any media or form. In return, authors retain: (1) all proprietary rights other than copyright; (2) re-use of all or part of the above paper in their other work; (3) right to reproduce or authorize others to reproduce the above paper for authors' personal use or for company use if the source and EJ's copyright notice is indicated, and if the reproduction is not made for the purpose of sale.