Publication: Expert classification for age class identification of oil palm plantation in Krabi Province, Thailand
Issued Date
2005-12-01
Resource Type
Other identifier(s)
2-s2.0-84866089253
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005. Vol.3, (2005), 1681-1691
Suggested Citation
Jarunya Kitiphaisannon, Sura Pattanakiat, Charlie Navanugraha, Prasong Sanguantham Expert classification for age class identification of oil palm plantation in Krabi Province, Thailand. Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005. Vol.3, (2005), 1681-1691. Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/16498
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Expert classification for age class identification of oil palm plantation in Krabi Province, Thailand
Other Contributor(s)
Abstract
The objective of this study is to apply the Geo-Information Technology including Remote Sensing, Global Positioning System, and Geographic Information System integrated with Expert System in order to generate a knowledge base system for age class identification of oil palm plantation. Rule base under the knowledge base for oil palm classification is generated from the relationship of multiple regressions related with Water Index (WI), Bare Soil Index (BI), Normalized Differential Vegetation Index (NDVI), and Advance Vegetation Index (AVI). These equations are used to define age class stage of oil palm plantation which can be divided into 4 classes: Young stage (1-3 years old), Intermediate stage (4-10 years old), Productive stage (11-20 years old), and Mature stage (more than 20 years old). The percentages of accuracy for each class using expert classification are 92.19, 50.88, 80.00, and 12.50 respectively. Meanwhile, the percentages of accuracy for maximum likelihood classification are 90.63, 42.11, 40.54, and 72.34 respectively. Therefore, the accuracy for each age class stage from the expert classification is higher than the maximum likelihood classification. Furthermore, the overall accuracy of the expert classification is about 63.11%, and the maximum likelihood classification is only about 60.33%. Thus the accuracy of the expert classification is about 2.78% higher than the maximum likelihood classification. In conclusion, application of the Geo-Information Technology and Expert System provides useful information about classification on age class of oil palm plantation.