29 December 2008 Application of decision tree on land suitability analysis
Author Affiliations +
Proceedings Volume 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA); 72854I (2008) https://doi.org/10.1117/12.814848
Event: International Conference on Earth Observation Data Processing and Analysis, 2008, Wuhan, China
Abstract
With increasing volume of data in modern science, there has been a rapid expansion of interests and researches on data mining, which is an increasingly popular tool in data analysis to obtain implicit knowledge. Decision Tree (DT), as one of widespread used classification approaches in data mining, is used successfully in many diverse areas. This paper attempts to show how to apply Decision Tree on land suitability analysis and make some conclusions for its application. Firstly, the approach of application of DT on Land Suitability and the popular learning algorithm is discussed. Then 3 towns' land units in Hainan province are selected as study case to demonstrate our approach by C4.5 implemented using C++ language, and the obtained results are compared to the results in the literature and are checked by random sample investigation. The major conclusion is that DT is suitable for land suitability analysis, by which a high veracity result can be obtained, and the obtained classifying knowledge is readable and can be interpreted well. In some sense, it can adjust knowledge by updated training dataset naturally and avoid the highly dependence with experience.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yajuan Hou, Yajuan Hou, Yaolin Liu, Yaolin Liu, Zhouqiao Ren, Zhouqiao Ren, } "Application of decision tree on land suitability analysis", Proc. SPIE 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA), 72854I (29 December 2008); doi: 10.1117/12.814848; https://doi.org/10.1117/12.814848
PROCEEDINGS
6 PAGES


SHARE
Back to Top