Comparison of pixel -based and artificial neural networks classification methods for detecting forest cover changes in Malaysia

8th International Symposium of the Digital Earth

地球科学;计算机科学

Deilmai, B.R.^1 ; Kanniah, K.D.^1 ; Rasib, A.W.^1 ; Ariffin, A.^1

Department of Geoinformation, Faculty of Geoinformation and Real Estate, Universiti Teknologi Malaysia, 81310 Johor, Malaysia^1

关键词: Change detection analysis;    Classification methods;    Classification scheme;    Food and agriculture organizations;    Forest cover change;    Landsat thematic mapper images;    Maximum likelihood classifications;    Tropical environments;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/18/1/012069/pdf
DOI  :  10.1088/1755-1315/18/1/012069

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

According to the FAO (Food and Agriculture Organization), Malaysia lost 8.6% of its forest cover between 1990 and 2005. In forest cover change detection, remote sensing plays an important role. A lot of change detection methods have been developed, and most of them are semi-automated. These methods are time consuming and difficult to apply. One of the new and robust methods for change detection is artificial neural network (ANN). In this study, (ANN) classification scheme is used to detect the forest cover changes in the Johor state in Malaysia. Landsat Thematic Mapper images covering a period of 9 years (2000 and 2009) are used. Results obtained with ANN technique was compared with Maximum likelihood classification (MLC) to investigate whether ANN can perform better in the tropical environment. Overall accuracy of the ANN and MLC techniques are 75%, 68% (2000) and 80%, 75% (2009) respectively. Using the ANN method, it was found that forest area in Johor decreased as much as 1298 km2 between 2000 and 2009. The results also showed the potential and advantages of neural network in classification and change detection analysis.