No abstract

No abstract

This paper presents an evaluation on strategies for rubber plantation mapping employing SAR data coupled with Random Forest (RF) and Support Vector Machine (SVM). Linear backscatter coefficients achieved saturation point at about 10 years, making this form of polarimetric data being robust only for young to mature stands. This research found that the performance of both algorithms was comparable. The addition of texture features gave substantial impact to the overall accuracy. As indicated by the analysis of variable importance, only some texture features have contributed to higher overall accuracy. Classification using a subset of texture features pointed out that accuracy could be improved using dual polarimetric data, while trivial enhancement was seen in combined HH, HV and VV backscatter intensities. The research showed that classification accuracy could be further augmented by setting proper classification parameters. Nonetheless, it is argued that the level of improvement would greatly depend on selecting a proper dataset fed into classifier, rather than tuning classifier parameters. ARTICLE HISTORY

This research aims to detect subtle changes by combining binary change analysis, the Iteratively Reweighted Multivariate Alteration Detection (IRMAD), over dual polarimetric Advanced Land Observing Satellite (ALOS) backscatter with augmented data for post-classification change analysis. The accuracy of change detection was iteratively evaluated based on thresholds composed of mean and a range constant of standard deviation. Four datasets were examined for post-classification change analysis including the dual polarimetric backscatter as the benchmark and its augmented data with indices, entropy alpha decomposition and selected texture features. Variable importance was then evaluated to build a best subset model employing seven classifiers, including Bagged Classification and Regression Tree (CAB), Extreme Learning Machine Neural Network (ENN), Bagged Multivariate Adaptive Regression Spline (MAB), Regularised Random Forest (RFG), Original Random Forest (RFO), Support Vector Machine (SVM), and Extreme Gradient Boosting Tree (XGB). The best accuracy was 98.8%, which resulted from thresholding MAD variate-2 with constants at 1.7. The highest improvement of classification accuracy was obtained by amending the grey level co-occurrence matrix (GLCM) texture. The identification of variable importance (VI) confirmed that selected GLCM textures (mean and variance of HH or HV) were equally superior, while the contribution of index and decomposition were negligible. The best model produced similar classification accuracy at about 90% for both years 2007 and 2010. Tree-based algorithms including RFO, RFG and XGB were more robust than SVM and ENN. Subtle changes indicated by binary change analysis were somewhat hidden in post-classification analysis. Reclassification by combining all important variables and adding five classes to include subtle changes assisted by Google Earth yielded an accuracy of 82%.