REMOTE SENSING TECHNIQUES FOR OIL PALM AGE CLASSIFICATION USING LANDSAT-5 TM SATELLITE

This paper demonstrates the procedure to classify the age of oil palm trees using Landsat-5 TM (thematic mapper) remote sensing data. The study was conducted in two phases: phase I focuses on the the land cover classification, and phase II involves the oil palm age classification. Firstly,the region of interest (ROI) was identified and drawn in order to supply the training and testing pixels for the supervised classification. Maximum likelihood (ML) classifier was used for land cover classification. The land cover classification using the ML produces a good result with an overall accuracy of 85.51% and kappa coefficient of 0.8208. Meanwhile, three classifiers were used to investigate the age of oil palm classification, which are the 1) Maximum likelihood (ML), 2) Neural Network (NN) and, 3) Support Vector Machine (SVM). The accuracy of the classifications was then assessed by comparing the classifications with a reference set using a confusion matrix technique. Among the three classifiers, SVM performs the best with the highest overall accuracy of 54.18% and kappa coefficient of 0.39.

[1]  Lian Pin Koh,et al.  Cashing in palm oil for conservation , 2007, Nature.

[2]  M. Schlerf,et al.  Classification of coniferous tree species and age classes using hyperspectral data and geostatistical methods , 2005 .

[3]  Julia Mcmorrow,et al.  Linear regression modelling for the estimation of oil palm age from Landsat TM , 2001 .

[4]  Asmala Ahmad,et al.  Application of support vector machine for classification of multispectral data , 2014 .

[5]  Abdul Rashid Mohamed Shariff.  7th IGRSM International Remote Sensing & GIS Conference and Exhibition , 2014 .

[6]  Asmala Ahmad,et al.  Analysis of Maximum Likelihood Classificationon Multispectral Data , 2012 .

[7]  S. Quegan,et al.  Analysis of Maximum Likelihood classification technique on Landsat 5 TM satellite data of tropical land covers , 2012, 2012 IEEE International Conference on Control System, Computing and Engineering.

[8]  A. Cracknell,et al.  Use of UK-DMC 2 and ALOS PALSAR for studying the age of oil palm trees in southern peninsular Malaysia , 2013 .

[9]  W. Cohen,et al.  Estimating the age and structure of forests in a multi-ownership landscape of western Oregon, U.S.A. , 1995 .

[10]  W. Salas,et al.  Mapping secondary tropical forest and forest age from SPOT HRV data , 1999 .

[11]  Bernard A. Engel,et al.  Optimization of training data required for neuro-classification , 1994 .

[12]  Shaun Quegan,et al.  Comparative analysis of supervised and unsupervised classification on multispectral data , 2013 .

[13]  J. Anderson,et al.  Quantification of oil palm biomass and nutrient value in a mature plantation. I. Above-ground biomass. , 1999 .

[14]  Eduardo S. Brondizio,et al.  Detecting subtle land use change in tropical forests , 2009 .

[15]  J. V. Gelder,et al.  Greasy palms: European buyers of Indonesian palm oil. , 2004 .

[16]  R. Hall,et al.  Discrimination of conifer height, age and crown closure classes using Landsat-5 TM imagery in the Canadian Northwest Territories , 2003 .

[17]  J. V. van Aardt,et al.  Spectral–age interactions in managed, even‐aged Eucalyptus plantations: application of discriminant analysis and classification and regression trees approaches to hyperspectral data , 2008 .

[18]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[19]  Alexandra C Morel,et al.  How will oil palm expansion affect biodiversity? , 2008, Trends in ecology & evolution.

[20]  George F. Hepner,et al.  Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification , 1990 .

[21]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[22]  J. Craggs.  Applied Mathematical Sciences , 1973 .