Determinate ASTER Satellite Data Capability and Classification and Regression Tree and Random Forest Algorithm for Forest Type Mapping

Document Type : Research Paper

Authors

1 Associate Professor of Forest Sciences Department, Natural Resources Faculty, Sari Agriculture and Natural Resource University, Sari, I.R. Iran

2 Ph.D. candidate of Forest Sciences Department, Natural Resources Faculty, Sari Agriculture and Natural Resource University, Sari, I.R. Iran

3 Associate Professor of Forestry Department, Natural Resources Faculty, Gorgan Agriculture and Natural Resource University, Gorgan, I.R. Iran

Abstract

Recognition equal units and segregation them and upshot planning per units most basic method for management forest units. Aim this study presentation and comparison classification and regression tree (CART) and random forest (RF) algorithm for forest type mapping using ASTER satellite data in district one didactic and research forest's darabkola. In start using inventory network 500* 350 m, take number 150 sample plat in over district. After accomplish Geometric correction and reduce atmospheric effect on image processing bands rationing, create general vegetation indices, principal component analysis and tesslatcap index. After extraction spectrum values relevant by sample plats fabric and processing bands, classification values other pixel accomplish using investigating algorithms. Evaluation accuracy results classification accomplish by some sample plat that not participate in process classification. The result showed preparation map using RF with overall accuracy 66% and kappa coefficient 0.57 than classification and regression tree with overall accuracy 58% and kappa coefficient 0.49 has superior accuracy. Totality result showed using above algorithm may increased accuracy forest type map.

Keywords

References

[1]. Shataee, Sh. (2003). Investigation on the possibility of beech forest type mapping using satellite data (Case study: Khyrood forest). Phd Thesis Tehran University, 155 pp.
[2]. Baatuuwie, N.B., and Leeuwen I.L.V. (2011). Evaluation of three classifiers in mapping forest stand types using medium resolution imagery: a case study in the Offinso Forest District, Ghana. African Journal of Environmental Science and Technology, 5(1): 25-36.
[3]. Quirós, E., Felicísimo Á.M., and Cuartero, A. (2009). Testing multivariate adaptive regression splines (MARS) as a method of land cover classification of TERRA-ASTER satellite images. Sensors, 9: 9011-9028.
[4]. Rashidi, F., Babaie Kafaki, S., and Oladi, DJ. (2009). Investigation on the capability of digital data of ETM+ sensor in seperating of forest types (Case study: Lafoor area of Savadkooh), Iranian Journal of Forest and Poplar Research, 17(13): 51-63.
[5]. Darvishsefat, A.A., Abbasi, M., and Marvi Mohadjer, M.R. (2009). Investigation on the possibility of beech forest type mapping using Landsat ETM+ data (Case study: Khyroud forest), Iranian Journal of Forest, 2(9): 105-113.
[6]. Kurt, I., Ture, M., and Kurum, A.T. (2008). Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease. Expert System Applied, 34(1): 366–374.
[7]. Sarunas, R. (1997). On dimensionality, sample size, and classification error of nonparametric linear classification algorithms IEEE Transactions on Pattern Analysis and Machine Intelligence, 19: 667–671.
[8]. Cortijo, F.J., and de la Blanca, N.P. (1999). The performance of regularized discriminant analysis versus non-parametric classifiers applied to high-dimensional image classification. International Journal Remote Sensing, 20: 3345–336.
[9]. Ham, J., Chen Y., Crawford, M.M., and Ghosh, J. (2005). Investigation of the random forest framework for classification of hyperspec- tral data. IEEE Transactions on Geoscience and Remote Sensing, 43(3):492–501.
[10]. Lawrence, R., and Wright, A. (2001). Rule-based classification systems using classification and regression tree (CART) analysis. Photogrammetric and Engineering Remote Sensing, 67:1137-1142.
[11]. Chen, D., and Stow, D. (2002). The effect of training strategies on supervised classification at different spatial resolutions. Photogrammetric Engineering & Remote Sensing, 68(11): 1155-1161.
[12]. Yarbrough, L.D., Easson, G., and Kuszmaul, J.S. (2005). Using at-sensor radiance and reflectance tasseled cap transforms applied to change detection for the ASTER sensor. IEEE Third International Workshop on the Analysis of Multi-temporal Remote Sensing Images, 16–18.
[13]. Breiman, L., Friedman, J.H., Olshen, R.A., and Stone. C.J. (1984). Classification and regression trees. Wadsworth and Brooks/Cole, Monterey, California, USA.
[14]. Yoneyama, Y., Suzuki, S., Sawa, R., Yoneyama, K., Power, G.G., and Araki, T. (2002). Increased plasma adenosine concentrations and the severity of preeclampsia. Obstetrics & Gynecology. 100(6): 66-70.
[15]. Kalbi, S. (2010). Investigation estimation forest structure attributes using ASTER and SPOT-HRG satellite data (case study: Darabkola Forest). MSC Thesis Sari University. 107 pp.
[16]. Dietterich, T. (2000). An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting and randomization. Machine Learning, 40: 139 –157.
[17]. Breiman, L. (2001). Random forests. Machine Learning, 45:15–32.
[18]. Yu. X., Hyypp, J., Vastaranta. M., Holopainen, M., Viitala., R. (2011). Predicting individual tree attributes from airborne laser point clouds based on the random forests technique. ISPRS Journal of Photogrammetry and Remote Sensing, 66: 28–37.
[19]. Shataee, S., Kalbi, S., Fallah, A., Pelz, D. (2012). Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN, SVR and random forest regression algorithms. International Journal of Remote Sensing, 33(19): 6254-6280.
[20]. Foody, G.M. (2004). Thematic map comparison: evaluating the statistical significance of differences in classification accuracy. Photogrammetric Engineering and Remote Sensing, 70: 627-634.

Files

Share

How to cite

Statistics