Land cover and land use mapping of the iSimangaliso Wetland Park, South Africa: comparison of oblique and orthogonal random forest algorithms
作者： Zaakirah Bassa , Urmilla Bob , Zoltan Szantoi , Riyad Ismail
关键词:
摘要: In recent years, the popularity of tree-based ensemble methods for land cover classification has increased significantly. Using WorldView-2 image data, we evaluate potential oblique random forest algorithm (oRF) to classify a highly heterogeneous protected area. contrast (RF) algorithm, oRF builds multivariate trees by learning optimal split using supervised model. The binary is adapted multiclass and use application both “one-against-one” “one-against-all” combination approaches. Results show that algorithms are capable achieving high accuracies ( 80% ). However, there was no statistical difference in obtained more popular RF algorithm. For all algorithms, user (UAs) producer (PAs) were recorded most classes. Both poorly classified indigenous class as indicated low UAs PAs. Finally, results from this study advocate support utility mapping areas data.
harvard.edu
cabdirect.org
sci-hub.se 参考文章(68)
Bjoern H. Menze, B. Michael Kelm, Daniel N. Splitthoff, Ullrich Koethe, Fred A. Hamprecht, On oblique random forests european conference on machine learning. pp. 453- 469 ,(2011) , 10.1007/978-3-642-23783-6_29
Thanh-Nghi Do, Philippe Lenca, Stéphane Lallich, Nguyen-Khang Pham, Classifying Very-High-Dimensional Data with Random Forests of Oblique Decision Trees EGC (best of volume). pp. 39- 55 ,(2010) , 10.1007/978-3-642-00580-0_3
Jean Gaudart, Belco Poudiougou, Stéphane Ranque, Ogobara Doumbo, Oblique decision trees for spatial pattern detection: optimal algorithm and application to malaria risk. BMC Medical Research Methodology. ,vol. 5, pp. 22- 22 ,(2005) , 10.1186/1471-2288-5-22
D. Gross, G. Dubois, J-F. Pekel, P. Mayaux, M. Holmgren, H.H.T. Prins, C. Rondinini, L. Boitani, Monitoring land cover changes in African protected areas in the 21st century Ecological Informatics. ,vol. 14, pp. 31- 37 ,(2013) , 10.1016/J.ECOINF.2012.12.002
C. Giri, B. Pengra, J. Long, T.R. Loveland, Next generation of global land cover characterization, mapping, and monitoring International Journal of Applied Earth Observation and Geoinformation. ,vol. 25, pp. 30- 37 ,(2013) , 10.1016/J.JAG.2013.03.005
Robert I. Mcdonald, Peter Kareiva, Richard T.T. Forman, The implications of current and future urbanization for global protected areas and biodiversity conservation Biological Conservation. ,vol. 141, pp. 1695- 1703 ,(2008) , 10.1016/J.BIOCON.2008.04.025
Shawn J. Leroux, Meg A. Krawchuk, Fiona Schmiegelow, Steven G. Cumming, Kim Lisgo, Lee G. Anderson, Mirela Petkova, Global protected areas and IUCN designations: Do the categories match the conditions? Biological Conservation. ,vol. 143, pp. 609- 616 ,(2010) , 10.1016/J.BIOCON.2009.11.018
Pall Oskar Gislason, Jon Atli Benediktsson, Johannes R. Sveinsson, Random Forests for land cover classification Pattern Recognition Letters. ,vol. 27, pp. 294- 300 ,(2006) , 10.1016/J.PATREC.2005.08.011
Moses Azong Cho, Pravesh Debba, Onisimo Mutanga, Nontembeko Dudeni-Tlhone, Thandulwazi Magadla, Sibusisiwe A. Khuluse, Potential utility of the spectral red-edge region of SumbandilaSat imagery for assessing indigenous forest structure and health International Journal of Applied Earth Observation and Geoinformation. ,vol. 16, pp. 85- 93 ,(2012) , 10.1016/J.JAG.2011.12.005
Néstor Fernández, José M. Paruelo, Miguel Delibes, Ecosystem functioning of protected and altered Mediterranean environments: A remote sensing classification in Doñana, Spain Remote Sensing of Environment. ,vol. 114, pp. 211- 220 ,(2010) , 10.1016/J.RSE.2009.09.001