Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments Export

@article{citeulike:2506984, abstract = {Remotely sensed images and processing techniques are a primary tool for mapping changes in tropical forest types important to biodiversity and environmental assessment. Detailed land cover data are lacking for most wet tropical areas that present special challenges for data collection. For this study, we utilize decision tree (DT) classifiers to map 32 land cover types of varying ecological and economic importance over an 8000 km2 study area and biological corridor in Costa Rica. We assess multivariate QUEST DTs with unbiased classification rules and linear discriminant node models for integrated vegetation mapping and change detection. Predictor variables essential to accurate land cover classification were selected using importance indices statistically derived with classification trees. A set of 35 variables from SRTM-DEM terrain variables, WorldClim grids, and Landsat TM bands were assessed. Of the techniques examined, QUEST trees were most accurate by integrating a set of 12 spectral and geospatial predictor variables for image subsets with an overall cross-validation accuracy of 93\% +/- 3.3\%. Accuracy with spectral variables alone was low (69\% +/- 3.3\%). A random selection of training and test set pixels for the entire landscape yielded lower classification accuracy (81\%) demonstrating a positive effect of image subsets on accuracy. A post-classification change comparison between 1986 and 2001 reveals that two lowland forest types of differing tree species composition are vulnerable to agricultural conversion. Tree plantations and successional vegetation added forest cover over the 15-year time period, but sometimes replaced native forest types, reducing floristic diversity. Decision tree classifiers, capable of combining data from multiple sources, are highly adaptable for mapping and monitoring land cover changes important to biodiversity and other ecosystem services in complex wet tropical environments.}, author = {Sesnie, Steven E. and Gessler, Paul E. and Finegan, Bryan and Thessler, Sirpa}, citeulike-article-id = {2506984}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.rse.2007.08.025}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0034425708000345}, citeulike-linkout-2 = {http://www.sciencedirect.com/science/article/B6V6V-4S02DB8-3/2/83a7b538caa6265f29b3f00cf17c5f2d}, doi = {10.1016/j.rse.2007.08.025}, journal = {Remote Sensing of Environment}, keywords = {change, habitat, landsat, machine-learning, srtm}, posted-at = {2008-12-01 18:12:24}, priority = {2}, title = {Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments}, url = {http://dx.doi.org/10.1016/j.rse.2007.08.025}, volume = {In Press, Corrected Proof} }

TY - JOUR ID - citeulike:2506984 L3 - citeulike-article-id:2506984 N2 - Remotely sensed images and processing techniques are a primary tool for mapping changes in tropical forest types important to biodiversity and environmental assessment. Detailed land cover data are lacking for most wet tropical areas that present special challenges for data collection. For this study, we utilize decision tree (DT) classifiers to map 32 land cover types of varying ecological and economic importance over an 8000 km2 study area and biological corridor in Costa Rica. We assess multivariate QUEST DTs with unbiased classification rules and linear discriminant node models for integrated vegetation mapping and change detection. Predictor variables essential to accurate land cover classification were selected using importance indices statistically derived with classification trees. A set of 35 variables from SRTM-DEM terrain variables, WorldClim grids, and Landsat TM bands were assessed. Of the techniques examined, QUEST trees were most accurate by integrating a set of 12 spectral and geospatial predictor variables for image subsets with an overall cross-validation accuracy of 93% +/- 3.3%. Accuracy with spectral variables alone was low (69% +/- 3.3%). A random selection of training and test set pixels for the entire landscape yielded lower classification accuracy (81%) demonstrating a positive effect of image subsets on accuracy. A post-classification change comparison between 1986 and 2001 reveals that two lowland forest types of differing tree species composition are vulnerable to agricultural conversion. Tree plantations and successional vegetation added forest cover over the 15-year time period, but sometimes replaced native forest types, reducing floristic diversity. Decision tree classifiers, capable of combining data from multiple sources, are highly adaptable for mapping and monitoring land cover changes important to biodiversity and other ecosystem services in complex wet tropical environments. JF - Remote Sensing of Environment TI - Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments VL - In Press, Corrected Proof KW - change KW - habitat KW - landsat KW - machine-learning KW - srtm AU - Sesnie, Steven AU - Gessler, Paul AU - Finegan, Bryan AU - Thessler, Sirpa UR - http://dx.doi.org/10.1016/j.rse.2007.08.025 ER -