Mapping land-cover modifications over large areas: A comparison of machine learning algorithms Export

@article{Rogan2008_mach_learn, abstract = {Large area land-cover monitoring scenarios, involving large volumes of data, are becoming more prevalent in remote sensing applications. Thus, there is a pressing need for increased automation in the change mapping process. The objective of this research is to compare the performance of three machine learning algorithms (MLAs); two classification tree software routines (S-plus and C4.5) and an artificial neural network (ARTMAP), in the context of mapping land-cover modifications in northern and southern California study sites between 1990/91 and 1996. Comparisons were based on several criteria: overall accuracy, sensitivity to data set size and variation, and noise. ARTMAP produced the most accurate maps overall (\~{} 84\%), for two study areas -- in southern and northern California, and was most resistant to training data deficiencies. The change map generated using ARTMAP has similar accuracies to a human-interpreted map produced by the U.S. Forest Service in the southern study area. ARTMAP appears to be robust and accurate for automated, large area change monitoring as it performed equally well across the diverse study areas with minimal human intervention in the classification process.}, author = {Rogan, John and Franklin, Janet and Stow, Doug and Miller, Jennifer and Woodcock, Curtis and Roberts, Dar}, booktitle = {Earth Observations for Terrestrial Biodiversity and Ecosystems Special Issue}, citeulike-article-id = {3206236}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.rse.2007.10.004}, citeulike-linkout-1 = {http://www.sciencedirect.com/science/article/B6V6V-4S26RV5-1/2/41e6a6cdd9c132974a51515540c4e73b}, day = {15}, doi = {10.1016/j.rse.2007.10.004}, journal = {Remote Sensing of Environment}, keywords = {classification, landcover, machine-learning}, month = {May}, number = {5}, pages = {2272--2283}, posted-at = {2008-09-08 15:12:15}, priority = {2}, title = {Mapping land-cover modifications over large areas: A comparison of machine learning algorithms}, url = {http://dx.doi.org/10.1016/j.rse.2007.10.004}, volume = {112}, year = {2008} }

TY - JOUR ID - Rogan2008_mach_learn L3 - citeulike-article-id:3206236 N2 - Large area land-cover monitoring scenarios, involving large volumes of data, are becoming more prevalent in remote sensing applications. Thus, there is a pressing need for increased automation in the change mapping process. The objective of this research is to compare the performance of three machine learning algorithms (MLAs); two classification tree software routines (S-plus and C4.5) and an artificial neural network (ARTMAP), in the context of mapping land-cover modifications in northern and southern California study sites between 1990/91 and 1996. Comparisons were based on several criteria: overall accuracy, sensitivity to data set size and variation, and noise. ARTMAP produced the most accurate maps overall (~ 84%), for two study areas -- in southern and northern California, and was most resistant to training data deficiencies. The change map generated using ARTMAP has similar accuracies to a human-interpreted map produced by the U.S. Forest Service in the southern study area. ARTMAP appears to be robust and accurate for automated, large area change monitoring as it performed equally well across the diverse study areas with minimal human intervention in the classification process. IS - 5 JF - Remote Sensing of Environment EP - 2283 TI - Mapping land-cover modifications over large areas: A comparison of machine learning algorithms VL - 112 T2 - Earth Observations for Terrestrial Biodiversity and Ecosystems Special Issue SP - 2272 KW - classification KW - landcover KW - machine-learning AU - Rogan, John AU - Franklin, Janet AU - Stow, Doug AU - Miller, Jennifer AU - Woodcock, Curtis AU - Roberts, Dar PY - 2008/05/15/ UR - http://dx.doi.org/10.1016/j.rse.2007.10.004 ER -