Ecological Modelling 192 (2006) 126–142 Improving image derived vegetation maps with regression based distribution modeling S.Z. Dobrowski ∗ , J.A. Greenberg, C.M. Ramirez, S.L. Ustin Center for Spatial Technologies and Remote Sensing, Department of Land Air and Water Resources, University of California, Davis, USA Received 5 January 2005; received in revised form 7 September 2005; accepted 7 September 2005 Available online 7 November 2005 Abstract Incorporating ecological information into image-based vegetation mapping remains a challenge. Much attention has been placed on the use of ancillary information layers in image classification (e.g. slope, aspect, elevation) in that they provide indirect links to information that is ecologically relevant to species distributions. The objective of this study was to assess the utility of incorporating regression-based distribution model surfaces with image classification results using a consensus theoretic approach. We used spatially explicit non-parametric regression modeling in order to incorporate ancillary information in the production of an existing vegetation map for the Lake Tahoe basin. Probability surfaces for 19 prevalent species or genera were produced using generalized additive modeling (GAM). Models were fit to plot data obtained from multiple resource agencies using land-form based explanatory variables derived from a digital elevation model. Model evaluation was assessed by examining species response curves and through cross-validation, resulting in a range of accuracies for individual species (ROC values from 0.58 to 0.85). Probability surfaces for the study area were subsequently generated within a GIS. These surfaces were spatially re-sampled and used in conjunction with IKONOS imagery for use in vegetation mapping. The GAM surfaces were combined with maximum likelihood image classification results using consensus theory and a simple iterative weighting scheme. Results from the analysis demonstrate that the inclusion of the GAM surfaces improved individual class accuracies and suggests the need for implementing standardized and objective species modeling techniques for improving vegetation maps. © 2005 Elsevier B.V. All rights reserved. Keywords: Generalized additive model (GAM); Species prediction; Distribution modeling; IKONOS; Ancillary data; Multi-source; Consensus theory; Vegetation mapping; Species mapping; Lake Tahoe 1. Introduction Mapping vegetation at high thematic resolutions remains a significant challenge for the remote sensing ∗ Corresponding author. community. Advances in the area of data-fusion have improved image classification results (Le Hegarat- Mascle et al., 2000; Solberg, 1999) and has focused on fusing image data from different sensors or different spatial scales (Pohl and Van Genderen, 1998; Prasad et al., 2001; Wald, 1999) while less attention has been 0304-3800/$ – see front matter © 2005 Elsevier B.V. All rights reserved. doi:10.1016/j.ecolmodel.2005.09.006