The Receiver Operating Characteristic (ROC) is widely used for assessing the performance of classification algorithms. In GIScience, ROC has been applied to assess models aimed at predicting events, such as land use/cover change (LUCC), species distribution and disease risk. However, GIS software packages offer few statistical tests and guidance tools for ROC analysis and interpretation. This paper presents a suite of GIS tools designed to facilitate ROC curve analysis for GIS users by applying proper statistical tests and analysis procedures. The tools are freely available as models and submodels of Dinamica EGO freeware. The tools give the ROC curve, the area under the curve (AUC), partial AUC, lower and upper AUCs, the confidence interval of AUC, the density of event in probability bins and tests to evaluate the difference between the AUCs of two models. We present first the procedures and statistical tests implemented in Dinamica EGO, then the application of the tools to assess LUCC and species distribution models. Finally, we interpret and discuss the ROC-related statistics resulting from various case studies.

Balvanera, P., T. M. Daw, T. Gardner, B. Martín-López, A. Norström, C. Ifejika Speranza, M. Spierenburg, E. M. Bennett, M. Farfan, M. Hamann, J. N. Kittinger, T. Luthe, M. Maass, G. D. Peterson, and G. Pérez-Verdin. 2017. Key features for more successful place-based sustainability research on social-ecological systems: a Programme on Ecosystem Change and Society (PECS) perspective. Ecology and Society 22(1):14. https://doi.org/10.5751/ES-08826-220114

Abandonment of agricultural lands promotes the global expansion of secondary forests, which are critical for preserving biodiversity and ecosystem functions and services. Such roles largely depend, however, on two essential successional attributes, trajectory and recovery rate, which are expected to depend on landscape-scale forest cover in nonlinear ways. Using a multi-scale approach and a large vegetation dataset (843 plots, 3511 tree species) from 22 secondary forest chronosequences distributed across the Neotropics, we show that successional trajectories of woody plant species richness, stem density and basal area are less predictable in landscapes (4 km radius) with intermediate (40–60%) forest cover than in landscapes with high (greater than 60%) forest cover. This supports theory suggesting that high spatial and environmental heterogeneity in intermediately deforested landscapes can increase the variation of key ecological factors for forest recovery (e.g. seed dispersal and seedling recruitment), increasing the uncertainty of successional trajectories. Regarding the recovery rate, only species richness is positively related to forest cover in relatively small (1 km radius) landscapes. These findings highlight the importance of using a spatially explicit landscape approach in restoration initiatives and suggest that these initiatives can be more effective in more forested landscapes, especially if implemented across spatial extents of 1–4 km radius.

Fire regimes in coniferous forests in Central Mexico have been severely disturbed by land use change and fire management activities. Hence, it is critical to assess the contribution of anthropic and environmental factors that drive the occurrence of fires in these forests. This information is essential for the effective planning of fire management and wildfire prevention policies. In this study, we identified the potential drivers of fire occurrence within the Monarch Butterfly Biosphere Reserve (MBBR) and modeled their spatial pattern through generalized linear mixed models. We employed fire event data for five years (2009-2013) and the spatial distribution of anthropic infrastructure and biophysical variables such as forest biomass and slope. We found fire occurrence increased with total population and forest edge density. The derived spatial model showed an acceptable accuracy (AUC = 0.71) for fire occurrence based on 2014 and 2015 fire events used to evaluate the model. To improve the model, we suggest the incorporation of direct fuel measurements. From our analyses, we suggest to develop fire management guidelines particularly in sites with high population density and close to forest fragments within the MBBR.