Abstract: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.
<p>El análisis jerárquico de intensidad de cambio de cobertura/uso de suelo es un marco cuantitativo de análisis espacial anidado que permite estimar los cambios en tres niveles de orden, intervalo de tiempo, categoría y transición, a partir de una matriz de cambio. Presentamos su aplicación para dos periodos de tiempo 2000-2004 y 2004-2008 en la Reserva de la Biosfera Sierra de Manantlán, área de estudio altamente heterogénea en términos de los tipos de vegetación y usos del suelo. Se usó cartografía del INEGI a escala 1:50 000 actualizada mediante una imagen Landsat ETM+ del 2000 e imágenes SPOT para 2004 y 2008. El análisis permitió conocer en qué intervalo de tiempo la tasa anual general de cambio es más rápida, cuáles son las categorías más activas y cuáles son latentes; cuáles son las categorías objetivo para las transiciones activas, y si el patrón de cambio es estable en el tiempo. Se observó una mayor tasa anual de cambio entre 2000 y 2004 en comparación con el periodo 2004-2008. A nivel de categorías, se encontraron altas tasas de deforestación de las selvas tropicales hacia usos agropecuarios, y latencia en bosques templados con baja intensidad de transición hacia usos agropecuarios. En particular la actividad ganadera arraigada en la región aparece como factor promotor del proceso de deforestación, que en la praxis sobre el terreno se expresa diferencialmente en selvas y bosques.</p>
The increase and preservation of the socio-environmental functions of urban green spaces (UGS) through suitable management is part of the actions of the United Nations' Sustainable Development Goals. UGS offer benefits to the population in function of their quantity, availability and accessibility. Therefore, we developed a methodology to measure and classify UGS within the urban center of the Queretaro Metropolitan Area in central Mexico. We established one UGS category: public green space and polygon digitization was conducted at 1:1000 scale through on-screen digitization using visual image interpretation. Spatial analysis was carried out in terms of ( 1) extent (urban green space area); (2) density of UGS (m2 of green area/city block; and (3) accessibility to UGS (access for the population at block level as a unit of analysis). Furthermore, cartographic accuracy assessment was conducted in order to validate the generated data. The results show not only the spatial distribution of UGS in the study area but also their spatial relations with the population, in terms of accessibility and density measured against conventional standards. These results may contribute to urban planning regarding UGS, for the improvement of their functions and contributions to the cities' populations.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.