Incluye bibliografíae: páginas 263-317 e índice: páginas 318-320

Preface page.. Acknowledgments.. Part I: History and ecological basis of species distribution modeling.. 1 Species distribution modeling.. 1.1 Introduction.. 1.2 What is in a name?.. 1.2.1 Niche models.. 1.2.2 Habitat suitability models.. 1.3 Heightened interest in species distribution modeling.. 1.4 What is species distribution modeling and how is this book organized?.. 1.5 Why model species distributions?.. 1.5.1 Reserve design and conservation planning.. 1.5.2 Impact assessment and resource management.. 1.5.3 Ecological restoration and ecological modeling.. 1.5.4 Risk and impacts of invasive species including pathogens.. 1.5.5 Effects of global warming on biodiversity and ecosystems.. 2 Why do we need species distribution models?.. 2.1 Introduction.. 2.2 Mapping species - atlas projects and natural history collections.. 2.2.1 Grid-based atlases of species distributions.. 2.2.2 Species locations from natural history collections.. 2.3 Direct interpolation of species data.. 2.4 Summary - what do we really want?.. 3 Ecological understanding of species distributions.. 3.1 Introduction.. 3.2 The species niche concept.. 3.2.1 The species niche in environmental and geographical space.. 3.2.2 The species niche in evolutionary time.. 3.2.3 Niche or resource selection function?.. 3.3 Factors controlling species distributions.. 3.4 Environmental gradients and species response functions.. 3.5 Conceptual models of environmental factors controlling species distributions.. 3.5.1 Heat, moisture, light, nutrients, and the distribution of plants.. 3.5.2 Hierarchical and nested scales of factors affecting species distributions.. 3.5.3 Environmental factors affecting species diversity and life form.. 3.6 Summary.. Part II: The data needed for modeling species distributions.. 4 Data for species distribution models: the biological data.. 4.1 Introduction - the species data model

4.2 Spatial prediction of species distributions: what is being predicted?.. 4.3 Scale concepts related to species data.. 4.4 Spatial sampling design issues related to species data.. 4.4.1 Probability sample designs.. 4.4.2 How many observations?.. 4.4.3 Species prevalence.. 4.4.4 Sample resolution.. 4.4.5 Study area extent and sampling environmental gradients.. 4.4.6 Using existing data for modeling.. 4.4.7 Species presence-only data.. 4.5 Temporal sampling issues and species data.. 4.5.1 Species detectability.. 4.5.2 Historical species data.. 4.6 Summary.. 5 Data for species distribution models: the environmental data.. 5.1 Introduction.. 5.2 Spatial data representing primary environmental regimes.. 5.2.1 Climate maps.. 5.2.2 Digital terrain maps.. 5.2.3 Soil factors and geology maps.. 5.3 Other environmental data for SDM.. 5.3.1 Vegetation maps.. 5.3.2 Disturbance and disturbance history.. 5.3.3 Remote sensing.. 5.3.4 Landscape pattern.. 5.3.5 The distributions of other species.. 5.4 Environmental data for aquatic and marine species.. 5.5 Summary.. Part III: An overview of the modeling methods.. 6 Statistical models - modern regression (Janet Franklin and Jennifer A. Miller.. 6.1 Introduction.. 6.2 The linear model.. 6.3 Generalized linear models.. 6.3.1 Transformations of the predictors.. 6.3.2 Model estimation.. 6.3.3 Model selection and predictor collinearity.. 6.3.4 Use of GLMs in species distribution modeling.. 6.3.5 Summary.. 6.4 Generalized additive models.. 6.4.1 Use of GAMs in species distribution modeling.. 6.4.2 Summary.. 6.5 Multivariate adaptive regression splines.. 6.5.1 Use of MARS in species distribution modeling..

6.6 Multivariate statistical approaches to SDM.. 6.7 Bayesian approaches to SDM.. 6.8 Spatial autocorrelation and statistical models of species distributions.. 6.8.1 Consequences of SAC data.. 6.8.2 Solutions to SAC data.. Autoregression.. Applications of autoregression methods in SDM.. Generalized estimating equations and generalized linear mixed models.. Geographically weighted regression.. Spatial filtering methods.. 6.8.3 Summary.. 7 Machine learning methods.. 7.1 Introduction.. 7.2 Decision tree-based methods.. 7.2.1 How decision trees work.. 7.2.2 When are decision trees useful?.. 7.2.3 A note about multivariate decision trees.. 7.2.4 Application of decision trees in species distribution modeling.. 7.3 Ensemble methods applied to decision trees - bagging, boosting, and random forests.. 7.4 Artificial neural networks.. 7.5 Genetic algorithms.. 7.6 Maximum entropy.. 7.7 Support vector machines.. 7.8 Ensemble forecasting and consensus methods.. 7.9 Summary.. 8 Classification, similarity and other methods for presence-only data.. 8.1 Introduction.. 8.2 Envelope models and similarity measures.. 8.2.1 Environmental envelope methods.. 8.2.2 Environmental distance methods.. 8.3 Species presence versus habitat availability.. 8.3.1 Resource selection functions using descriminative models.. 8.3.2 Ecological niche factor analysis.. 8.3.3 Genetic algorithms for rule production (GARP.. 8.3.4 Maximum entropy.. 8.4 Habitat suitability indices and other expert models.. 8.5 Summary.. Part IV: Model evaluation and implementation.. 9 Model evaluation.. 9.1 Introduction.. 9.2 Data for model evaluation.. 9.3 Measures of prediction errors.. 9.3.1 Threshold-dependent measures of accuracy

AUC.. Correlation.. Calibration.. 9.3.4 Evaluating presence-only models.. 9.3.5 Spatial distribution of model uncertainty and error.. 9.4 Summary.. 10 Implementation of species distribution models.. 10.1 Introduction.. 10.2 Species attributes.. 10.3 Species data.. 10.4 Environmental data and scale.. Maps of species' distributions or habitat suitability are required for many aspects of environmental research, resource management and conservation planning. These include biodiversity assessment, reserve design, habitat management and restoration, species and habitat conservation plans and predicting the effects of environmental change on species and ecosystems. The proliferation of methods and uncertainty regarding their effectiveness can be daunting to researchers, resource managers and conservation planners alike. Franklin summarises the methods used in species distribution modeling (also called niche modeling and presents a framework for spatial prediction of species distributions based on the attributes (space, time, scale of the data and questions being asked. The framework links theoretical ecological models of species distributions to spatial data on species and environment, and statistical models used for spatial prediction. Providing practical guidelines to students, researchers and practitioners in a broad range of environmental sciences including ecology, geography, conservation biology, and natural resources management.. 10.5 Modeling methods.. 10.6 Model evaluation.. 10.7 Summary - beyond species distribution modeling.. References.. Index

Maps of species' distributions or habitat suitability are required for many aspects of environmental research, resource management and conservation planning. These include biodiversity assessment, reserve design, habitat management and restoration, species and habitat conservation plans and predicting the effects of environmental change on species and ecosystems. The proliferation of methods and uncertainty regarding their effectiveness can be daunting to researchers, resource managers and conservation planners alike. Franklin summarises the methods used in species distribution modeling (also called niche modeling) and presents a framework for spatial prediction of species distributions based on the attributes (space, time, scale) of the data and questions being asked. The framework links theoretical ecological models of species distributions to spatial data on species and environment, and statistical models used for spatial prediction. Providing practical guidelines to students, researchers and practitioners in a broad range of environmental sciences including ecology, geography, conservation biology, and natural resources management Inglés