Package: flexsdm 1.4.2

Intro | Data | Delimit calibration area | Create pseudo-absence data | Partition data for evaluating models | Extracting environmental values | Modeling | Standard models | Ensemble of small models | Comparing our models | Conclusions | References

Introduction | Installation | Project directory setup | Data, species occurrence and background data | 1. Fit and validate models | 2. Model Ensemble | 3. Fit and validate models with Ensemble of Small Model approach

Introduction | Installation | Project directory setup | Species occurrence, presence/absense and environmental data | 1. Fit and ensemble the models above | 2. Merge model performance tables | 3. Raster interpolation between two time periods | 4. Measure model extrapolation | 5. Correction of suitability based on extrapolation | 6. Create spatial predictor variables to reduce overprediction of species distribution models | 7. Methods to correct overprediction of species distribution models based on occurrences and suitability patterns

Introduction | Installation | Project Directory Setup | Data, species occurrence and background data | Geographic region | Calibration area | 1. Buffer | 2. Minimum convex polygon | 3. Buffered minimum convex polygon | 4. Mask | Reducing collinearity among the predictors | Environmental predictors | 1. Pearson correlation | 1. Stephenson, N. 1998. Actual evapotranspiration and deficit: biologically meaningful correlates of vegetation distribution across spatial scales. Journal of biogeography 25:855–870. | 2. Woodward, F. I., M. R. Lomas, and C. K. Kelly. 2004. Global climate and the distribution of plant biomes. Philosophical transactions of the Royal Society of London. Series B, Biological sciences 359:1465–1476. | 2. Variance inflation factor | 3. Principal component analysis | 4. Factorial analysis | 5. Comments | Data filtering | Environmental filtering | Geographical filtering | Data partitioning | 1. Conventional data partitioning methods (part_random) | 2. Spatial band cross-validation (part_sband) | 3. Spatial block cross-validation (part_sblock) | 4. Environmental and spatial cross-validation (part_senv) | Background and pseudo-absence sampling | 1. Sample background | 2. Sample pseudo-absences | Extracting environmental values

title: 'flexsdm: Red Fir example'output: rmarkdown::html_vignettevignette: >%\VignetteIndexEntry | Example of full modeling process | Study species & overview of methods | Delimit of a calibration area | Occurrence filtering | Block partition with 4 folds | Pseudo-absence/background points (using partition previously created as a mask) | Fit models with tune_max, fit_gau, and fit_glm | Fit an ensemble model | Project the ensemble model | Constrain the model with msdm_posterior

Introduction | Data | Delimit calibration area | Create pseudo-absence data | Partition data for evaluating models | Extracting environmental values | Modeling | Comparing our models | Partial dependence plots to explore the impact of predictor conditions on suitability | Extrapolation evaluation | Truncating SDMs predictions based on extrapolation thresholds

Introduction | Required packages | 1. Directory Setup | 2. Load Species Occurrence Data | 3. Environmental Data | 4. Define species training area | 5. Evaluate Species-Specific Multicollinearity | 6. Correct Multicollinearity | 7. Process environmental PCA for all species | 8. Occurrence Sample Bias Correction | 9. Sample Pseudo-Absences & Background points | 10. Data Partitioning | 11. Configuration of output directories and data used during model fitting | 12. Main loop by species for model fitting, evaluation and prediction | 13. Visualization of spatial predictions | 14. Visualize future projections | 15. Conclusion | 1. Initial Setup | 2. Data Preparation | 4. Deine model calibration area | 5. Evaluate species-specific predictor collinearity | 6. Correct predictor collinearity | 7. Environmental PCA for all species | 8. Occurrence sample bias correciton | 9. Pseudo-absence Generation | 11. Configure and organize output directory | 12. Modeling | 13. Visualize spatial predictions | 16. Other examples of entire modeling workflows with flexsdm.

Cite our package as | 2026 (n = 42) | 2025 (n = 46) | 2024 (n = 49) | 2023 (n = 13) | 2022 (n = 2)