enmSdmX: enmSdmX: Species distribution modeling and ecological niche...

In enmSdmX: Species Distribution Modeling and Ecological Niche Modeling

enmSdmX: Species distribution modeling and ecological niche modeling

Description

Tools for implementing species distribution models and ecological niche models, including: bias correction, spatial cross-validation, model evaluation, raster interpolation, biotic "velocity" (speed and direction of movement of a "mass" represented by a raster), and tools for using spatially imprecise records. The heart of the package is a set of "training" functions which automatically optimize model complexity based number of available occurrences. These algorithms include MaxEnt, MaxNet, boosted regression trees/gradient boosting machines, generalized additive models, generalized linear models, natural splines, and random forests. To enhance interoperability to and from other packages, the package does not create any new classes. The package works with PROJ6 geodetic objects and coordinate reference systems.

Details

Create an issue on GitHub.

Using imprecisely-georeferenced occurrences

coordImprecision: Coordinate imprecision
nearestEnvPoints: Extract "most conservative" environments from points and/or polygons
nearestGeogPoints: Create a minimum convex polygon from a set of spatial polygons and/or points

Data preparation

geoFold: Assign geographically-distinct k-folds
geoFoldContrast: Assign geographically-distinct k-folds to background or absence sites
elimCellDuplicates: Eliminate duplicate points in each cell of a raster

Bias correction

geoThin: Thin geographic points deterministically or randomly
weightByDist: Proximity-based weighting for occurrences (points) to correct for spatial bias

Model calibration

trainByCrossValid: and summaryByCrossValid: Implement a trainXYZ function across calibration folds (which are distinct from evaluation folds).
trainBRT: Boosted regression trees (BRTs)
trainESM: Ensembles of small models (ESMs)
trainGLM: Generalized linear models (GLMs)
trainGLM: Generalized linear models (GLMs)
trainMaxEnt: MaxEnt models
trainMaxNet: MaxNet models trainNS: Natural spline (NS) models
trainRF: Random forest (RF) models

Model prediction

predictEnmSdm: Predict most model types using default settings
predictMaxEnt: Predict MaxEnt model
predictMaxNet: Predict MaxNet model

Model evaluation

evalAUC: AUC (with/out site weights)
evalMultiAUC: Multivariate version of AUC (with/out site weight)
evalContBoyce: Continuous Boyce Index (with/out site weights)
evalThreshold: Thresholds to convert continuous predictions to binary predictions (with/out site weights)
evalThresholdStats: Model performance statistics based on thresholded predictions (with/out site weights)
evalTjursR2: Tjur's R2 (with/out site weights)
evalTSS: True Skill Statistic (TSS) (with/out site weights)
modelSize: Number of response values in a model object

Response curves and niche overlap

compareResponse: Compare model responses to a single variable
nicheOverlapMetrics: Niche overlap metrics
responseCurves: Create plots of response curves for one or more models

Functions for rasters

bioticVelocity: Velocity of movement across a series of rasters
getValueByCell: Get value(s) in raster cell(s) by cell number
globalx: "Friendly" wrapper for terra::global() for calculating raster statistics
interpolateRasts: Interpolate a stack of rasters
longLatRasts: Generate rasters with values of longitude/latitude for cell values
sampleRast: Sample raster with/out replacement
setValueByCell: Set value(s) in raster cell(s) by cell number
squareCellRast: Create a raster with square cells

Coordinate reference systems

getCRS: Return a WKT2 string (coordinate reference system string) using a nickname
crss: Table of coordinate reference systems and nicknames
customAlbers: Create a custom Albers conic equal-area projection
customLambert: Create a custom Lambert azimuthal equal-area projection
customVNS: Create a custom "vertical near-side" projection

Geographic utility functions

countPoints: Number of points in a "spatial points" object
decimalToDms: Convert decimal coordinate to degrees-minutes-seconds
dmsToDecimal: Convert degrees-minutes-seconds coordinate to decimal
extentToVect: Convert extent to polygon
plotExtent: Create a 'SpatialPolygon' the same size as a plot region
spatVectorToSpatial: Convert SpatVector object to a Spatial* object.

Data

canada: Outline of Canada
lemurs: Lemur occurrences
mad0: Madagascar spatial object
mad1: Madagascar spatial object
madClim: Madagascar climate rasters for the present
madClim2030: Madagascar climate rasters for the 2030s
madClim2050: Madagascar climate rasters for the 2050s
madClim2070: Madagascar climate rasters for the 2070s
madClim2090: Madagascar climate rasters for the 2090s

Author(s)

Adam B. Smith

See Also

Useful links:

• https://github.com/adamlilith/enmSdmX

• Report bugs at https://github.com/adamlilith/enmSdmX/issues

enmSdmX documentation built on April 3, 2025, 7:50 p.m.