The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
h3sdm_pa() now transforms presence records to the CRS
of the H3 grid before joining, fixing an error when the grid is in a
projected CRS.h3sdm_aoa() estimates the Dissimilarity Index (DI) and
the Area of Applicability (AOA) for spatial prediction models, based on
Meyer & Pebesma (2021).h3sdm_get_grid() now preserves the CRS of the input
sf_object. Previously, the function always returned the
grid in WGS84 (EPSG:4326) regardless of the input CRS. Now, if the AOI
is in a projected CRS, the output grid will be reprojected to match it.
The internal H3 computation still uses WGS84 as required by the H3
system.h3sdm_predict() internal comments translated to English
and @seealso updated to include
h3sdm_aoa().h3sdm_fit_model() now automatically detects model
mode (classification or regression), enabling count-based models
(Poisson, Negative Binomial) with appropriate metrics (RMSE, R², MAE)
without requiring manual configuration.
h3sdm_fit_model() and h3sdm_predict()
now automatically detect model mode (classification or regression),
enabling count-based models (Poisson, Negative Binomial) without manual
configuration. Full backward compatibility maintained.
h3sdm_get_records() now supports
"biodatacr" as an optional provider, querying occurrence
records from BiodataCR (Costa Rica) via the rbiodatacr
package. h3sdm_pa() inherits this support automatically
through its providers argument. rbiodatacr is
listed as a suggested dependency.
h3sdm_pa_from_records(): generates a
presence/pseudo-absence dataset from user-provided records. Accepts a
data.frame or sf object with coordinates in
WGS84 (EPSG:4326). Supports optional filtering by a
geospatialKosher column to remove records with questionable
spatial quality.
h3sdm_count_from_records(): generates a hexagonal
grid with count-based response variables (species richness, total
detections, or individual abundance) from user-provided records. Accepts
a data.frame or sf object. Supports optional
filtering by presence column, confidence threshold, and date
range.
h3sdm_recipe(): added response_col
parameter (default "presence") to support count-based
response variables. Use response_col = "count" when working
with data generated by h3sdm_count_from_records().
h3sdm_recipe_gam(): added response_col
parameter (default "presence") with the same behavior as
h3sdm_recipe(). Also added documentation examples for both
presence/absence and count-based models.
h3sdm_workflow_gam(): updated documentation to
clarify the use of set_mode("classification") for
presence/absence models and set_mode("regression") with
family = poisson() for count-based models.
h3sdm_workflow(): updated documentation to clarify
model mode selection for presence/absence and count-based
models.
h3sdm_workflows(): updated documentation to clarify
model mode selection for presence/absence and count-based
models.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.