PointedSDMs

Simplify the construction of integrated species distribution models (ISDMs) for large collections of heterogeneous data.
https://github.com/philipmostert/pointedsdms

Category: Biosphere
Sub Category: Species Distribution Modeling

Last synced: about 10 hours ago
JSON representation

Repository metadata

Wrapper function for 'inlabru' for modeling species distribution models from disparate datasets.

• Host: GitHub
• URL: https://github.com/philipmostert/pointedsdms
• Owner: PhilipMostert
• Created: 2021-05-19T10:01:46.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2025-09-24T10:03:56.000Z (3 months ago)
• Last Synced: 2025-10-22T05:59:46.758Z (2 months ago)
• Language: R
• Size: 19 MB
• Stars: 26
• Watchers: 4
• Forks: 6
• Open Issues: 1
• Releases: 4
• Metadata Files:
  • Readme: README.Rmd
  • Changelog: NEWS.md

README.Rmd

          ---
output: github_document
---



```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
```

# PointedSDMs



[![R-CMD-check](https://github.com/PhilipMostert/PointedSDMs/actions/workflows/R-CMD-check.yaml/badge.svg?branch=main)](https://github.com/PhilipMostert/PointedSDMs/actions/workflows/R-CMD-check.yaml)[![Codecov test coverage](https://codecov.io/gh/PhilipMostert/PointedSDMs/branch/main/graph/badge.svg)](https://app.codecov.io/gh/PhilipMostert/PointedSDMs?branch=ChangingToR6) [![DOI](https://zenodo.org/badge/368823136.svg)](https://zenodo.org/badge/latestdoi/368823136)



The goal of *PointedSDMs* is to simplify the construction of integrated species distribution models (ISDMs) for large collections of heterogeneous data. It does so by building wrapper functions around [inlabru](https://besjournals.onlinelibrary.wiley.com/doi/abs/10.1111/2041-210X.13168), which uses the [INLA methodology](https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-9868.2008.00700.x) to estimate a class of latent Gaussian models.

## Installation

You can install the development version of PointedSDMs from [GitHub](https://github.com/) with:

``` r
# install.packages("devtools")
devtools::install_github("PhilipMostert/PointedSDMs")
```

or directly through CRAN using:

``` r
install.packages('PointedSDMs')
```

## Package functionality

*PointedSDMs* includes a selection of functions used to streamline the construction of ISDMs as well and perform model cross-validation. The core functions of the package are:

| Function name | Function description |
|-------------------|-----------------------------------------------------|
| `startISDM()` | Initialize and specify the components used in the integrated model. |
| `startSpecies()` | Initialize and specify the components used in the multi-species integrated model. |
| `blockedCV()` | Perform spatial blocked cross-validation. |
| `fitISDM()` | Estimate and preform inference on the integrated model. |
| `datasetOut()` | Perform dataset-out cross-validation, which calculates the impact individual datasets have on the full model. |

The function `intModel()` produces an [R6](https://github.com/r-lib/R6) object, and as a result there are various *slot functions* available to further specify the components of the model. These *slot functions* include:

| `intModel()` slot function | Function description |
|--------------------|----------------------------------------------------|
| `` `.$help()` `` | Show documentation for each of the slot functions. |
| `` `.$plot()` `` | Used to create a plot of the available data. The output of this function is an object of class [`gg`](https://github.com/tidyverse/ggplot2). |
| `` `.$addBias()` `` | Add an additional spatial field to a dataset to account for sampling bias in unstructured datasets. |
| `` `.$updateFormula()` `` | Used to update a formula for a process. The idea is to start specify the full model with `startISDM()`, and then thin components per dataset with this function. |
| `` `.$updateComponents()` `` | Change or add new components used by [inlabru](https://besjournals.onlinelibrary.wiley.com/doi/abs/10.1111/2041-210X.13168) in the integrated model. |
| `` `.$priorsFixed()` `` | Change the specification of the prior distribution for the fixed effects in the model. |
| `` `.$specifySpatial()` `` | Specify the spatial field in the model using penalizing complexity (PC) priors. |
| `` `.$spatialBlock()` `` | Used to specify how the points are spatially blocked. Spatial cross-validation is subsequently performed using `blockedCV()`. |
| `` `.$addSamplers()` `` | Function to add an integration domain for the PO datasets. |
| `` `.$specifyRandom()` `` | Specify the priors for the random effects in the model. |
| `` `.$changeLink()` `` | Change the link function of a process. |

## Example

This is a basic example which shows you how to specify and run an integrated model, using three disparate datasets containing locations of the solitary tinamou (*Tinamus solitarius)*.

```{r setup, include=FALSE}
knitr::opts_chunk$set(warning = FALSE, message = FALSE) 
```

```{r example}

library(PointedSDMs)
library(ggplot2)
library(terra)

```

```{r data}

bru_options_set(inla.mode = "experimental")

#Load data in

data("SolitaryTinamou")

projection <- "+proj=longlat +ellps=WGS84"

species <- SolitaryTinamou$datasets

covariates <- terra::rast(system.file('extdata/SolitaryTinamouCovariates.tif', 
                                      package = "PointedSDMs"))

mesh <- SolitaryTinamou$mesh


```

Setting up the model is done easily with `startISDM()`, where we specify the required components of the model:

```{r intModel, message = FALSE, warning = FALSE}

#Specify model -- here we run a model with one spatial covariate and a shared spatial field

model <- startISDM(species, spatialCovariates = covariates,
                 Projection = projection, Mesh = mesh, responsePA = 'Present')

```

We can also make a quick plot of where the species are located using `` `.$plot()` ``:

```{r plot, warning = FALSE, message = FALSE, fig.width=8, fig.height=5}

region <- SolitaryTinamou$region

model$plot(Boundary = FALSE) + 
  geom_sf(data = st_boundary(region))

```

To improve stability, we specify priors for the intercepts of the model using `` `.$priorsFixed()` ``

```{r specifyPriors}

model$priorsFixed(Effect = 'Intercept',
                  mean.linear = 0, 
                  prec.linear = 1)

```

And *PC* priors for the spatial field using `` `.$specifySpatial()` ``:

```{r specifySpatial}

model$specifySpatial(sharedSpatial = TRUE,
                     prior.range = c(0.2, 0.1),
                     prior.sigma = c(0.1, 0.1))

```

We can then estimate the parameters in the model using the `fitISDM()` function:

```{r fitISDM, warning = FALSE, message = FALSE}

modelRun <- fitISDM(model, options = list(control.inla = 
                                            list(int.strategy = 'eb'), 
                                          safe = TRUE))
summary(modelRun)

```

*PointedSDMs* also includes generic predict and plot functions:

```{r predict_and_plot, warning = FALSE, message = FALSE, fig.width=8, fig.height=5}

predictions <- predict(modelRun, mesh = mesh,
                       mask = region, 
                       spatial = TRUE,
                       fun = 'linear')

plot(predictions, variable = c('mean', 'sd'))

```

        

---

Owner metadata

• Name: Philip Mostert
• Login: PhilipMostert
• Email:
• Kind: user
• Description:
• Website:
• Location: Trondheim, Norway
• Twitter:
• Company: Norwegian University of Science and Technology
• Icon url: https://avatars.githubusercontent.com/u/81858712?v=4
• Repositories: 4
• Last ynced at: 2023-03-03T16:22:15.112Z
• Profile URL: https://github.com/PhilipMostert

---

GitHub Events

Total

• Create event: 2
• Release event: 1
• Issues event: 18
• Watch event: 3
• Issue comment event: 30
• Push event: 31
• Pull request event: 2
• Fork event: 1

Last Year

• Create event: 2
• Release event: 1
• Issues event: 18
• Watch event: 2
• Issue comment event: 30
• Push event: 30
• Pull request event: 2
• Fork event: 1

---

Committers metadata

Last synced: about 2 months ago

Name	Email	Commits
Philip Mostert	p****t@n****o	533
Philip Mostert	p****m@d****o	69
Philip Mostert	p****m@d****o	62
Philip Mostert	p****m@d****o	54
Philip Mostert	p****m@d****o	52
Philip Mostert	p****m@d****o	52
Philip Mostert	p****m@d****o	50
Philip Mostert	p****m@d****o	48
Philip Mostert	p****m@d****o	45
Philip Mostert	p****m@d****o	42
Philip Mostert	p****m@P****l	37
Philip Mostert	p****m@d****o	36
Philip Mostert	p****m@d****o	32
Philip Mostert	p****m@d****o	26
Philip Mostert	p****m@d****o	25
Philip Mostert	p****m@d****o	24
Philip Mostert	p****m@d****o	19
Philip Mostert	p****m@d****o	17
Philip Mostert	p****m@d****o	17
Philip Mostert	p****m@d****o	16
Philip Mostert	p****m@d****o	15
Philip Mostert	p****m@d****o	14
Philip Mostert	p****m@d****o	12
Philip Mostert	p****m@d****o	12
Philip Mostert	p****m@d****o	10
Philip Mostert	p****m@d****o	9
Philip Mostert	p****m@d****o	7
Finn Lindgren	F****n@g****m	6
Philip Mostert	p****m@d****o	4
RRTogunov	r****v@g****m	3
and 14 more...

Committer domains:

• vpn-10-50-238-127.vpn-a.ntnu.no: 1
• dhcp-10-24-6-86.wlan.ntnu.no: 1
• dhcp-10-24-5-229.wlan.ntnu.no: 1
• dhcp-10-24-31-45.wlan.ntnu.no: 1
• dhcp-10-24-28-84.wlan.ntnu.no: 1
• dhcp-10-24-22-246.wlan.ntnu.no: 1
• dhcp-10-24-20-92.wlan.ntnu.no: 1
• dhcp-10-24-20-55.wlan.ntnu.no: 1
• dhcp-10-24-106-153.wlan.ntnu.no: 1
• dhcp-10-24-22-212.wlan.ntnu.no: 1
• dhcp-10-24-22-247.wlan.ntnu.no: 1
• dhcp-10-24-5-189.wlan.ntnu.no: 1
• dhcp-10-24-6-104.wlan.ntnu.no: 1
• vpn-10-50-238-12.vpn-a.ntnu.no: 1
• dhcp-10-24-20-102.wlan.ntnu.no: 1
• dhcp-10-24-20-192.wlan.ntnu.no: 1
• dhcp-10-24-6-146.wlan.ntnu.no: 1
• dhcp-10-24-21-144.wlan.ntnu.no: 1
• dhcp-10-24-23-27.wlan.ntnu.no: 1
• dhcp-10-24-20-11.wlan.ntnu.no: 1
• dhcp-10-24-22-254.wlan.ntnu.no: 1
• dhcp-10-24-23-62.wlan.ntnu.no: 1
• dhcp-10-24-23-35.wlan.ntnu.no: 1
• dhcp-10-24-22-183.wlan.ntnu.no: 1
• dhcp-10-24-20-157.wlan.ntnu.no: 1
• dhcp-10-24-23-217.wlan.ntnu.no: 1
• dhcp-10-24-21-192.wlan.ntnu.no: 1
• dhcp-10-24-20-125.wlan.ntnu.no: 1
• dhcp-10-24-23-41.wlan.ntnu.no: 1
• dhcp-10-24-22-154.wlan.ntnu.no: 1
• dhcp-10-24-21-201.wlan.ntnu.no: 1
• dhcp-10-24-22-32.wlan.ntnu.no: 1
• dhcp-10-24-21-173.wlan.ntnu.no: 1
• dhcp-10-24-23-113.wlan.ntnu.no: 1
• dhcp-10-24-22-197.wlan.ntnu.no: 1
• dhcp-10-24-23-55.wlan.ntnu.no: 1
• dhcp-10-24-22-145.wlan.ntnu.no: 1
• dhcp-10-24-21-189.wlan.ntnu.no: 1
• dhcp-10-24-21-41.wlan.ntnu.no: 1
• dhcp-10-24-20-62.wlan.ntnu.no: 1
• ntnu.no: 1

---

Issue and Pull Request metadata

Last synced: about 2 months ago

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/philipmostert/pointedsdms

---

---

---

Package metadata

• Total packages: 3
• Total downloads:
  • cran: 739 last-month
• Total dependent packages: 1 (may contain duplicates)
• Total dependent repositories: 1 (may contain duplicates)
• Total versions: 15
• Total maintainers: 1

---

Dependencies

Score: 13.68937574308997