Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.
This is the third part of a blog post series on spatial machine learning with R.
You can find the list of other blog posts in this series in part one.
Introduction
In this blog post, we will show how to use the tidymodels framework for spatial machine learning. The tidymodels framework is a collection of R packages for modeling and machine learning using tidyverse principles.
Prepare data
Load the required packages:
library(terra) library(sf) library(tidymodels) library(ranger) library(dplyr) library(spatialsample) library(waywiser) library(vip)
Read data:
trainingdata <- sf::st_read("https://github.com/LOEK-RS/FOSSGIS2025-examples/raw/refs/heads/main/data/temp_train.gpkg")
predictors <- terra::rast("https://github.com/LOEK-RS/FOSSGIS2025-examples/raw/refs/heads/main/data/predictors.tif")
Prepare data by extracting the training data from the raster and converting it to a sf object.
trainDat <- sf::st_as_sf(terra::extract(predictors, trainingdata, bind = TRUE)) predictor_names <- names(predictors) # Extract predictor names from the raster response_name <- "temp"
Compared to caret, no dropping of the geometries is required.
A simple model training and prediction
First, we train a random forest model. This is done by defining a recipe and a model, and then combining them into a workflow. Such a workflow can then be used to fit the model to the data.
# Define the recipe
formula <- as.formula(paste(
response_name,
"~",
paste(predictor_names, collapse = " + ")
))
recipe <- recipes::recipe(formula, data = trainDat)
rf_model <- parsnip::rand_forest(trees = 100, mode = "regression") |>
set_engine("ranger", importance = "impurity")
# Create the workflow
workflow <- workflows::workflow() |>
workflows::add_recipe(recipe) |>
workflows::add_model(rf_model)
# Fit the model
rf_fit <- parsnip::fit(workflow, data = trainDat)
Now, let’s use the model for spatial prediction with terra::predict().
prediction_raster <- terra::predict(predictors, rf_fit, na.rm = TRUE) plot(prediction_raster)
Spatial cross-validation
Cross-validation requires to specify how the data is split into folds. Here, we define a non-spatial cross-validation with rsample::vfold_cv() and a spatial cross-validation with spatialsample::spatial_block_cv().
random_folds <- rsample::vfold_cv(trainDat, v = 4) block_folds <- spatialsample::spatial_block_cv(trainDat, v = 4, n = 2) spatialsample::autoplot(block_folds)
# control cross-validation keep_pred <- tune::control_resamples(save_pred = TRUE, save_workflow = TRUE)
Next, we fit the model to the data using cross-validation with tune::fit_resamples().
### Cross-validation
rf_random <- tune::fit_resamples(
workflow,
resamples = random_folds,
control = keep_pred
)
rf_spatial <- tune::fit_resamples(
workflow,
resamples = block_folds,
control = keep_pred
)
To compare the fitted models, we can use the tune::collect_metrics() function to get the metrics.
### get CV metrics tune::collect_metrics(rf_random)
# A tibble: 2 × 6 .metric .estimator mean n std_err .config <chr> <chr> <dbl> <int> <dbl> <chr> 1 rmse standard 0.934 4 0.0610 Preprocessor1_Model1 2 rsq standard 0.908 4 0.0154 Preprocessor1_Model1
tune::collect_metrics(rf_spatial)
# A tibble: 2 × 6 .metric .estimator mean n std_err .config <chr> <chr> <dbl> <int> <dbl> <chr> 1 rmse standard 1.33 4 0.271 Preprocessor1_Model1 2 rsq standard 0.740 4 0.0783 Preprocessor1_Model1
# rf_spatial$.metrics # metrics from each fold
Additionally, we can visualize the models by extracting their predictions with tune::collect_predictions() and plotting them.
Similar to caret, we first define folds and a definition of train control. The final model, however, is still stored in a separate object.
Model tuning: spatial hyperparameter tuning and variable selection
Hyperparameter tuning
Next, we tune the model hyperparameters. For this, we change the workflow to include the tuning specifications by using the tune() function inside the model definition and define a grid of hyperparameters to search over. The tuning is done with tune::tune_grid().
# mark two parameters for tuning:
rf_model <- parsnip::rand_forest(
trees = 100,
mode = "regression",
mtry = tune(),
min_n = tune()
) |>
set_engine("ranger", importance = "impurity")
workflow <- update_model(workflow, rf_model)
# define tune grid:
grid_rf <-
grid_space_filling(
mtry(range = c(1, 20)),
min_n(range = c(2, 10)),
size = 30
)
# tune:
rf_tuning <- tune_grid(
workflow,
resamples = block_folds,
grid = grid_rf,
control = keep_pred
)
The results can be extracted with collect_metrics() and then visualized.
rf_tuning |>
collect_metrics()
# A tibble: 60 × 8
mtry min_n .metric .estimator mean n std_err .config
<int> <int> <chr> <chr> <dbl> <int> <dbl> <chr>
1 1 5 rmse standard 1.91 4 0.307 Preprocessor1_Model01
2 1 5 rsq standard 0.613 4 0.0849 Preprocessor1_Model01
3 1 9 rmse standard 1.93 4 0.311 Preprocessor1_Model02
4 1 9 rsq standard 0.582 4 0.103 Preprocessor1_Model02
5 2 4 rmse standard 1.61 4 0.318 Preprocessor1_Model03
6 2 4 rsq standard 0.697 4 0.0692 Preprocessor1_Model03
7 2 2 rmse standard 1.68 4 0.285 Preprocessor1_Model04
8 2 2 rsq standard 0.654 4 0.111 Preprocessor1_Model04
9 3 7 rmse standard 1.47 4 0.304 Preprocessor1_Model05
10 3 7 rsq standard 0.713 4 0.0837 Preprocessor1_Model05
# ℹ 50 more rows
rf_tuning |>
collect_metrics() |>
mutate(min_n = factor(min_n)) |>
ggplot(aes(mtry, mean, color = min_n)) +
geom_line(linewidth = 1.5, alpha = 0.6) +
geom_point(size = 2) +
facet_wrap(~.metric, scales = "free", nrow = 2) +
scale_x_log10(labels = scales::label_number()) +
scale_color_viridis_d(option = "plasma", begin = .9, end = 0)
Finally, we can extract the best model and use it to get the variable importance and make predictions.
finalmodel <- fit_best(rf_tuning) finalmodel
══ Workflow [trained] ══════════════════════════════════════════════════════════ Preprocessor: Recipe Model: rand_forest() ── Preprocessor ──────────────────────────────────────────────────────────────── 0 Recipe Steps ── Model ─────────────────────────────────────────────────────────────────────── Ranger result Call: ranger::ranger(x = maybe_data_frame(x), y = y, mtry = min_cols(~19L, x), num.trees = ~100, min.node.size = min_rows(~3L, x), importance = ~"impurity", num.threads = 1, verbose = FALSE, seed = sample.int(10^5, 1)) Type: Regression Number of trees: 100 Sample size: 195 Number of independent variables: 22 Mtry: 19 Target node size: 3 Variable importance mode: impurity Splitrule: variance OOB prediction error (MSE): 0.7477837 R squared (OOB): 0.9062111
imp <- extract_fit_parsnip(finalmodel) |>
vip::vip()
imp
final_pred <- terra::predict(predictors, finalmodel, na.rm = TRUE) plot(final_pred)
Area of applicability
The waywiser package provides a set of tools for assessing spatial models, including an implementation of multi-scale assessment and area of applicability. The area of applicability is a measure of how well the model (given the training data) can be applied to the prediction data. It can be calculated with the ww_area_of_applicability() function, and then predicted on the raster with terra::predict().
model_aoa <- waywiser::ww_area_of_applicability(
st_drop_geometry(trainDat[, predictor_names]),
importance = vip::vi_model(finalmodel)
)
AOA <- terra::predict(predictors, model_aoa)
plot(AOA$aoa)
More information on the waywiser package can be found in its documentation.
Summary
This blog post showed how to use the tidymodels framework for spatial machine learning. We demonstrated how to train a random forest model, perform spatial cross-validation, tune hyperparameters, and assess the area of applicability. We also showed how to visualize the results and extract variable importance.1
The tidymodels framework with its packages spatialsample and waywiser provides a powerful and flexible way to perform spatial machine learning in R. At the same time, it is a bit more complex than caret: it requires getting familiar with several packages2 and relationships between them. Thus, the decision of which framework to use depends on the specific needs and preferences of the user.
This blog post was originally written as a supplement to the poster “An Inventory of Spatial Machine Learning Packages in R” presented at the FOSSGIS 2025 conference in Muenster, Germany. The poster is available at https://doi.org/10.5281/zenodo.15088973.
Footnotes
-
We have not, though, covered all the features of the tidymodels framework, such as feature selection (https://stevenpawley.github.io/recipeselectors/) or model ensembling.
︎ -
Including remembering their names and roles
︎
︎Reuse
Citation
@online{meyer2025,
author = {Meyer, Hanna and Nowosad, Jakub},
title = {Spatial Machine Learning with the Tidymodels Framework},
date = {2025-05-28},
url = {https://geocompx.org/post/2025/sml-bp3/},
langid = {en}
}
with the Tidymodels Framework.” May 28, 2025. https://geocompx.org/post/2025/sml-bp3/.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you’re looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.
Continue reading: Spatial machine learning with the tidymodels framework
Spatial Machine Learning with R and the Tidymodels Framework
In a recent series of blog posts, authors Hanna Meyer and Jakub Nowosad have shed light on the use of the tidymodels framework for spatial machine learning using R. This is a topic of keen interest to both data scientists and developers harnessing the potential of spatial analysis and machine learning algorithms.
A rundown of the Blog post series
The blog post series is broken down into three parts. The introduction and preparation of data started off the process. The authors shared the sequence to import the necessary packages, read, and prepare the data. They elaborated on how to make use of the libraries – terra, ranger, dplyr, spatialsample, waywiser, and vip.
Meyer and Nowosad then dive deeper into training a basic random forest model with the use of the tidymodels framework. This involves defining a recipe and a model, integrating them into a workflow, and fitting the model to the data. They also use this trained model to conduct spatial prediction.
Furthermore, the subject of spatial cross-validation is clearly touched upon. The authors elaborate on the process of fitting the model to the data using cross-validation and then comparing the fitted models. Visualizing these models has also been made easier with the tune::collect_predictions() function.
Fine-tuning of models
In the article, focus is also put on model tuning including spatial hyperparameter tuning and variable selection. Hanna Meyer and Jakub Nowosad walk through the process of changing the workflow to include tuning specifications, defining a grid of hyperparameters and realizing the tuning. This is followed by visualizing the tuning results and visualizing the model’s performance.
Lastly, they focus on the applications of these models that include implementation of multi-scale assessment and area of applicability. Here is detailed an example of a spatial model being assessed, with a brief overview of how to calculate and predict the area of applicability using the ‘waywiser’ package.
Long-term implications and future prospects
Given the advent and rise of spatial data analytics, these tutorials offer invaluable insights into the role of R in harnessing spatial machine learning for varied data applications. Being an open-source language, R has extensive libraries and resources that can accommodate complex analyses such as spatial machine learning.
The tidymodels framework, as elucidated in the tutorials, opens up new avenues for spatial and geo-spatial analyses coupled with machine learning. The long-term implications could include sophisticated predictive models that power critical decision making in areas such as climate modeling, urban planning, infrastructure development, and even healthcare management.
The possible future developments may include incorporating element of artificial intelligence (AI) to make predictions more accurate. Furthermore, integrating the tidymodels framework with other languages such as Python could enhance the analytical versatility of developers and data scientists alike.
Actionable Advice
Based on the insights offered by Meyer and Nowosad, data scientists and developers keen on leveraging spatial machine learning should make a note of the following:
- Invest time into learning and getting accustomed to the tidymodels framework. Understand the relationship between its several packages for efficient utilization.
- Practice writing code for model training, cross-validation, and tuning in R using tidymodels to improve proficiency.
- Experiment in real-time with different models, packages, and data to identify models that work best with specific spatial data.
- Stay updated with advancements in spatial analysis to incorporate cutting-edge features and techniques in your analyses.