fireSense_ignitionPredict Manual

v.1.1.0

Last updated: 2026-09-29

fireSense_ignitionPredict Module

made-with-Markdown

Authors:

Eliot McIntire [aut, cre], Ian Eddy [aut], Jean Marchal [aut], Alex M Chubaty [ctb]

Module Overview

Module summary

Each year, predicts ignitions and escapes from the models fitted by fireSense_ignitionFit and fireSense_EscapeFit, for the ignition component of fireSense (Marchal, Steve G. Cumming, et al. 2017b; Marchal, Steve G. Cumming, et al. 2017a; Marchal et al. 2019).

  1. The covariates in fireSense_igAndEscapePred_Covariates are rescaled with fireSenseUtils::prepareCovariatesOuter(), the function used for fitting (rescaleVars, modelAlgorithm).
  2. Expected ignitions per coarse pixel are the mean of the predictions of the per-fold ignition models; the number of ignitions is drawn from a Poisson.
  3. For coarse pixels with ignitions, the escape probability is the mean of the per-fold escape models, clamped to [0, 1]; escapes are drawn from a binomial with size = ignitions.
  4. Each ignition is placed in a randomly chosen flammable pixel of flammableRTM inside its coarse pixel.

Only xgboost models are supported.

Module inputs and parameters

ignitionFitRTM (the coarse raster used for fitting, from fireSense_dataPrepFit) is also read from the simList, though it is not declared as an input. modelAlgorithm and rescaleVars must have the same value in every module that defines them.

Table 1 shows the full list of module inputs.

Table 1: Table 2: List of fireSense_ignitionPredict input objects and their description.
objectName objectClass desc sourceURL
fireSense_EscapeFitted fireSense_EscapeFit Fitted escape models ($modelList$model, one per fold), from fireSense_EscapeFit. NA
fireSense_IgnitionFittedList list Only with several fitted ELFs: one fireSense_IgnitionFitted per ELF, named by ELFind. Each ELF’s model predicts the coarse pixels of that ELF. NA
fireSense_EscapeFittedList list Only with several fitted ELFs: one fireSense_EscapeFitted per ELF, named as fireSense_IgnitionFittedList. NA
rasterToMatchLargeELF SpatRaster Only with several fitted ELFs: each pixel’s ELF (ELFind), from fireSense_ELFs with a studyAreaLarge. NA
fireSense_IgnitionFitted fireSense_IgnitionFit Fitted ignition models ($modelList$model, one per fold) and $modelList$fittingRes, from fireSense_ignitionFit. NA
fireSense_igAndEscapePred_Covariates data.table This year’s covariates, from fireSense_dataPrepPredict. pixelID is the cell index of ignitionFitRTM. NA
flammableRTM SpatRaster Binary raster, 1 where the pixel is flammable. NA

Summary of user-visible parameters (Table 3)

Table 3: Table 4: List of fireSense_ignitionPredict parameters and their description.
paramName paramClass default min max paramDesc
modelAlgorithm character xgboost NA NA Algorithm used to fit the models; only xgboost is supported. Must agree with the value in the other fireSense modules.
rescaleVars logical TRUE NA NA Rescale the covariates before predicting? With xgboost they are standardized with scale(). Must agree with the value in the other fireSense modules.
.runInitialTime numeric 0 NA NA Time of the first prediction.
.runInterval numeric 1 NA NA Interval between predictions, in years. NA predicts once.
.saveInitialTime numeric NA NA NA Time of the save event, which does nothing. NA means never.
.saveInterval numeric NA NA NA If not NA, the ignition probability raster is plotted each year.
.studyAreaName character NA NA NA Human-readable name for the study area used.
.useCache logical FALSE NA NA Should this entire module be run with caching activated? This is generally intended for data-type modules, where stochasticity and time are not relevant

Events

  • init: schedules run at .runInitialTime, and save at .saveInitialTime if that is not NA.
  • run: makes the predictions and draws described above; repeats every .runInterval.
  • save: does nothing but say so. To save the predicted raster, name fireSense_IgAndEscapeProbRas in outputs(sim).

Plotting

If .saveInterval is not NA, the ignition probability raster is plotted each year with Plots().

Module outputs

Description of the module outputs (Table 5).

Table 5: Table 6: List of fireSense_ignitionPredict outputs and their description.
objectName objectClass desc
fireSense_IgAndEscapeProbRas SpatRaster Two layers, ignitionProb (expected ignitions per pixel) and escapeProb, at the resolution of ignitionFitRTM.
ignitionsAndEscapes data.table One row per ignited pixel, in random order: pixelID (cell index of flammableRTM), igProb, ignitions, escapeProb, escapes of the coarse pixel it was drawn from, and escaped, whether this ignition escaped: exactly escapes of a coarse pixel’s rows are TRUE.

Runs after fireSense_dataPrepPredict, which supplies the covariates. ignitionsAndEscapes is used by fireSense to start fires. It is normally run as part of the fireSense module group.

Getting help

References

Marchal, Jean, Steve G. Cumming, and Eliot J. B. McIntire. 2017a. “Exploiting Poisson Additivity to Predict Fire Frequency from Maps of Fire Weather and Land Cover in Boreal Forests of Québec, Canada.” Ecography 40 (1): 200–209. https://doi.org/10.1111/ecog.01849.
Marchal, Jean, Steve G Cumming, and Eliot J B McIntire. 2017b. “Land Cover, More Than Monthly Fire Weather, Drives Fire-Size Distribution in Southern Québec Forests: Implications for Fire Risk Management.” PLoS ONE 12 (6): 1–17. https://doi.org/10.1371/journal.pone.0179294.
Marchal, Jean, Steven G. Cumming, and Eliot J. B. McIntire. 2019. “Turning Down the Heat: Vegetation Feedbacks Limit Fire Regime Responses to Global Warming.” Ecosystems, ahead of print, May. https://doi.org/10.1007/s10021-019-00398-2.