(ref:fireSense-ignitionPredict) fireSense_ignitionPredict
Eliot McIntire eliot.mcintire@nrcan-rncan.gc.ca [aut, cre], Ian Eddy ian.eddy@nrcan-rncan.gc.ca [aut], Jean Marchal jean.d.marchal@gmail.com [aut], Alex M Chubaty achubaty@for-cast.ca [ctb]
Each year, predicts the expected number of ignitions and of escapes from the models fitted by fireSense_ignitionFit and fireSense_EscapeFit, for the ignition component of fireSense [@Marchal:2017a; @Marchal:2017b; @Marchal:2019].
fireSense_igAndEscapePred_Covariates are rescaled with fireSenseUtils::prepareCovariatesOuter(), the function used for fitting (rescaleVars, modelAlgorithm).fireSense_IgAndEscapeDistribution. Nothing is drawn here: fireSense_burn draws the ignitions and escapes, places them and spreads the fires.Only xgboost models are supported.
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 @ref(tab:moduleInputs-fireSense-ignitionPredict) shows the full list of module inputs.
| 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 studyArea_fireSense.
|
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 |
| ignitionFitRTM | SpatRaster |
The coarse grid of fireSense_igAndEscapePred_Covariates: from fireSense_dataPrepFit, else fireSense_dataPrepPredict. The probability rasters are made on it.
|
NA |
Summary of user-visible parameters (Table @ref(tab:moduleParams-fireSense-ignitionPredict))
| paramName | paramClass | default | min | max | paramDesc | cacheKey |
|---|---|---|---|---|---|---|
| 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.
|
TRUE |
| 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.
|
TRUE |
| .runInitialTime | numeric | 0 | NA | NA | Time of the first prediction. | TRUE |
| .runInterval | numeric | 1 | NA | NA |
Interval between predictions, in years. NA predicts once.
|
TRUE |
| .saveInitialTime | numeric | NA | NA | NA |
Time of the save event, which does nothing. NA means never.
|
TRUE |
| .saveInterval | numeric | NA | NA | NA |
If not NA, the ignition probability raster is plotted each year.
|
TRUE |
| .studyAreaName | character | NA | NA | NA | Human-readable name for the study area used. | TRUE |
| .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 | TRUE |
init: schedules run at .runInitialTime, and save at .saveInitialTime if that is not NA.run: makes the predictions described above; repeats every .runInterval.save: does nothing but say so. To save the predicted raster, name fireSense_IgAndEscapeProbRas in outputs(sim).If .saveInterval is not NA, the expected-ignitions raster is plotted each year with Plots().
Description of the module outputs (Table @ref(tab:moduleOutputs-fireSense-ignitionPredict)).
| objectName | objectClass | desc |
|---|---|---|
| fireSense_IgAndEscapeProbRas | SpatRaster |
Two layers at the resolution of ignitionFitRTM, for every pixel with covariates: ignitionProb, the expected number of ignitions per pixel and year, and escapeProb, the expected number of escapes per pixel and year, given at least one ignition. Both are means of the fitted distributions in fireSense_IgAndEscapeDistribution, not probabilities. And two more, ignitionYearSD and escapeYearSD: the sd of the year effect of each pixel’s ELF’s ignition and escape fit (modelList$yearSD, 0 for a fit without one), with which fireSense_burn scales both means each year. And, only when a fit has a fitted effect for the year floor(time(sim)) (modelList$yearEffects of fireSense_ignitionFit), ignitionYearEffect and escapeYearEffect: that multiplier (NA in an ELF without one), and ignitionYearEffectShape and escapeYearEffectShape: the shape of its gamma posterior (NA: no uncertainty), which fireSense_burn uses instead of the draw with yearEffects = "fitted".
|
| fireSense_IgAndEscapeDistribution | list |
list(ignition = , escape = ): the objective of the fitted models (e.g. "count:poisson"), which says how fireSense_burn draws from the means in fireSense_IgAndEscapeProbRas.
|
Runs after fireSense_dataPrepPredict, which supplies the covariates. fireSense_IgAndEscapeProbRas and fireSense_IgAndEscapeDistribution are used by fireSense_burn, which draws the ignitions and escapes and starts the fires. It is normally run as part of the fireSense module group.