WLF · Física
Incendios forestales
Simulaciones de propagación del fuego con Cell2Fire sobre un mapa global de combustibles CC-BY, emuladas a 90 m, ancladas a 23 años de área quemada de NASA MODIS (2001–2023) con un anclaje local por celda al historial y calibradas para que el nivel global coincida con la media de 2014–2023 · v1.0 · 2026-09
Oeste de EE. UU. — Sierra Nevada, el chaparral del sur de California y la Gran Cuenca a 90 m
Probabilidad de incendio forestal con base física: simulaciones de propagación del fuego emuladas a 90 m y ancladas a 23 años de área quemada de MODIS. Contrastada con inventarios de incendios independientes —MTBS (EE. UU.) AUC 0.88, NBAC (Canadá) 0.92, EFFIS (Europa) 0.82—, con un AUC 0.95 a nivel de píxel frente a 20 años de historial de quemas de MODIS a 500 m y una concordancia de rango de 0.52 con el modelo FSim del USFS. La probabilidad de quema es relativa al área quemada detectable por MODIS, así que los incendios pequeños están infradetectados; el suelo edificado puntúa 0 por construcción —para direcciones, usa la banda de exposición—; la ubicación dentro de una celda de 0.25° tiene una capacidad predictiva modesta (AUC dentro de la celda 0.61); y es una probabilidad anual a largo plazo, no un estado posterior al incendio: una zona recién quemada no baja de puntuación. Los rásteres descargables llevan la probabilidad ANUAL; /score de la API devuelve por defecto la probabilidad a 50 años (?horizon=50|100|250|500, o ?band=susceptibility para el valor anual): mismo producto, dos bases, así que compare lo equivalente. Se actualiza cada año contra el registro de área quemada, con el corte cada primavera una vez que están completos los archivos de área quemada del año anterior.
Qué incluye
Surfaces — seis bandas globales a 90 m sobre tierra firme entre 60°S y 75°N: probabilidad anual de quema por píxel (0–1; el suelo edificado, el agua, el suelo desnudo y el hielo leen 0), exposición (la mayor probabilidad anual de quema en un radio de 2 km — lo que ve una dirección en un pueblo junto al monte), un corte en cinco clases global y otro relativo a la región de fuego, incertidumbre y cobertura (no combustible / combustible / cultivo). Returns — probabilidad de al menos una quema en 50 / 100 / 250 / 500 años (rp50–rp500, 0–1).
Cada versión: puntuación de 0 a 1 · banda de 5 clases · incertidumbre por píxel · máscara de cobertura de entradas · elemento STAC · documento de metodología.
Entradas
ESA WorldCover 2021 + tabla de correspondencia de combustibles Petrel v1.4 (clases FM40 de Scott y Burgan), Capa de ignición Petrel v0.3, climatología meteorológica de la temporada de incendios de ERA5, terreno Copernicus GLO-30, área quemada NASA MODIS MCD64CMQ 2001–2023 (anclaje), campaña de simulación Cell2Fire (28,498 incendios)
Historial de versiones
Qué cambió entre versiones: las mismas notas que se publican con los datos. De más reciente a más antigua.
Surfaces
v1.0
2026-09
First shipped release of the Petrel wildfire product. An earlier statistical line was listed as v1.1 but never shipped (its entry is kept below for the record); several internal builds of this physics line preceded it.
- Simulation-emulation model at 90 m. Ignition-centric Cell2Fire fire-spread simulations over a designed global sample — 2,261 one-degree clusters stratified across 68 fire-region × land-cover strata, 33,082 seed fires — feed a stopping model calibrated to Global Fire Atlas durations and a gradient-boosted footprint emulator (holdout R² 0.80 on log fire area). Expected fire size is evaluated per (0.1° cell × fuel model × slope) stratum on the 90 m fuel grid; fires are placed on burnable 90 m pixels and their footprints convolved analytically at the scale each fire-size class resolves. The 90 m structure follows fuel, terrain and the wildland edge — a built-up pixel reads 0 beside a scored forest ridge.
- Fire rate from the Petrel Ignition Layer v0.3. Fires per year per cell from the anthropogenic ignition probability (inverted to expected occurrences) and the lightning ignition index, with dryness, precipitation, canopy, temperature and elevation covariates. The rate model is fitted on v0.3 itself — the lightning index enters through log1p, so v0.3's rescale of that band needed a refit, not an intercept adjustment.
- Anchored to NASA MODIS MCD64 burned area, 2001–2023. Three steps: a covariate-space correction fitted at 0.5° separately within each of the 14 GFED basis regions (region definitions only — no GFED burned-area data is used) and applied as a smooth 0.1° field; then a local history anchor that sets each 0.25° cell's level from its own 23-year record by credibility weighting (Gamma-Poisson posterior mean, prior weight chosen by a temporal holdout — calibrate 2001–2012, score 2013–2023 — and the log-ratio interpolated bilinearly so the anchor grid is not printed on the product); then the global level set to the 2014–2023 mean, the latest decade (3.64 Mkm²/yr against 4.03 for the full record). Held-out Poisson deviance 0.43 of the covariate-only baseline (0.1° prototype: 0.20).
- CC-BY fuel crosswalk v1.4. WorldCover 2021 × Köppen-Geiger → FM40, with Copernicus LC100 bare-cover fraction deciding burnable vs bare on sparse land (replaces climate-map stair-steps on desert margins), LC100 tree cover and Meta/WRI canopy height v2 for canopy structure. v1.4 splits Mediterranean-climate tree cover by canopy height (below 6 m SH5 chaparral, 6 m and above TU5 timber-understory) and moves tropical rainforest from TL9 to TL2 low-load timber litter. Cropland is burnable (GR2) and flagged as coverage 2.
- Surfaces. Susceptibility is the annual burn probability 1 − exp(−λ); classification is quintiles of λ over burnable pixels, globally and (classification_regional) within the pixel's fire region; uncertainty is a model-internal log-scale σ of λ (1.0 = unconstrained); exposure is the annual probability of a wildland fire within 2 km, defined on non-burnable land; coverage is 0 non-burnable / 1 wildland fuel / 2 cropland. Non-burnable land reads 0, never nodata.
- Validation. MODIS burned area is a calibration input at the 0.25° cell level, so agreement with it at that scale is not quoted as validation. The product is scored out of time on the MODIS record (2013–2023 holdout), within cells against MCD64A1 500 m burn counts, and against records independent of the anchor — MTBS, NBAC, EFFIS burnt areas 2016+, ESA Fire_cci — plus the USFS FSim burn-probability benchmark for the conterminous US. Results in model_card.md.
- Known limits. Spread simulated at 250 m (the campaign ran on the ~270 m v1.1 crosswalk; the 90 m structure comes from the strata, not from 90 m simulation); ERA5 fire-season climatology cannot resolve Santa Ana / Diablo / föhn events; MCD64 is a 500 m product that under-detects small fires, so prescribed, understory and agricultural burning are under-represented and low rates in those regimes are relative to MODIS-detectable burned area; the anchor adds no structure finer than 0.25°; no intensity or flame-length products in this vintage (horizon burn probabilities ship as the companion Returns line). See model_card.md.
- Versioning and annual refresh. v1.0 is a conventional product version — the first release of this model line. The next refresh is v1.1, or v2.0 if the method changes; the label is not a year and carries no data currency, so the currency is stated separately and prominently: burned-area record 2001–2023, global level 2014–2023, WorldCover 2021 fuel through crosswalk v1.4, Ignition Layer v0.3. The product is refreshed once a year, cut each spring once the previous year's monthly burned-area files are complete; an interim release may follow an exceptional fire season. The physics is held fixed between refreshes — only the burned-area history, the regional level and updated inputs move. Older releases remain available; pin one, and re-derive rather than rescale anything baked from it. Details in README.md → *Versioning and refresh*.
v1.1-xgb
2026-05
never shipped. Listed as pending while the global model was retrained; superseded by the physics-based simulation-emulation line, shipped as v1.0, before release.
- Machine-learning wildfire likelihood. Gradient-boosted trees (XGBoost) trained on satellite active-fire detections with spatially-blocked cross-validation and climate-envelope-matched negatives (hold-out AUC 0.94). Inputs include peak-fire-season NDVI, canopy height, dry-month count, lightning density, categorical land cover, roads, and a climate envelope. Ships with a bootstrap-ensemble uncertainty layer and coverage.
Returns
v1.0
2026-09
First shipped release of the wildfire Returns line; companion to Wildfire Surfaces v1.0 and built from the same annual burn rate.
- Horizon burn probability at 90 m. rp50 / rp100 / rp250 / rp500: P = 1 − (1 + λ/k)^(−k·T), a negative-binomial annual burn count with mean λ (the Surfaces rate, including its local history anchor to the MODIS record) and dispersion k fitted per GFED basis region × land-cover group from the year-to-year variance of NASA MODIS MCD64CMQ burned fraction, 2001–2023. Poisson limit where the record is under-dispersed.
- Semantics. Non-burnable land reads 0 at every horizon; horizons are monotone; ocean and Antarctica nodata. Not an intensity product — flame length / fireline intensity at return periods is a later line.
- Known limits. Stationary rate over the horizon; no fuel recovery; regional dispersion applied at pixel scale. Inherits every Surfaces limit.
- Versioning and annual refresh. v1.0 is a conventional product version — the first release of this model line; the next refresh is v1.1, or v2.0 if the method changes. A Returns release always pairs with the Surfaces release of the same label. The label is not a year, so data currency is stated separately: burned-area record 2001–2023, global level 2014–2023, dispersion from the same record, WorldCover 2021 fuel through crosswalk v1.4, Ignition Layer v0.3. One refresh a year against the burned-area record, an interim release after an exceptional season; the physics is held fixed between refreshes and the dispersion is refitted from the extended record. Older releases remain available — pin one. Details in README.md → *Versioning and refresh*.
Otros peligros
DeslizamientosAvalanchasTerremotosVendavalesCalor extremoFrío extremoHeladasRayosErosión del sueloHuracanesSequíaErupciones volcánicasTsunamiMarea meteorológicaGranizo