WLF · Machine learning

Wildfire

XGBoost · spatially blocked CV · envelope-matched negatives · hold-out AUC 0.94 · v1.1 · pending

preview pending

Preview ships when the v1.1 global retrain finishes

Machine-learning likelihood trained on satellite active-fire detections - vegetation, climate, and ignition drivers.

What ships

Surfaces — calibrated 0–1 probability per pixel, with bootstrap-ensemble uncertainty.

Every release: 0–1 score · 5-class band · per-pixel uncertainty · input-coverage mask · STAC item · methodology doc.

Inputs

NDVI peak-fire-season, canopy height, dry months, lightning density, landcover (categorical), roads, climate envelope

Validation

Spatially blocked hold-out AUC 0.94 — cross-validation blocks prevent leakage across nearby pixels.

Version history

What changed between releases — the same notes that ship with the data. Newest first.

v1.1

2026-05

global retrain in progress. The v1.1 global model is being retrained; the showcase preview and full global coverage publish once it completes.

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.