isolation_forest_fire 5aad0a100366
Unsupervised anomaly detector for daily fire activity over the TerraSentinel study
regions. Trained with IsolationForest on 27 strictly causal
features — every rolling window ends at 1 preceding, so no feature can see the day it
scores.
Provenance
| Dataset commit | e9fdff66d92411a5bdafc476d33db2369d42c227 |
| Gold table | gold.gold_fire_anomalies |
| Rows | 1476 |
| Regions | greece_fire, iberia_fire |
| Date range | 2024-09-28 → 2026-10-05 |
| Reference rule | median/MAD z-score in gold.gold_fire_anomalies (is_anomaly, z >= 5) |
| Trained at | 2026-10-05T12:56:56.484055+00:00 |
| n_estimators | 300 |
| Contamination | 0.025 |
The dataset commit is the point of this table: it is what lets you answer "which data produced this model".
Evaluation
No labels exist, so accuracy and F1 are not reported — they would be fabricated. What was measured:
| Metric | Value |
|---|---|
| Flagged days (contamination budget) | 37.0000 |
| Mean detections, flagged slice | 2521.0000 |
| Mean detections, rest | 122.9402 |
| Ratio (separation) | 20.5059x |
| Agreement with the median/MAD rule | 0.3243 |
| Jaccard with the rule | 0.1967 |
| Score mass in the top slice | 0.0452 |
| Known-event regression | 1.0000 (6/6 documented events) |
Reference agreement. The comparator is gold_fire_anomalies.is_anomaly — the independent median/MAD rule (z ≥ 5) — not this model's own flags, so the numbers below can disagree and the model can be wrong. It flags 37 days, the rule flags 36, they share 12: precision 0.3243, reference recall 0.3333, Jaccard 0.1967.
Documented events used as a regression test
ml/validation/known_events.py holds real events with measured signatures. 3 of 6 were caught only by rank (below the serving threshold), which is reported rather than hidden:
- iberia_fire 2025-08-15..2025-08-17, peak 13,329 — caught by the serving threshold
- greece_fire 2025-08-12..2025-08-13, peak 2,005 — caught by rank only, below the serving threshold
- iberia_fire 2026-02-24..2026-02-27, peak 1,184 — caught by rank only, below the serving threshold
- iberia_fire 2026-07-03..2026-07-03, peak 2,238 — caught by the serving threshold
- greece_fire 2024-09-30..2024-09-30, peak 808 — caught by rank only, below the serving threshold
- iberia_fire 2025-07-26..2025-07-26, peak 172 — correctly not flagged (negative control)
Limitations
- 2 regions, 2024-09-28 → 2026-10-05. 1,476 training rows. This is a baseline, not a production dataset.
- No labels. Every number above is distributional or agreement-based. Nothing here is a precision or recall against truth.
- Instrument FRP is not comparable across sensors: MODIS mean FRP is ~100 MW where
VIIRS is ~15 MW for the same fires. The model consumes
frp_sumandfrp_per_detectionpooled across instruments, so intensity features carry an instrument-mix confound. - The percentile score is relative to the training distribution. A genuinely new regime (a year far outside the training range) will saturate the percentile.
Usage
from ml.bundle import load_bundle, score_to_percentile
bundle = load_bundle("path/or/hub/snapshot")
raw = -bundle.model.score_samples(X[bundle.feature_columns])
percentiles, comparable = score_to_percentile(bundle, raw)
Anomaly is percentile >= 0.9750.
Attribution
Fire detections: NASA FIRMS (MODIS and VIIRS active fire products). Sea-surface temperature precursor: NOAA OISST v2.1. Imagery (not used by this model, but by the pipeline): Copernicus Sentinel.