FIRMS

NASA’s near-real-time active fire detections used for operational wildfire monitoring and event labeling.

Overview

FIRMS distributes active fire and thermal anomaly detections derived from MODIS and VIIRS satellite sensors, with each record corresponding to a time-stamped hotspot observation.

PyHazards uses FIRMS as a wildfire occurrence signal for operational monitoring and label construction when combined with weather and land-surface context.

At a Glance

Provider

NASA LANCE / FIRMS

Hazard Family

Wildfire

Source Role

Active Fire Detections

Coverage

Global

Geometry

Event-based point detections

Spatial Resolution

~375 m for VIIRS, ~1 km for MODIS

Temporal Resolution

Event-based detections with multiple updates per day

Update Cadence

Fire maps refresh about every 5 minutes and downloadable files refresh about hourly

Period of Record

Near-real-time archive with later standard-science replacements

Formats

CSV, Shapefile, GeoJSON, KML

Inspection CLI

python -m pyhazards.datasets.firms.inspection --path /path/to/firms_data --max-items 10

Data Characteristics

  • Global event-based point detections rather than gridded tensors.

  • Latency is typically under 3 hours globally and faster for some U.S. and Canada products.

  • Common attributes include location, detection time, fire radiative power, and confidence indicators.

  • Near-real-time detections are later replaced by standard or science-quality products.

Typical Use Cases

  • Operational wildfire monitoring and early detection.

  • Event labeling for wildfire prediction pipelines.

  • Spatiotemporal analysis of fire occurrence and activity patterns.

Access

Use the links below to access the upstream source or its public documentation.

PyHazards Usage

Use this dataset through the public inspection or registry surface documented below.

This dataset is currently documented as an external or inspection-first source rather than a public load_dataset(...) entrypoint.

Inspection Workflow

Use the documented inspection path below to validate local files before training or analysis.

python -m pyhazards.datasets.firms.inspection --path /path/to/firms_data --max-items 10

  • Some archive and bulk-download routes require Earthdata login credentials.

Reference