Changelog
Dataset updates, releases and significant changes
Updated
Apr 2026
2026
V1 platform launch — all four catalogs live
Initial public release of FuelMaps. Fuel Hazard (6 metrics), Fuel Load (GEDI L4A biomass), Fuel Type (NBIC ACS Stage 2 BFC) and Forest Metrics (6 layers) all available for 2017–2025 at 10m resolution.
All catalogs2017–202510m
Assumptions
Project-level assumptions and caveats
5 entries
GEDI footprint sampling is unbiased at 10m aggregation
Data
GEDI L4A footprints (~25m diameter) are assumed representative when aggregated to 10m. Slope >40° and canopy cover >95% cause under-sampling in tall dense forests.
Models developed for Victorian ecosystems
Scope
Current datasets cover Victoria and trained on Victorian ecosystems. Expansion to other regions may require training region specific models.
Known Issues
Active bugs, artifacts and limitations under investigation
4 open
Mask layer for water features
Medium
Review the masking rules behind this for areas in Wilsons Prom and along the Gippsland coastline.
Bark hazard scores in grasslands
Medium
Bark hazard scores in grasslands and farmland - mask to be developed, planned for v2.
Methodology
Data sources, modelling approach and processing pipeline
Reference doc
01 — Input data sources
GEDI spaceborne LiDAR (L2A, L4A)
Structural
NASA GEDI L2A height metrics and L4A aboveground biomass density. ~25m footprint from ISS orbit, non-contiguous sampling.
Field fuel assessments (DSE Report 82)
Labels
~8,000 ground-truth fuel hazard ratings from trained assessors using the DSE Overall Fuel Hazard Assessment Guide. VIC coverage.
02 — AlphaEarth embedding model
03 — Output processing & delivery
Cloud-Optimised GeoTIFF (COG)
Overviewed, tiled COGs in EPSG:3857. Tile size: 512×512px. COGS @ 20m resolution. Compression: Deflate. Hosted on Melbourne Research Cloud.
TiTiler dynamic tile service
Serves XYZ map tiles on demand with dynamic rescaling and colormap application. Point query endpoint for per-pixel hover readout.
04 — Validation
Decoding using randomforest models and cross validation.

Model evaluation using LiDAR as an independant measurement of forest extent and structure under development.