01
Acquire
Pull from the sources you choose — Sentinel-2, Sentinel-1 SAR, Landsat, SRTM, Copernicus DEM, OpenStreetMap, and more — in parallel, scoped to your area of interest and delivered as Cloud-Optimized GeoTIFFs.
Fabric Engine
The processing engine that ingests multi-source Earth observation (EO) data, harmonizes it to a common baseline, and produces analysis-ready outputs with a complete, auditable provenance record. Define a Pattern. Run it anywhere. Reproducible every time.
The problem
Sentinel-2 delivers 10-meter multispectral imagery across 13 bands. Landsat 9 uses a different band layout, different radiometric calibration, a 30-meter resolution, and a different temporal cadence. SRTM elevation data is 30-meter global coverage but requires reprojection to match. SAR backscatter from Sentinel-1 has no direct optical equivalent. OpenStreetMap vector features need spatial alignment before they can be used alongside any of these.
Every analysis project starts with the same labor: download, reproject, resample, align, correct, clip. Done manually this takes days.[1]USGS: The Value of Data Managementusgs.gov ↗ Done with one-off scripts it works once, then breaks silently when the upstream data format changes.
Fabric Engine encodes the harmonization knowledge as a repeatable pipeline. Define your study area and data sources in a Pattern. Engine resolves the cross-sensor inconsistencies, runs each step in isolation, and writes analysis-ready outputs with a full record of exactly what was processed, when, and how.
How it works
Pull from the sources you choose — Sentinel-2, Sentinel-1 SAR, Landsat, SRTM, Copernicus DEM, OpenStreetMap, and more — in parallel, scoped to your area of interest and delivered as Cloud-Optimized GeoTIFFs.
The hard part, automated. Engine clips, reprojects, resamples, and aligns every source so they share one projection, one grid, and one resolution — the step that otherwise eats days by hand and breaks silently in one-off scripts.
Run standard spectral indices, custom band math, multi-sensor harmonized analysis, SAR-based flood mapping, and summary statistics — composed into a single Pattern, with independent steps running concurrently.
Analysis-ready outputs in standard formats — Cloud-Optimized GeoTIFF (COG), GeoJSON, GeoPackage (GPKG), JSON reports — each run carrying a complete W3C PROV provenance record of what ran, on what data, in what order.
ARD guarantee
Analysis-Ready Data means every output from Fabric Engine meets the same guarantees before it leaves the pipeline: one consistent coordinate reference system, matching pixel dimensions and spatial extent across all sources, a consistent target resolution, proper NoData masking, and embedded geospatial metadata.
The Pattern definition is version-controllable, shareable, and portable across environments. Run the same Pattern six months later on new data and the output is structurally consistent with the original: same coordinate system, pixel dimensions, layer ordering, and metadata. Reproducibility is built into how Engine runs.
Every run produces a complete provenance record — the inputs, parameters, and processing steps behind the output. That record is what makes the result legally defensible and scientifically reproducible.
Pattern library
Snow extent mapping via NDSI, multi-year snow comparison, ice extent time series. Multi-season composites with automatic cloud-free scene selection.
NDVI time series, deforestation detection, crop health assessment, and fire scar mapping via dNBR. Built from standard indices and custom band math.
SAR flood extent mapping, water body detection via NDWI/MNDWI, pre/post flood comparison. SAR provides coverage when cloud cover limits optical data.
Urban growth detection via NDBI, construction site monitoring, impervious surface mapping, road network change detection. Combine optical imagery with OSM vector data.
Wildfire risk mapping, flood risk modelling using elevation and land cover data. Pre/post disaster change detection with dNBR and multi-source fusion.
Need a step the library doesn't ship yet? Engine is built to extend — bring your own processing logic and chain it into any Pattern, so a gap never blocks a workflow.
Built on Engine
Fabric Studio is the visual interface for building Patterns that Engine executes. Whether a Pattern is built manually in Studio or generated by Iris (in development), Engine runs it the same way. Harmonization, provenance, and the analysis-ready guarantees are Engine features. Everything above exposes them.
Explore Fabric Studio →Also in the platform
Iris Natural language intelligence layer