mesopotamia-marshes
Two-epoch surface-water extent of the Mesopotamian Marshes of southern Iraq from Landsat NDWI. Drained by canal and embankment after 1991 to roughly a tenth of their former area, then partially re-flooded from 2003 onward — a loss and a deliberate restoration in the same bounding box.
- recipe
- Apache-2.0
- outputs
- CC-BY-4.0
The contract
Read from this recipe's own declarations — parameters:,
outputs:, requires:, and the ops its layers name. Not from its
style blocks and not from any benchmark: a colour ramp is not a contract, and a measured
run is evidence about one AOI rather than a domain.
Parameters
The legacy dialect has no typed parameter schema. Read the folia.yaml for what this recipe takes; nothing here can type-check it.
Outputs
| output | kind | layer | what it is |
|---|---|---|---|
water_baseline |
answer | answer/water-baseline |
Pre-drainage proxy open-water pixel count. |
water_recent |
answer | answer/water-recent |
Post-restoration proxy open-water pixel count. THE answer, read against the baseline. |
ndwi_change |
raster | compute/ndwi-change |
dNDWI raster, recent minus baseline (show-your-work). |
Capabilities it requires
The legacy dialect has no requires: block.
Where it runs
- Browser preview does not run here answer/water-baseline: layer type "answer" is not one folia-view parses; answer/water-recent: layer type "answer" is not one folia-view parses; compute/ndwi-baseline: depends on layer "source/ndwi-baseline-scenes", which cannot run here; and 7 more
- Local CLI (folia run) runs here runs locally through the legacy (no spec_version) parser
- Operated fleet (POST /plan, /run) runs here legacy dialect: a lock binds by the cut's layer names, not by digest
registry/recipes/mesopotamia-marshes/folia.yaml