mcp · Global

aihydro-watershed

library to do watershed level analysis/dilineation globally

Feature or claim this listing

Represent aihydro-watershed? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Data offered docs-verified: watershed delineation from a USGS gauge or global lat/lon pour point · geomorphic parameters (28 indices) · topographic wetness index · curve number event runoff (SCS-CN, TR-55) · RUSLE erosion · SSURGO soil attributes in CONUS (gNATSGO, Soil Data Access); POLARIS/SoilGrids elsewhere · baseflow index (Lyne-Hollick) · flow-duration curve · flood frequency (Gumbel/GEV) · drought indices (SPI, SPEI, Palmer)
Coverage docs-verified: Global (any point on Earth; NLDI and small_catchment tiers are CONUS only)
Resolution docs-verified: Varies by tier: MERIT-Hydro about 90 m; USGS 3DEP 10 m bare-earth DEM for small catchments; NLDI uses NHDPlus catchments
Formats docs-verified: Python API (typed HydroResult) · GeoJSON
Access docs-verified: Open source under Apache 2.0 licence per docs badge (catalogue licence field says 'Other'); no authentication in catalogue metadata; some delineation tiers call external services (USGS NLDI, Google Earth Engine, USGS 3DEP)

Use cases llm-inferred: Drainage area for road culvert sizing at CONUS sites under about 5 km2 (small_catchment tier) · Catchment area and geomorphic attributes for a flood risk assessment at an ungauged pour point · Baseline flow-duration and flood frequency analysis for a delineated basin
Audience llm-inferred: hydrologists · flood consultants · drainage engineers · GIS analysts

Constraints docs-verified: Flood-inundation suite is not part of this package · NLDI and small_catchment tiers are CONUS only · v0.1.0 release, early-stage package · Small_catchment tier matched engineer-computed areas within a factor of 2 at 76 % of sites in one Indiana study (67 culverts) · Results under 0.05 km2 are often roadside-ditch snaps (flagged LIKELY_DITCH_SNAP) · USGS StreamStats not used as a tier because its old API is retired · On Python 3.13 the analysis extra omits xrspatial, so TWI needs the analysis-legacy extra on 3.10-3.12 · Licence mismatch: docs state Apache 2.0 but catalogue metadata says Other · Tool names in catalogue metadata (merit, characterize, signatures) do not match the documented Python API

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 16/10/2026 · daily-2026-10-15 (github-search)