Climate-decadal activity viability
Score how a spot's activity viability changes across the next 20–80 years under multiple climate scenarios. Backed by CMIP6 + CORDEX regional downscaling, bias-corrected per sub-spot when local outcomes are available.
Scale plan only. Three endpoints — single-spot single-decade granularity, portfolio across many spots + decades, and a narrative adaptation report for tourism-board / DMO clients.
What it does
For a given (spot × activity × scenario × decade), the engine runs an ensemble of bias-corrected CMIP6 model outputs through the same scoring curves as real-time. Returns: lower / mean / upper score bands, frequency of favorable-or-better days, dimension-level attribution (does the spot degrade because of wind shifts, water temperature, swell direction?).
POST /v1/projections
One spot, multiple scenarios, multiple decades.
{
"spot": {
"location": { lat: 36.013, lng: -5.604 },
"activity": "kitesurfing",
"spotId": "tarifa-balneario"
},
"scenarios": ["SSP2-4.5", "SSP5-8.5"],
"horizonDecades": ["2030s", "2050s", "2070s"]
}POST /v1/projections/portfolio
Same shape as single, but with an array of spots (up to 50). Use for "how does our 30-spot resort network look in 2050 under SSP3-7.0?". Heavy compute — typically 30-60s wall time; consider async + polling for big portfolios.
POST /v1/projections/adaptation-report
Combines portfolio projections with a qualitative narrative — identifies which dimensions are likely to be the binding constraint per spot (wind shift, water temperature, snow line moving up, precipitation regime change). Designed as input for a tourism-board adaptation plan deliverable.
Sub-spot bias correction
Raw CMIP6 is too coarse for spot-level scoring. The engine applies sub-spot bias correction when local observation history exists: Bayesian-shrunken multiplicative + additive offsets per variable, propagated through the projection. The resolvedSubSpotSlug in the response tells you whether bias correction was applied. Where there's no local data yet, the engine returns the raw projection plus an explicit wider-uncertainty signal in confidence.