ORBISPECT

We publish skill, not promises.

Every Orbispect layer gets benchmarked against independent, in-situ national networks before it ships. The comparisons below are maintained continuously — they weren't produced once for a sales deck and then left to go stale. Where the model is weak, this page just says so.

STATUS · CLOSED BETA

The platform is in an intensive development and closed-beta phase. What follows are the protocols for how each layer gets validated against independent networks — published skill figures will follow once the beta completes. We're onboarding design partners now. Join the list below.

01 / ONGOING BENCHMARKS

Three instruments, three independent referees.

STUDY V-01GRAVIMETRY × BOREHOLES

Groundwater vs national well network

We compare downscaled satellite water-storage trends against geological-survey monitoring boreholes, across every district we score. Agreement has to be there before a Water Credit Score gets issued. Districts that fail the check get flagged instead of scored.

REFERENCENational geological survey borehole network
CADENCEre-run with every monthly gravimetry release
SAMPLE380 districts · continuous gravimetric record
FAILURE MODEdistrict flagged "insufficient agreement" — no score shipped
STUDY V-02REANALYSIS × MET STATIONS

Climate inputs vs national met stations

The gridded climate fields that feed every index are benchmarked against the national meteorological station network. Bias gets measured per region and season, documented, then corrected before any downstream model ever sees the data.

REFERENCENational met service synoptic stations
SCOPEtemperature, precipitation, reference evapotranspiration
SAMPLEdaily series, full national synoptic network, multi-decade
OUTPUTper-region bias tables, applied upstream of all indices
STUDY V-03FLOW MODEL × GAUGES

Streamflow vs national river gauges

Basin flow forecasts get verified against national hydrological gauge readings, river by river. So we publish skill per basin, and clients see exactly where the model is sharp and where a catchment just defeats it. Weak basins are labelled as such right in the product.

REFERENCENational hydrological service gauge network
GRANULARITYskill reported per basin, not as one flattering average
SAMPLEnational gauge network · daily flows · verified release by release
HONESTY RULEbasins below skill threshold ship with a "low confidence" label
02 / KNOWN LIMITS

What we are not yet good at.

// PUBLISHED LIMITATIONS — UPDATED QUARTERLY
  • Yield anomaly forecasting is in pilot. The AgroTransformer engine ships to design partners only, until out-of-sample skill clears our internal bar. We will publish the bar and the score.
  • Small, fragmented parcels below sensor resolution carry wider uncertainty — flagged per parcel, priced accordingly.
  • Mountain basins with sparse gauging defeat streamflow verification; those basins are labelled low-confidence in the product.
  • Sedimentation monitoring (HydroSed) is validated on a small set of reservoirs so far; coverage grows survey by survey.
03 / EARLY ACCESS

Join the closed beta.

Orbispect is onboarding design partners right now and building a waitlist for early access. Leave your work email and we'll reach out once the beta opens for your region. No sales deck.

See the methods behind our checks →