Narrow Product · Reactive narrow product

Per-Geyser Narrow Classifiers

Dedicated classifiers for individual named geysers (Steamboat, Daisy, Riverside, Beehive). 83-100% measured skill on small but real samples.

Headline metric
83-100%
measured per-geyser hit rate (small-n, real outcomes)
Status
LIVE
daily evening retrain from GeyserTimes
Designed for
YVO / NPS, tourism operators, Yellowstone researchers
Request engagement Methodology Verify on ledger ← All products

What it does

Individual classifiers trained per named geyser, each consuming the geyser's local FDSN tremor signature + basin-wide multi-physics context. Specific geysers (esp. Steamboat) have dramatically higher skill than the Old Faithful bulk classifier because their eruption sequences are more distinctive.

Physics basis

Each geyser has a distinctive pre-eruptive tremor signature, fluid-pressure cycle, and local ground-motion pattern. Dedicated classifiers on these narrow signals outperform any bulk model.

When it fires

Continuous; auto-train daily evening on GeyserTimes.

What the customer receives

  • Per-geyser eruption classification + lead-time prediction
  • Confidence + waveform excerpt per fire
  • Monthly skill summary per geyser

Operational numbers (live)

83.3% (n=6)
Steamboat
100% (n=2)
Daisy
100% (n=1)
Riverside
100% (n=1)
Beehive

Engagement paths

Per-query, subscription, territorial-exclusive, and royalty-on-find structures are all available. Specific commercial terms are scoped after a technical-fit conversation.

Honest caveats

  • Small-n: the 100% numbers reflect 1-2 matched eruptions; these are real but not yet statistically significant.
  • Skill is per-geyser; does not transfer automatically to a newly-monitored geyser without retraining.
  • Ground-truth denominator is GeyserTimes community observations; a missed user report becomes a missed classification.
Ready to talk?
Michael Jessop — michael@deepmapai.com · partner portal