How DeepMap AI actually works.
No black boxes. This page walks through the full pipeline, from raw geophysical data ingestion, through the 18,000+-dimensional Earth State Tensor, to the ledger that pins every prediction to a tamper-evident hash chain. Our public 7-day earthquake watch uses how quakes cluster; the tensor and its classifiers are research, tested in the open.
The pipeline, end to end
Five stages, each built from public data + peer-reviewed physics.
Why we don't quote accuracy numbers
AUC translated for humans.
You may see AUC (Area Under the ROC Curve) in machine-learning papers: a standard score of how well a model ranks events above non-events, where 0.5 is a coin flip and 1.0 is perfect ranking. It is not an accuracy figure. We no longer quote AUC or hit-rate figures for our own classifiers.
Why not: most models in our saved-model population turned out to score well by construction rather than by skill, and a hit rate on wide forecast windows mostly measures coverage, not skill. A number that flatters a model is worse than no number.
The validation method is LOOCV (Leave-One-Out Cross-Validation), and in July 2026 we established that it flatters this particular model. We re-tested the per-region earthquake classifier with a temporal holdout, train only on earlier data, score only on later data, and its score fell to chance. The cause is that our tensor snapshots are 15 minutes apart while carrying a 7-day forward label, so a randomly held-out sample has near-identical neighbours sitting in the training set with the same label. Random folds cannot separate them; a temporal split can. We are publishing this because it is exactly the kind of thing a reader should not have to discover for us.
The flywheel
Why the models retrain every week.
Most ML systems ship once and decay. DeepMap AI is built as a flywheel: every confirmed outcome becomes a new labeled training sample, and the whole stack retrains on it.
Verification
Every claim on this site, reproducible.
Two ways to independently verify any number we publish:
sha256_hash. The chain itself is queryable at /api/v1/ledger/integrity. Any row rewrite would break every subsequent hash. Try it →
Scientific advisory panel
The people who keep us honest.
Independent domain experts who review our methods, challenge our claims, and hold the platform to discipline-standard rigor. Active recruitment of three founding advisors: seismology, isotope hydrology, and reinsurance quantitative risk.
Advisory compensation: modest equity grant (DeepMap AI Inc., Wyoming). Typical vest: 18-24 months with a 6-month cliff. No publication restrictions; we encourage advisors to publish their own reviews.
For scientists & researchers
Bring your own event, test the pipeline.
Create a free account to get programmatic access to the ledger, the tensor eigenmode stream, and the convergence-gate feed. Query historical predictions by region, by confidence, by hazard type. Reproduce our backtests against your own event list.
Free researcher account API docs