Perilyx AI Request a briefing
Technology

A simulation engine that models the chain, not just the event.

Perilyx's core is a set of GPU-accelerated neural PDE solvers trained to approximate the physical propagation of climate hazards through terrain, vegetation, hydrology, and built infrastructure — then to model how each hazard changes the conditions for the next one.

Core architecture

Three layers, one continuous state model.

Sensing layer

Continuous ingestion of satellite soil moisture and canopy density, utility grid telemetry, USGS stream gauges, and NOAA ensemble forecasts, resolved to parcel-level grids.

Simulation layer

Neural PDE solvers — trained against physical hazard-propagation equations, not just historical loss curves — model heat transfer, fuel combustion, saturation, and debris-flow dynamics.

State layer

A persistent per-parcel state vector tracks how each hazard event shifts underlying conditions, so cascade probability compounds correctly instead of resetting to a historical base rate.

Why not a historical loss model

Backward-looking models can't see a cascade they haven't priced before.

Actuarial loss tables are excellent at pricing events that look like the past. They structurally cannot anticipate a compound sequence — say, three consecutive wet-then-dry seasons priming a watershed for post-fire debris flow — because that exact sequence may never have appeared in the training window for that geography.

Capability Historical loss models Perilyx cascade engine
Prices known historical patternsYesYes
Models novel hazard sequencesLimitedYes
Tracks parcel-level physical state over timeNoYes
Forward lead time on compound eventsDays–weeksMonths–18mo
Portfolio correlation from shared cascade exposureNoYes
Delivery

API-first, built into how your team already works.

Cascade scores, lead-time windows, and confidence intervals are delivered by REST API or scheduled batch export, with pre-built connectors for common underwriting and GIS platforms.

Parcel Scoring API

Query cascade probability, expected severity, and forward lead time for any parcel or portfolio, refreshed nightly.

Portfolio Correlation Reports

Book-level exposure clustering by shared cascade pathway, delivered ahead of renewal cycles.

Want to see the model run on real terrain?

Our science team can walk your team through a live simulation on a region of your choosing.

Request a briefing