Example exposure · north-pool portfolioExample

Winter quarter, tail view

Scenarios generated
5,000
Worst 1 % imbalance cost
illustrative
Main driver
storm cut-out ramps
Policy tested
Dispatra L0 rules v3
Suggested change
earlier position cut at gusts above 22 m/s
Stress test found two ramp patterns the current rules handle poorly.Deviation
Example. Values are illustrative.

Tempora · Stress-test

Price the storms you have not seen yet

Tempora generates rare weather your history does not contain, such as storms, ramps, icing and heat, then runs it through your forecasts and decisions to show the exposure.

Capabilities

What Tempora does

Synthetic extremes

Rare events, made plausible

Cosmos and Earth-2 world models generate extremes conditioned on each site's climate.

Exposure

Probability, severity, euros

Tail risk expressed as imbalance and curtailment cost, not only as weather statistics.

Stress tests

Test policies before the storm

Run Dispatra, Cellix and Fleetra rules through thousands of extremes.

Reports

For operators and insurers

Exposure analytics in a form risk teams and insurers can use.

Corpus

Rare data for every model

Generated extremes enrich the training data for the whole platform.

Early warning

Signals before regimes arrive

Flags when forecasts start to resemble a stressed scenario.

How it works

Inside Tempora

  1. Generate

    World models create extremes conditioned on location and climatology.

  2. Downscale

    Skycast's chain turns each scenario into asset-level power.

  3. Price

    Settlement rules turn power swings into imbalance and curtailment cost.

  4. Harden

    Policies are tested and adjusted where the tails hurt most.

Scenario library

Browse example extremes

Filter by event type. Each card is an illustrative scenario of the kind Tempora generates for a site.

Showing 8 of 8 example scenarios

North Sea storm with cut-outStorm

Winds pass cut-out speed across a coastal cluster and output collapses within two hours.

Return period
1 in 10 yr
Peak ramp
−85 % in 2 h
Morning front passageRamp

A cold front crosses a wind cluster earlier than the day-ahead forecast expected.

Return period
1 in 2 yr
Peak ramp
+60 % in 1 h
Rime icing at altitudeIcing

Freezing fog ices blades on a hill site for most of a day.

Return period
1 in 5 yr
Energy lost
−40 % for 18 h
Heat dome over solarHeat

High module temperatures and inverter derating cut midday output during a price spike.

Return period
1 in 10 yr
Peak loss
−18 % at noon
Winter wind lullLull

A cold, still, overcast week with low wind and solar across a region.

Return period
1 in 5 yr
Duration
6 days
Convective squall lineStorm

Fast-moving thunderstorms cause sharp swings across a solar and wind mix.

Return period
1 in 3 yr
Swing
±45 % in 30 min
Fog burn-off on solarRamp

Morning fog clears later than forecast and the solar ramp arrives two hours late.

Return period
1 in 1 yr
Delay
+2 h
Freezing rain on a coastal siteIcing

Freezing rain triggers ice-detection stops across a whole site.

Return period
1 in 8 yr
Stop time
11 h

Example scenarios with illustrative values. A real library is generated per asset and climatology.

Specification

Inputs, outputs and hardware

ItemDetail
InputsSite climatology, Skycast models, settlement rules, decision policies
OutputsScenario libraries, exposure curves, stress-test reports
GenerationCosmos and Earth-2 (CorrDiff) on DGX or HGX; GB200 at scale
ValidationPhysical plausibility checks; fully validated extremes are a later goal
StatisticsExtreme-value analysis on RAPIDS
DeliveryReports, API and Parquet exports

Questions

About Tempora

Are synthetic storms realistic?

They are generated to be physically plausible for each location and checked against historical extremes. We state the validation for every library and do not present them as observed events.

Can insurers use the reports?

Reports are designed to be shared with insurers and risk teams. They describe exposure; they are not an insurance product or an actuarial opinion.

Do we need Tempora to use the other products?

No. Tempora is an add-on. It is most useful once Skycast and Dispatra are running on your sites.

How many scenarios do you generate?

Thousands per site and season, so tail estimates rest on more than a handful of events.

See Tempora on your own sites

We start with a backtest on your history and show the result side by side with your current approach.