Can a tyre recover once it is past the cliff?

Post-cliff tyre behaviour by compound: how often a worn tyre shows pace recovery when the driver backs off, and whether the wear is thermal (recoverable) or structural (not).

Once a tyre is past the degradation cliff, is it gone, or can the driver nurse some pace back by lifting off? The recovery forecast answers that by looking only at post-cliff laps and asking how often, and how strongly, a tyre shows a partial recovery and critically, whether the wear is thermal (surface, recoverable) or structural (bulk, not).

​

What it shows

The chart breaks post-cliff recovery into three signals per compound:

• Recovery rate (recovery_flag): the fraction of post-cliff laps where the driver’s next two laps were, on average, faster relative to the field than this one, by any margin. It runs at about 58–64% by compound. Pure lap-to-lap noise would put it near 50%, so it is a low bar.
• Average recovery probability: a fixed formula, not a fitted model: a logistic curve in the surface/bulk ratio (50% at a ratio of 0.5), shrunk the further past the cliff the lap is. The chart shows its average per compound.
• Surface/bulk ratio: how much of the recent push load is fresh (surface, ~3-lap memory) against longer-lived (bulk, ~5-lap memory), each scaled so a steady push reads 0.5. It tops out at about 0.61, when all the push came on the current lap. Below 0.35 the lap is labelled bulk-driven (compound breakdown, hard to recover); everything above is mixed. There is no surface-driven label: its old threshold (0.65) sat above the ratio’s ceiling and never fired.

Only post-cliff laps are included the feature is silent about pre-cliff behaviour, which the degradation timeline covers.

​

How to use it

1. Select a compound to see its post-cliff recovery profile.
2. Read the rate against 50%, not against 0%. A coin flip would score about 50%, so what a compound has is the margin above that. The average probability moves with the surface/bulk ratio by construction, so it restates the ratio rather than adding evidence.
3. Read the surface/bulk ratio to know why a tyre can or cannot recover: a low ratio means structural breakdown that lifting won’t fix.
4. Cross-reference a real stint in the pit strategy Gantt to see whether a driver who extended was riding recoverable thermal wear or terminal structural wear.

​

Reading the signal correctly

A recovery rate above 50% does not mean tyres bounce back to fresh pace. It means that slightly more often than not, the next two laps were a little quicker relative to the field than this one. The flag carries no magnitude, and the probability is a formula of the ratio, not a measured recovery.

Surface/bulk ratios near the 0.35 boundary are ambiguous: the same lap can read as thermal or structural across nearby laps. Treat the boundary as a soft transition, not a hard switch.

​

Data source

The chart queries int_tyre_surface_vs_bulk_decoupling via DuckDB-Wasm in the browser, using post-cliff laps only.

Column	Meaning
recovery_flag	Whether the next two laps’ average field-relative residual beat this lap’s
recovery_probability	Fixed-formula probability from the surface/bulk ratio and laps past the cliff, averaged per compound
surface_bulk_ratio	Surface share of the two push loads, each scaled by its weight sum: 0.5 at steady push, at most about 0.61

The data window covers 2018–2025, post-cliff laps only.

For the full model definition, see the int_tyre_surface_vs_bulk_decoupling reference.