How accurate are these estimates?

Our independent, county-wide restoration estimates, graded against what actually happened. Unofficial — always follow your utility's guidance.

At a glance

Across 600 scored outages since Sep 30, 2026, median absolute error 1.6 h (56% within 2 h). For 68 time-matched cases, our median error was 2.6 h versus the utility's 1.2 h; ours was lower in 40% of them.

17,046

outages scored all-time

of 33,251 tracked (51%)

1.6 h

median absolute error

across the 600 most recent scored

2.2 h

first forecast error

made early in an outage (n=600)

0.9 h

final forecast error

made just before power returned

1.2 h

utility's own estimate

median error at the same readings (n=68); ours: 2.6 h

Every error figure is a median absolute error across outages — each outage is scored by the estimates published during it, and half of outages scored at or under the figure shown. The utility comparison is time-matched — both graded on the same readings against the same restoration.

How close: of the 600 most recent scored outages, 40% landed within 1 hour of the actual restoration, 56% within 2 hours, 73% within 4. Typical direction of the miss: 0.1 h early — we tend to call restoration sooner than it happens.

Utilities pushed their posted time back at least once in 54% of the 54 outages whose posted time we could follow outage by outage (median 2× when they did).

Median error by time into the outage: 2.1 h at 1 h in (n=549) · 2.4 h at 3 h in (n=373) · 2.5 h at 6 h in (n=218). Each figure is a different set of outages — only those that lasted at least that long — so read them as separate cohorts, not one outage sharpening over time (a survivor effect: longer outages dominate the later horizons).

Median error by outage size: 1.7 h for under 500 customers out (n=269) · 1.5 h for 500–2,000 customers out (n=235) · 1.8 h for 2,000–10,000 customers out (n=86) · 1.7 h for 10,000–50,000 customers out (n=10).

Data updated Oct 4, 8:02 AM EDT · methodology 2026-09-26.v3 · new events land ~3 h after restoration holds. Every statistic above except the all-time count is computed over the 600 most recently scored outages (about 3.5 days of outages) — the window the published ledger retains — not all 17,046. Each newly scored outage pushes the oldest one out, so these figures move with whatever storms those days held, and one large storm can dominate them. The gap between tracked and scored is outages where unscored events made no forecast — too small to publish an estimate for, or restored before one became dependable — so there is nothing to grade.

Related: how often utilities push back their posted restoration times — same ledger, utilities graded.

Method

While an outage is active, the model watches how many customers are out and how fast the number is falling, projects the rest of the recovery forward with the pace easing off as it drags on, since crews clear the easy faults first — and leans on weather and past outages in that area. Recalculated ~every 15 min; independent of the utility. When a utility also posts a time, both are shown, labeled separately.

How we grade

Typical error — each outage is scored by the median hours off across the estimates published during it, and the figure shown is the median of those scores. ±3 h means half of outages scored within 3 h of truth. Smaller is better.
"Restored" (what every grade is measured against) — the moment the county's reported outage count first fell to 10% of its peak or less. Every grade above (ours and the utility's) measures against that same moment — "time until most reported outages are restored", not the last single customer.
Bias — near zero means we don't systematically over- or under-promise.
First vs final — earliest estimate vs the last one before power returned; shows whether estimates sharpen.
Effective restoration — the target we grade against: the first reading at or below 10% of the peak (~90% recovered), not the literal last customer. Utilities' outage maps routinely leave stragglers for hours; the live label says "to restore" and grading uses this endpoint — stated here so the numbers can't quietly flatter us.

Only outages that have fully ended are graded, and we never score an estimate against another estimate. When an outage's recovery never settled, the site showed "no clear recovery yet" — a deliberate non-answer, so nothing to grade (that's why "scored" is smaller than "tracked").

Read these numbers with the following in mind

A rolling window — every figure except the all-time count covers only the most recently scored outages (the note under the numbers says how many, and how many days they span), so one large storm can swing them.
County-wide — estimates cover a whole county; your street can come back earlier or later.
Coverage depends on which utilities report into public sources; missing data is not zero outages.
Small outages excluded, not dressed up: counties under 5 customers out get no county-wide forecast, city and neighborhood estimates under 10 get none; very small outages are marked "too small to estimate" rather than scored.
How it works: the estimate follows the live recovery pace, slows its projection for the long tail of repairs, and can draw on past outages in the same area (method updated Jul 2026). Scoring is automatic.

How the error moved across the window

Error here is normalized by each outage's length — a 5-hour miss on a two-day outage isn't the same as on a five-hour one. Raw hours-of-error mostly tracks how severe that week's storms were, so this is the cleaner way to watch the estimator itself improve; the typical outage column shows whether a cohort was simply harder. Outages that lasted under an hour are left out of this table — dividing a miss by a very short outage would turn minutes into hundreds of percent and swamp the trend.

Prediction error by cohort of close date, normalized by outage length.
Cohort (by close date)	Outages	Error ÷ length	Median error	Typical outage
Earliest	193	20%	±1.3 h	~7 h
Middle	193	22%	±1.8 h	~7 h
Latest	195	24%	±1.7 h	~6 h

Roughly flat across the window. The window holds only the 600 most recently scored outages — about 3.5 days of them — so this compares the storms of those days, not the estimator over time; it cannot show a long-term trend.

What each number measures

What each number measures — the published definitions for this methodology version (2026-09-26.v3), quoted from the metric contract itself.

our median absolute error (whole event)

Median absolute error, in hours, of every estimate we published across a completed outage, against its observed effective restoration (count first at/below 10% of peak and holding). Median across events.

posted-time median absolute error (as recorded)

Median absolute error, in hours, of the posted restoration times we recorded — a restoration time carried by the national county feed (the only posted-time source the event series records) — over the readings where one was present while meaningfully out, against the same observed restoration. Median across those events. Events where the utility posted a time that never reached that feed are NOT counted.

our median absolute error on the same posted-time events

independentWholeEventMae restricted to the events counted by utilityPostedMae — same event population, whole-event alignment (not the same readings). It inherits that metric's posted-time source limitation exactly.

time-matched head-to-head (same readings)

Both graded at the identical readings where a recorded posted time — a restoration time carried by the national county feed (the only posted-time source the event series records) — AND our estimator both produced a value: the strictest like-for-like. Reported as a pair (posted vs ours) with its own n.

posted time moved later at least once

Share of events carrying a recorded posted time — a restoration time carried by the national county feed (the only posted-time source the event series records) — where an outage whose time had been the county's posted time then moved its own time later by >30 minutes at least once before the county's restoration (its count first at or below the restored level, the moment every error is graded against), while still out, measured from the time it had when first followed or at its last counted move, so small steps add up (a time withdrawn and posted again counts). A county's posted time is the earliest of its outages' times, so it also moves when the outage holding it is restored or another outage posts; those moves are NOT counted, and neither are earlier moves. The denominator is the events followed outage by outage from their start; events whose posted time never reached that feed, or whose moves could not be traced to one outage, are not in it.

average later revisions per posted-time event

Mean count, per event carrying a recorded posted time — a restoration time carried by the national county feed (the only posted-time source the event series records) — of >30-minute later moves an outage made to its own time after that time had been the county's posted time, counting 0 when none did, over the same events as utilityPushbackRate (moves measured the same way). Moves of the county's time from one outage to another are NOT counted.

Recent examples from the scored sample

The newest 10 scored events (most recent first — not a curated or representative sample); the aggregate statistics above cover the whole window. Records of individual outages and downloadable datasets aren't part of the public site; contact us about future API access.

The newest scored outage events, with our median prediction error and the utility's where one was posted.
County	Closed	Peak out	Restore took	Our error	Utility's error
San Luis Obispo, CA	2026-10-04	343	14 h	±7.7 h	—
Warren, MS	2026-10-04	597	10.8 h	±7.6 h	—
Hampton city, VA	2026-10-04	2,508	3.5 h	±1.8 h	—
Carroll, MD	2026-10-04	372	3.2 h	±1 h	—
Montgomery, OH	2026-10-04	492	17.5 h	±3.7 h	—
Delaware, PA	2026-10-04	219	7.5 h	±5.4 h	—
Wayne, MI	2026-10-04	395	62.5 h	±1.4 h	—
Cook, IL	2026-10-04	253	3.7 h	±0.8 h	—
Orleans, LA	2026-10-04	281	14 h	±4.6 h	—
Monmouth, NJ	2026-10-04	2,044	1.5 h	±1.5 h	—

Newest 10 of 600 scored. Error = median difference between predicted and actual hours-to-restore across the estimates published during that outage. "—" in the utility column means no official restoration time was posted.