ETA accuracy benchmark · 🇫🇷 Saint-Nazaire / Montoir

How Port Flow's predicted ETA compares to each vessel's own broadcast ETA at Saint-Nazaire / Montoir, measured on closed voyages over the last 90 days. We publish the number — good or bad. Lower error is better.

Port Flow predicted ETA (RMSE)

18.50 h

MAE 20.91 h · 382 voyages

Broadcast ETA (RMSE)

69.44 h

crew-declared, 230 voyages (same set)

Our advantage

73.4 %

lower error than the broadcast ETA

Broadcast ETAs more than 7 days from the actual arrival are excluded as AIS sentinel / placeholder values (111 excluded). Both figures are computed on the same remaining voyage set — apples to apples.

Closed voyages

error = predicted/broadcast minus actual arrival (hours)


228020700	container	08/26, 03:59 PM UTC	0.68 h	5.50 h
636025212	general-cargo	08/26, 11:02 AM UTC	0.07 h	-1177.04 h
228025700	container	08/26, 07:37 AM UTC	0.46 h	-1.37 h
304473000	container	08/26, 03:53 AM UTC	0.14 h	-1.89 h
250001723	container	08/26, 02:50 AM UTC	2.44 h	-20.85 h
255954000	product	08/26, 01:51 AM UTC	0.53 h	27.15 h
244909000	container	08/26, 12:46 AM UTC	-0.13 h	—
249435000	product	08/25, 10:07 PM UTC	2.11 h	-314.12 h
244909000	container	08/25, 08:12 PM UTC	-0.29 h	—
224876000	container	08/25, 07:56 PM UTC	0.08 h	-128.94 h
244909000	container	08/25, 05:29 PM UTC	-0.39 h	—
228024800	container	08/25, 03:55 PM UTC	1.46 h	3080.08 h
636021944	product	08/25, 02:10 PM UTC	-0.96 h	-144.18 h
244909000	container	08/25, 12:05 PM UTC	0.04 h	—
538006120	product	08/25, 03:22 AM UTC	3.25 h	-47.17 h
229767000	product	08/25, 01:18 AM UTC	-0.15 h	-3.31 h
255954000	chemical	08/24, 03:13 PM UTC	0.50 h	-2.72 h
256579000	general-cargo	08/24, 11:04 AM UTC	0.58 h	-0.07 h
304509000	container	08/24, 08:24 AM UTC	0.76 h	-3.92 h
266002000	product	08/24, 08:24 AM UTC	1.97 h	-464.39 h
228024800	container	08/23, 03:37 PM UTC	0.47 h	-144.88 h
538005645	product	08/23, 01:36 PM UTC	0.51 h	-11.60 h
255916071	container	08/23, 11:37 AM UTC	2.04 h	-112.62 h
226340000	product	08/23, 01:37 AM UTC	1.08 h	-183.62 h
218627000	general-cargo	08/22, 07:05 PM UTC	-0.17 h	-458.58 h
636026247	container	08/22, 05:24 PM UTC	0.60 h	-77.41 h
215994000	product	08/22, 02:42 PM UTC	-94.43 h	-116.70 h
227681520	product	08/22, 02:40 PM UTC	-104.78 h	-100.17 h
229632000	product	08/22, 02:40 PM UTC	-963.48 h	-919.67 h
228020700	container	08/22, 02:37 PM UTC	-739.54 h	-390.62 h
224876000	container	08/18, 07:55 PM UTC	0.44 h	-541.93 h
538007530	container	08/18, 07:48 PM UTC	1.05 h	-0.55 h
353539000	container	08/18, 06:36 PM UTC	1.74 h	-9.61 h
538005094	product	08/18, 05:35 PM UTC	2.12 h	-71.59 h
266457000	product	08/18, 03:34 PM UTC	-0.48 h	-620.57 h
256765000	product	08/18, 03:08 AM UTC	-0.34 h	-795.14 h
228024800	container	08/17, 09:28 PM UTC	0.64 h	-370.47 h
255916315	product	08/17, 09:12 PM UTC	-361.00 h	-358.21 h
226344000	product	08/17, 06:26 PM UTC	0.74 h	-464.44 h
215994000	product	08/17, 05:53 PM UTC	0.36 h	0.11 h
226340000	product	08/17, 01:37 PM UTC	3.04 h	-51.62 h
227681520	product	08/17, 12:57 PM UTC	-294.23 h	-290.96 h
249435000	product	08/17, 08:12 AM UTC	-373.85 h	-290.21 h
228084000	container	08/05, 05:03 AM UTC	0.78 h	-357.06 h
255915690	product	08/05, 02:11 AM UTC	0.76 h	-1750.19 h
226340000	product	08/04, 08:14 PM UTC	2.10 h	-85.75 h
256784000	product	08/04, 08:06 PM UTC	0.31 h	-1805.11 h
229259000	product	08/04, 07:46 PM UTC	-0.99 h	-29.77 h
227022600	container	08/03, 10:17 PM UTC	0.22 h	—
229447000	chemical	08/03, 07:24 PM UTC	0.32 h	—

See it on a live desk

Predicted ETAs, congestion and sanctions screening across 51 ports — try it in one click, no signup.

Open dashboard See pricing →

How it's measured

Predicted ETA: distance-to-berth over speed-made-good, refreshed on every AIS position, with a seasonal correction from rolling medians.
Broadcast ETA: the crew-entered ETA in the vessel's AIS message — the de-facto industry default.
Both are compared to the actual arrival timestamp on the same closed voyages. We report RMSE (penalises large misses) and MAE (typical error).
Broadcast ETAs more than 7 days off are dropped as AIS sentinel / placeholder values, and our model is scored on that same set — so the comparison is honest, not cherry-picked.
Coverage is public AIS only; ports with weak coverage show fewer closed voyages. We'd rather show a small honest sample than a big misleading one.