
Custom ocean
modeling
Reliable coastal forecasts for your operational decisions. We calibrate your models (WW3, CROCO) against in-situ measurements, document error by variable, and deliver actionable results.
Modeling, marine data analysis, and AI
Precise solutions for your coastal and offshore projects — from raw data to operational forecasting.
Modeling and calibration
Optimization of wave, current, and water-level forecasts. Statistical adjustment and improvement of existing coastal models.
Data analysis
Time-series studies, measurement quality control (QA/QC), advanced statistical analyses, and detection of extreme events.
Applied AI and expertise
Observation-model blending, hybrid AI + physics models, high-precision diagnostics, and custom scientific support.
Explore weather windows across 47 years of wind and waves
At a fictional site north of Roscoff, explore conditions month by month and adjust the thresholds. A separate replay at two points (Brest and site) screens historical hours in 2024, with a conventional 24-hour offset between phases.
Public ERA5 · Fictional site · Indicative analysis without local validationMetocean study — from 2 500 € excl. VAT
A quantified sea-state conditions analysis, based on ERA5 and GLORYS12: climatology, extreme values and operability. First deliverable within 5 working days.
Expertise in oceanography and data science
We turn oceanographic data into reliable forecasts through modeling, statistical analysis, and artificial intelligence. An approach that combines scientific rigor with operational solutions.
Bias and RMSE evaluation on significant wave height (Hs) after calibrating the model against an in-situ ADCP, on a client coastal campaign. The report is covered by a non-disclosure agreement; the method itself is reproducible. Models and forcings: CROCO and WW3 in production, NEMO, ECMWF (ERA5), GFS and AROME for forcing and data.
Climate Observer — live global temperature anomalies
Interactive globe and daily tracking of oceanic and continental temperature anomalies.
- NOAA OISST v2.1 (0.25°) & CPC anomalies reanalyzed (1991–2020)
- 9-day forecasts (Copernicus Marine GLO12 & ECMWF open data)
- Real-time El Niño / La Niña tracking (Niño 3.4 & ONI index)
- Polar sea ice monitoring (NSIDC) and coral reef bleaching (NOAA)
Sediment mobility atlas and optimal corridor
Pre-survey screening for cable layers: where the seabed moves, and where to route.
- Soulsby bottom-boundary physics, Shields threshold
- 500 m grid, 8,871 cells, 30 years (1993–2022)
- A* corridor and depth-of-lowering guidance
- Validated on 51 SHOM points and 908 dune crests
FNO surrogate — currents of the Brest roadstead
Emulating the currents of a high-resolution CROCO model with a neural operator.
- Fourier neural operator (2D FNO), autoregressive output
- CROCO ground truth, 250 m grid, multi-start windows
- Relative L2 evaluation over surface time windows
- Initial state supplied by the physical model; the emulator is not autonomous
SeaRoute-Py — weather routing
Vessel trajectory optimization via A* weighted by wind, waves and currents.
- Time, fuel or balanced cost profiles
- ETA validated on 800 real AIS voyages
- Gain concentrated in heavy seas (Hs 2–5 m)
- GeoJSON, GPX and KPI outputs (ETA, fuel, CO₂)
Blend AI — observation and model fusion
Calibrating model output against in-situ measurements.
- Observation quality control
- Analysis of model ↔ measurement gaps
- Model-to-measurement comparison for Hs
- Evaluation documented during extreme conditions
MeteoData Hub — unified metocean data access
Query ERA5, GLORYS12 and GFS without building the ingestion pipeline.
- A single interface for heterogeneous sources
- Extraction by point, by route or by bounding box
- Directly usable outputs (NetCDF, JSON)
- Product in beta, join the waiting list
Climate Observer — global ocean and land anomalies, day by day
Interactive 3D globe and daily tracking of oceanic and continental temperature anomalies: El Niño thermometer (Niño 3.4), polar sea ice (NSIDC), and coral bleaching alerts (NOAA Coral Reef Watch). Satellite observations from NOAA OISST, Copernicus Marine, and ECMWF reanalyzed.
Metocean AI Scoreboard — live AI vs physics comparison
Every day at 06:00 UTC, our AI post-processing model is evaluated against official physical forecasts (MFWAM, GFS, harmonic tides) across French Candhis wave buoys and SHOM tide gauges. Results are published live, including where AI does not beat physics.
Latest insights & case studies
Validation methods, metocean case studies and applied maritime algorithms.
Harmonic water-level baselines: a one-year fit window is exactly the wrong length
One year is not "a full cycle": it is the worst possible place to cut the fit window.
Why we will not publish a retro-routing gain percentage
+7.01 % to +4.57 % to +0.98 %: every methodological tightening ate into the gain. The "star vessel" was a grid artefact.
NetCDF or Zarr: chunking depends on the workload
The same ERA5 dataset, rechunked three times, produces three different winners depending on the read scenario.
MeteoData Hub — weather models, ready to use
Select a model, an area, variables and a format. Get a clean, documented and reproducible file, without downloading or decoding hundreds of GRIB files. GFS, ICON-EU and AROME, from GRIB2 to Zarr.
Let us discuss your coastal project
For any question or diagnostic request, write to us directly. Response within 48 hours.
Request a diagnostic
Describe your need, and we will get back to you quickly.
We respond within 48 business hours.
