Route and speed decision under weather-conditioned vessel behaviour.
P1-Maritimo is a physics-based voyage optimisation engine for container shipping. It identifies the admissible route-and-speed configuration that minimises fuel consumption while remaining within safety and schedule limits. The result is weather-conditioned routing decisions that translate directly into lower operating costs.
Observed across evaluated voyages in replay analysis
Blended across vessel classes at current fuel prices
Asia-Europe to Transatlantic
Across vessel classes and lane conditions
"A route that is shorter geometrically may be worse economically if environmental conditions are adverse. A route that is slightly longer or differently timed may reduce fuel burn materially. The optimisation problem is not shortest path. It is minimum-cost path under weather-conditioned vessel behaviour."
Acceptance corridor
Existing routing systems run one weather model across the corridor and accept its forecast at every point along the route. Maritimo treats each node of the corridor as a separate forecasting problem. A dedicated calibrator at each point learns the local bias structure of the upstream forecast relative to observed conditions and is refreshed hourly. The corridor is a composition of independently calibrated points, each with its own correction history.
The system recomposes itself every hour. Forecast precision at any given node is determined by that node's own observation history. Routing decisions are made over this point-wise calibrated field.
Weather-conditioned environmental modelling
Calibrated wind, wave, and ocean current fields from P1-Tempo, corrected for location-specific and lead-time-dependent biases before they reach the routing layer. Each node of the corridor is calibrated independently against its own observation history, refreshed hourly. The precision of environmental modelling sets the ceiling on achievable routing improvement.
Vessel performance modelling
Physics-based hydrodynamic resistance and propulsion models calibrated to individual vessels, not class averages. Outputs are fuel consumption per leg, conditioned on the vessel's own resistance curve and propulsion characteristics. Calibration is refreshed against observed performance data, narrowing the gap between modelled and realised burn.
Constrained route optimisation
Dynamic programming on a directed acyclic graph across all voyage legs simultaneously. Speed choices on each leg account for the full voyage ahead, producing a globally optimal speed profile rather than a sequence of local heuristics. Hard operational limits are enforced as boundary conditions, not soft penalties, so no recommended configuration violates them.
The corridor below is composed of independently calibrated points, each refreshed against the latest forecast issuance and the latest observation cycle. Wind, wave, and current values shown along the route are the post-calibration field, not the raw model output. Adverse conditions surfaced here are the conditions the optimisation layer is reasoning over, at the resolution the optimisation layer sees them.
Voyage replay
The sections below apply the system to voyages this fleet has already sailed. For each completed voyage, the system is run against the environmental forecasts and operational constraints applicable at the time of execution. The recommended route-and-speed configuration is compared to the route actually sailed. No retrospective information is used.
Routing economics
Select a fleet composition to see the projected annual saving across vessel classes. Figures are per-vessel and per-year, computed from the saving rate observed in the replay analysis for this fleet. Total fleet impact scales linearly with the number of vessels in each class.
Current operating baseline
The system operates on high-resolution global forecast data. Replay analysis demonstrates consistent fuel reduction across evaluated voyages under these conditions alone.
Current results are a baseline, not an upper bound. The system outperforms existing routing solutions on standard forecast inputs before any operational data integration.
Expansion with operational data
Integration with vessel-level data sources including onboard sensors, vessel-specific performance telemetry, and proprietary weather observations increases modelling precision and further improves routing outcomes.
Maritimo is the first full-stack Principia application, a domain-specific instantiation of the Intelligence OS architecture applied to maritime operations. Calibrated environmental intelligence from P1-Tempo feeds directly into the routing optimisation layer. The chain is explicit and quantifiable: forecast precision at the Tempo layer determines the quality of the field over which Maritimo optimises, which determines the speed and route choices on each leg, which determine the realised fuel outcome at the operational layer. Routing decisions are traceable to the forecast precision, vessel model, and constraint set that produced them.