Abstract
Our work with TEN produced an ANN-based FOC prediction pipeline validated on real high-frequency vessel telemetry produced for a period of over four years. The work on voyage segmentation, drifting/canal/port removal, fuel type filtering produced a clean RPM signal and a strong data engineering moat.
"Turn raw vessel data into fuel intelligence that improves voyage, cost, and efficiency decisions."
The work in plain English
This paper is one piece of the verification chain behind the VF Engine. Every recommendation a fleet operator sees in production traces back to a body of work like this one — published, peer-reviewed where applicable, and signed by named authors who can be reached for follow-up.
The full technical paper, including figures, tables, and the methodological appendix, is available on request. We are happy to walk through the work with technical buyers, charter parties, and underwriters who want to verify what the system actually does.
Where this lives in the engine
The findings in this paper inform fuel oil consumption prediction decisions inside the routing pipeline. For the full picture of how data flows from sensor to bridge, see The VF Engine. For verified outcomes built on this methodology, see Case Studies.