Study examines impact of Noon Reports vs sensor data in analytics models

Maritime software company Nautilus Labs has released a White Paper comparing the impact of different data source inputs on simulation accuracy rates in performance and voyage optimisation models in the shipping sector.

The study evaluated data science metrics that measure the accuracy of simulations built with three types of data sets: models based on noon reports only; models based on high-frequency sensor data; and models based on a combination of a vessel’s noon reports combined with high-frequency sensor data from other similar vessels.

The paper found that, while simulations built on high-frequency sensor data yield the most accurate simulations, in situations where a vessel is not equipped with sensors, simulation accuracy can be significantly improved by feeding the underlying model with a combination of data from the vessel’s noon reports and sensor data from similar vessels. Models based only on noon reports yielded the least accurate predictions.

The research found that noon report data combined with data derived from similar vessels within Nautilus’s own data pool provided 62% of the benefits of high frequency data from the ship itself.

“While high-frequency sensors are the gold standard in data collection for seafaring vessels, the reality is that many fleets may not yet be fully equipped with sensors,” said Todd Sundsted, Chief Technology Officer (CTO) at Nautilus Labs.

“Being able to produce more accurate simulations even for vessels without sensors brings us much closer to achieving fleet-wide optimisation and efficiency rooted in machine learning-based simulations.”

Share this story

About the Author

Picture of Rob O'Dwyer
Rob O'Dwyer

Rob is Chief Network Officer and one of the founders of Smart Maritime Network. He also serves as Chairman of the Smart Maritime Council. Rob has worked in the maritime technology sector since 2005, managing editorial for a range of leading publications in the transport and logistics sector. Get in touch by email by clicking here, or on LinkedIn by clicking here.

Further Reading

News Archive