Americas News
Older Ships Can Still Access Data-driven Performance
A white paper from US-based marine technology firm Nautilus Labs has looked at three types of data collection for measuring ships' performance.
The simulations were based on three models: noon reports only, using high-frequency sensor data, and using a combination of a vessel's noon report with high-frequency sensor data taken from 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," Nautilus said.
According to the whiite paper, the second option -- combining noon reports with comparable ship-type data from the Nautilus data pool -- provided 62% of the benefits of high-frequency data while the predictive power of this option over the noon-only model increased by 33%.
As many ships do not yet have sensors, achieving greater accuracy without them brings ship operators "closer to achieving fleet-wide optimization and efficiency rooted in machine learning-based solutions", commented Nautilus executive Todd Sundsted.