Informed decisions through machine learning will keep it afloat & going

0
1523
File Photo

2020, a new year and this one brings along a sea change for those who deal with the sea business. Keeping in view the business as well as the environmental aspects, the authorities concerned, have rolled out several directions that the companies on and off-the shores need to follow.

Amidst the new rules and guidelines follow there are, of course, institutions’ growth targets. Recounting a few directions from the authorities concerned, with the Chief Operating Officer of Greensteam Learning Technology – Simon Whitford, here we have his insights on how is Greensteam taking up the challenges.

Simon Whitford, Chief Operating Officer of Greensteam Learning Technology (File Photo)

Recently, the UN announced that global GHG emissions must be reduced by 7.6% every year for the next decade. With regard to GreenSteam’s fuel saving figures, Mr Whitford talks about solutions they have and explains:

“GreenSteam’s ML platform calculates a 30% non-propulsion fuel use for an average non-optimised deep sea voyage. bad weather accounts for half of this fuel use (15%) and poor vessel optimisation makes up the rest (15%). Right now, GreenSteam has tools to measure and improve vessel optimisation. The 3 target areas for vessel optimisation are trim, speed and hull cleanliness. We have solutions for trim and hull cleanliness and we are beta testing a speed optimisation solution. That means we can address this 15% of fuel wastage.”

(Image Courtesy: GREENSTEAM)

To survive this period of upheaval and change in a sector already grappling with heightened security risks, recruitment challenges and rising operational costs, machine learning will be a vital tool in the arsenal of any shipping company, regardless of size, location, or mode of operation.

Embracing machine learning can no longer be regarded as a ‘nice-to-have’: in the post-2020 world, it is a Must-have.

Talking on the future strategies of the company, Mr Whitford says, “On our roadmap we will apply our decade in development ML platform to route. Let’s say this can help avoid 3% of poor weather losses. That would allow shipping companies to meaningfully address 18% of fuel use with our zero capex, zero down-time machine learning tools.”

From 2020, shipping companies operating outside emissions control areas (ECAs) have to meet tighter regulations in the shape of the well-documented global 0.50% sulphur cap. The IMO 2020 has brought the current sulphur limit outside ECAs down from 3.5%. Technology, machine learning – to be more specific, has the solutions.

Machine learning is an advanced form of artificial intelligence in which systems use powerful algorithms and logic to cut through the noise. By learning from experience, and by being able to identify patterns and discover trends, decisions can be made with minimal human involvement.

Mr Whitford , when asked about challenges replies with the term – “Not Exactly”. He chooses to put it very differently. He states: “There is an adoption period for the technology when the algorithm is learning about the ship and crew are learning about the technology. Legacy models have to discard 90% of (good) data to create their simple, shallow stereotype of each vessel. This creates a very poor image of the way the vessel will react in various conditions, and means they cannot measure fuel wastage with any accuracy, and forecasting performance is impossible.”

He adds – “The difficulty with machine learning is the initial 3 month learning period to capture the behaviour of the ship across a wide variety of operating conditions – but this is necessary to thoroughly understand how the individual vessel will operate, divide up the areas of fuel wastage and to enable speed, trim and fouling forecasts.”

(Image Courtesy: GREENSTEAM)

The era of the machines is finally in full swing. There is proof all over that machine learning models are highly adaptive. They are continuously revised and refined, becoming more accurate as new data enriches the dataset. Solutions based on machine learning enable businesses solve complex problems quickly, and much more effectively, than has been possible traditionally.

To sum it up, it’s all about improving efficiency to survive during and beyond rapid and deep change. By helping human experts to make better-informed decisions, accurate predictive automated modelling frees up the creative human for alternative tasks, which may include responding to emergencies or other unforeseen events.

Sea News Feature, January 13