New Tools to Support Just In Time Arrivals at Ports, Reducing Costs and GHG Emissions

Globally, 90% of everything we consume is moved by sea and the shipping industry emits around 1 billion tonnes of CO2 annually, representing about 3% of total emissions. The industry is under intense pressure to reduce emissions, but remains behind in the use of data-driven, real-time analytics to improve and streamline operations. The accurate allocation of resources at ports is a key requirement to improve this, with labour accounting for 60% of variable costs.

Port operations are undermined when there is a shortage of workers, leading to substantial delays in vessel loading and discharging operations, subsequently limiting the further supply chain. Better forecasting of port operations using data and statistics will give job allocation teams the information required to ensure that they are aware of future skill requirements and are able to maximise efficient resource utilisation. This approach will deliver faster ship turnaround times, minimise delays and deliver cost and energy reductions to reduce emissions from unnecessary fuel consumption, since ships cannot turn off power when in port.

The situation is compounded by most UK transport and logistics sectors not being digitally enabled and by difficulty in sourcing skilled staff. Labour shortages are projected to be a limiting factor in the productivity of UK ports in the years to come, so it is vitally important to improve efficiency in terms of the resources available. In the UK, the majority of port employees have said that they do not think maritime work pays enough, nor is it technologically/digitally advanced enough to attract people into the sector. Staff shortages reduce capacity and efficiency, resulting in delays at ports, exacerbating supply chain impacts. Ensemble's approach to solving these difficulties is to deliver accurate forecasting tools that can provide predictive systems for job allocations using data from scenario-based modelling. Currently, forecasting is cumbersome and lacks granularity, is slow and this results in a reactive rather than proactive approach to dealing with frequent changes in demand.

This project enhances Ensemble's Athena resource management system, which is currently being rolled out as part of an ongoing project, to utilise machine learning to analyse historical timesheet data. This will help to improve scheduling accuracy, improve job satisfaction and deliver better resource allocation. It will increase the effectiveness and functionality of our existing tools and accelerate the pace at which Athena can deliver fully effective predictive capability.