Reducing Offshore Logistics Emissions Through Artificial Intelligence

Abstract

Abstract This paper explores two case studies indicating how artificial intelligence can be used to automate, predict, and optimize the complexities within offshore logistics. It focuses on Offshore Supply Vessel (OSV) fleet management with multiple points of delivery, spread out across geographic locations, each location needing specific cargo items within a given time window. The study indicates how this can free up assets and reduce fuel consumption, ultimately driving cost reductions and enabling supply-chain efficiency by redeploying assets. The first use case shows the effect of applying these methods within a ‘greenfield’ environment. That is, we assume that our constraint parameters are generally flexible or, at least, can be modified by the operator within some reasonable bounds. For example, we might consider that a vessel can depart from a port any day of the week rather than be bound to a specific day, or that deliveries can happen at night and not only during the day. Thus, the first use case is answering the question "what would the efficiency gain be if we allow enough flexibility in our operations to adapt to the output of the model?" The second use case shows the effect of applying these methods with a ‘brownfield’ environment wherein our operational constraint parameters are not generally able to be modified to adapt to the model output. For example, we might have an assumption of the type that "port departures are only allowed on Thursdays." Thus, even if the model suggested that departing three days a week would lead to an optimal outcome, we would not allow ourselves to change from the set departure dates.