Operational efficiency #2: route optimization 1.2 1.3Route optimization refers to the strategic planning and management of routes to enhance efficiency and effectiveness in logistics operations. Inefficient miles can result in higher fuel use, more vehicle wear and greater labour costs. Freight logistics operators that have optimized their routes have seen a reduction in their carbon footprints.13 To put the potential impact into perspective, if route optimization tools were deployed at full-scale across road freight transport globally, the emissions reduction impact could be equivalent to taking approximately 25% of all heavy- and medium-duty trucks in the US off the road.14 Furthermore, it can play a critical role in supporting the deployment of zero-emission trucks (ZETs). By ensuring strategic route planning, operators can overcome infrastructure limitations and maximize the operational efficiency of ZETs, accelerating the transition to sustainable freight transport. Route optimization in the context of this section entails day-to-day dynamic routing, rather than network optimization that may require infrastructure investments and which is reflected in the other themes in this paper. While route optimization is not new, the rise of AI and ML in the past five years has revolutionized this field. AI-driven systems use real-time data and sophisticated algorithms to dynamically adjust routes for maximum efficiency and sustainability. They gather data from GPS devices, traffic systems, weather forecasts and historical route performance. Today, freight logistics companies often invest in route optimization tools as add-ons to their existing transportation management system platforms – something many were reluctant to do not long ago. Notable examples of route optimization leading to reductions in fuel consumption and emissions include Alaska Airlines and DHL Express (see Box 1). Such AI-enabled route optimization solutions are available, relatively easy to implement and can have high impact, making this area a potential priority for transport companies. Alaska Airlines and DHL Express use AI to optimize routes BOX 1 Over the last four years, Alaska Airlines, in partnership with Airspace Intelligence, has used an AI-based routing system, Flyways AI, that dynamically adjusts flight paths based on real- time data such as current weather conditions, airspace congestion and route efficiency across the fleet, leading to fuel savings of 3-5% for flights longer than four hours.15 The AI-based system ingests millions of real-time data points to predict future scenarios and deliver what it calculates as the safest and most efficient flight path. Similarly, Greenplan, a DHL Express funded start-up, developed an AI-based route optimization tool which can achieve up to 20% in fuel cost savings while using 70% less computing time than standard routing tools.16 Operational efficiency #3: driver behaviour AI-powered route optimization can reduce inefficiencies in real time, significantly unlocking opportunities to reduce carbon emissions. Alex Nederlof, Director of Engineering, Flexport Driving styles significantly impact fuel consumption and emissions across all transportation modes, in particular the road sector (e.g. aggressive acceleration and braking) and maritime shipping sector (e.g. “sail fast then wait”). In trucking, such driving behaviour increases emissions by up to 23%.17 AI could help to address this problem by leveraging real-time data from on-board sensors and machine learning algorithms to monitor driving behaviour and idling, alongside external factors such as traffic, weather and road conditions. These inputs could enable the system to identify inefficiencies and provide drivers with real-time feedback to optimize their driving and reduce fuel consumption. Over time, AI could refine its recommendations by learning from both historical and real-time data, improving accuracy and effectiveness. In addition to influencing driver behaviour, AI brings greater precision to the monitoring of vehicle health (e.g. tyre pressure, engine temperature), allowing it to alert drivers to potential issues that could lead to breakdowns or fuel inefficiencies. However, while AI can provide access to information, it would require a behavioural shift in organizational culture and ways of operating to fully capture potential gains. As autonomous technologies advance, these suggestions could be implemented in real time, leading to a more fuel-efficient future. Intelligent Transport, Greener Future: AI as a Catalyst to Decarbonize Global Logistics 12

Intelligent Transport Greener Future 2025