A scalable digital twin employing machine-learning to discover actionable insights to reduce emissions/resource consumption utilising shared portside data. (Portunus)

我们消费的90%的东西都是海运的。然而，在数字化和发展颠覆性、数据驱动、实时分析以改善和简化运营方面，航运业仍然落后。航运业每年排放约9.4亿吨二氧化碳，至少占全球二氧化碳总排放量的2.5% （UKRI， 2021年）。港口在促进航运减排方面处于有利地位。**该项目将引入Portunus**，这是一个数字孪生，旨在通过跨港口的实时数据共享实现准时（JIT）到达，并优化港口资源（起重机/叉车/卡车等）。我们将利用机器学习模型并提供可操作的见解，利用共享的港口数据来减少排放/资源消耗。**环境影响—Portunus:***在船舶到达港口前至少12小时提供JIT信息，可以**减少4%的总行程排放**（国际海事组织，2022年）。** *船舶在港口内/附近每节省一小时，可减少总排放量**2%。2019年英国航运业排放量= 1430万吨二氧化碳当量/年。如果所有英国港口都采用Portunus， EA预计航运业的温室气体排放总量将减少约** 100万吨** **

90% of everything we consume is moved by sea. However, the shipping industry remains a laggard in terms of digitalisation and the development of disruptive, data-driven, real-time analytics to improve and streamline operations.The shipping industry is responsible for around 940mt of CO2 annually, at least 2.5% of the world's total CO2 emissions (UKRI, 2021).Ports are well-positioned to catalyse a reduction in shipping emissions.**This project will introduce Portunus**, a digital twin designed to enable just-in-time (JIT) arrivals through real-time data sharing across ports and optimize port resources (cranes/forklift/trucks etc.). We will utilise ML models and delivering actionable insights to reduce emissions/resource consumption utilising shared portside data.**Environmental impact -- Portunus:*** Information on JIT at least 12 hours before a vessel arrives at port can **reduce total journey emissions by 4%** (IMO,2022).* **2% reduction in total emissions** from a vessel for every hour saved in/around port.UK shipping emissions for 2019=14.3 MtCO2e/year. If all UK ports adopt Portunus, EA anticipate approximately **1 million tonnes reduction** **in total GHG emissions within shipping industry.**