Waterway police use AI to detect undeclared dangerous goods
05 Jun 2024 10:02 Digitalization
The Hamburg Waterway Police has introduced a digital model that uses artificial intelligence (AI) to systematically detect undeclared dangerous goods. In doing so, the responsible authority is setting a milestone for more security in the port of Hamburg. The IT software company DAKOSY was responsible for the technical implementation. The project, which was supported by the InnoTecHH fund, was launched in January 2023 and went into regular operation at the end of April 2024.
The new digital application uses algorithms to generate recommendations for containers to be checked during import and export. Waterway police officers use the AI-generated recommendation lists to check the identified cargo units.
Lutz Dreyer, Head of Unit at the Waterway Police WSP 52, Central Dangerous Goods Monitoring Unit, explains the reasons for the digitalisation: "The checks were previously carried out manually and were only possible on a random basis due to the large number of containers." A specialist analysis in 2021 showed that the search for undeclared dangerous goods could be significantly improved and made more efficient by incorporating intelligent processes, particularly from the field of artificial intelligence (AI).
"We started the AI project at the beginning of 2023 with financial support from the InnoTecHH fund of the Hamburg Senate Chancellery and technical support from DAKOSY," says Dreyer. To be able to systematically identify undeclared dangerous goods, the authority first needed digital access to all export and import shipment information on the containers handled through the Port of Hamburg. This information is available in the Port Community System (PCS) operated by DAKOSY.
By the end of 2023, the import data had been integrated into the waterway police's digital dangerous goods information system (GEGIS), and by the end of April 2024, the export data from the PCS had been integrated and trained with an AI. "The shipments will be marked with a probability factor for undeclared dangerous goods and checked by us," explains Dreyer. Thilo Buchheister, who is leading the project for DAKOSY, adds: "We use a deep learning model for the automated, regular training procedures and can therefore also include new aspects, such as additional goods descriptions, in the analysis."
The basis for the AI project was the new version of the Hamburg Port Security Act. It authorises the Water Protection Authority to process cargo data to determine whether undeclared hazardous goods are being loaded or unloaded in transport units in the Port of Hamburg. Previously, the Water Protection Authority did not have the legal basis to systematically check containers that had not been declared as dangerous goods.
Olaf Hagenloch, Deputy Head of the Hamburg Waterway Police, recalls a tragic incident: "Many of us still remember the serious fire on a container ship in 2016, when the numerous emergency services spent several days trying to extinguish the fire on board. The cause of the fire was undeclared dangerous goods. This shows how important it is to declare dangerous goods for safe transport. Thanks to the AI support, my colleagues now have an innovative tool that significantly increases their own safety and that of the port as a whole. I am very grateful for this.
All in all, the newly created framework conditions and the innovative IT technology enable a new level of transparency for dangerous goods in day-to-day operations. Dreyer considers the project goal to have been achieved: "We have a continuously learning AI system in our GEGIS. This provides us with good suggestion lists that we can use to detect undeclared dangerous goods quickly and efficiently. With the help of the automated training runs, our database is continuously expanded and kept up to date.
About DAKOSY Datenkommunikationssystem AG
As one of the leading software houses for logistics, DAKOSY has been offering digital solutions for international freight forwarding, customs clearance and supply chain management for over 40 years. DAKOSY also operates the Port Community System (PCS) for the Port of Hamburg and the Cargo Community System (FAIR@Link) for the airports of Frankfurt and Hamburg. All companies and authorities involved in the export and import processes can use the digital platforms to handle their transport processes quickly and automatically.
In future, the Hamburg Waterway Police will be able to detect undeclared dangerous goods with the help of artificial intelligence.
