Professional intelligent munitions assessment using 3D reconstructions and Bayesian Neural Networks


Decision-making during offshore explosive ordnance disposal (EOD) is a highly complex task that requires extensive knowledge on a multitude of types of munitions, numerous available clearance technologies and the surrounding marine environment.

The ProBaNNt (Professional intelligent munitions assessment using 3D reconstructions and Bayesian Neural Networks) project aims at improving decision-making capabilities on various levels and generating a comprehensive tool to support offshore EOD campaigns. The project integrates sustainable convergence, use and analysis of existing EOD data with new data acquisition techniques, such as 3D photogrammetry and ad-hoc assessment of sediment properties. All of this information will be integrated into an EOD decision-making software that uses Bayesian Neural Networks to propose the most viable clearance option for a given munitions item at a given location.

ProBaNNt will improve the planning of EOD campaigns, data acquisition and the decision-making process. The new approaches will make EOD safer, more reliable and objective for project owners to judge the undertaken action, for nature conservation authorities to understand the rationale behind the action and most importantly for the EOD experts themselves to select the best and safest action.

In order to achieve these ambitious targets a consortium of GEOMAR Helmholtz Centre for Ocean Research (project lead), SeaTerra GmbH, Institute of Oceanology of Polish Academy of Sciences (IO PAN) and G-tec SA has been formed. The project is funded for the duration from October 2021 until September 2024 through the MarTERA ERA-NET COFUND.

Find out more

Project Proposal

More information on ProBaNNt can be found in our project proposal