Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

AI-driven probabilistic method for response-based design of rock armour slopes

Project description

AI-driven method for sustainable rock armour design

Storms and rising sea levels increasingly threaten coastal areas. To protect these shores, engineers typically build rubble-mound breakwaters, but these structures drain budgets and emit large amounts of CO2. Current design methods rely on overly conservative safety factors, which leads to overengineered structures and wasted resources. Supported by the Marie Skłodowska-Curie Actions programme, the PRO-ARMOUR project is developing an AI-driven approach to designing rock armour. The project uses Monte Carlo simulations and a 3D dataset to predict how designs perform under random wave conditions. The goal is to design an open-access Python tool to help engineers and policymakers cut costs, cut emissions, and boost sustainability. Ultimately, this will help strengthen coastal resilience and protect the environment.

Objective

Coastal regions are increasingly threatened by more severe and frequent storms and sea-level rise, which intensify erosion and flooding risks and endanger ports and coastal regions. To counter these hazards, rubble-mound breakwaters constructed with large quarry rocks are the most widely used protection structures worldwide. However, their construction demands vast material volumes, high financial costs, and generates significant CO2 emissions. Despite these investments, the hydraulic stability of armour units remains a critical challenge in design practice. Current methods largely rely on deterministic or semi-probabilistic approaches, applying conservative safety factors that ensure stability but result in overdesign, excessive rock consumption, and inflated carbon footprints. PRO-ARMOUR tackles this gap by delivering a new response-based AI-driven probabilistic method for rock armour design. The project combines advanced Level III Monte Carlo simulations, physics-informed AI-driven surrogate models, and a novel 3D experimental dataset to predict armour unit response under random waves and quantify uncertainty and failure probability with high accuracy. These advances will be translated into an open-access Python tool, providing engineers, contractors, and policymakers with transparent and practical tool for risk-informed design. By enabling cost-effective and climate-resilient solutions, PRO-ARMOUR will reduce armour use, construction costs, and CO2 emissions, directly supporting EU sustainability and adaptation goals. Hosted at TU Delft (Netherlands) with a secondment at the Polytechnic University of Bari (Italy), the fellowship merges world-leading expertise in probabilistic modelling, AI, breakwater engineering and experimental hydraulics. Beyond scientific innovation, I will foster societal impact by strengthening the resilience of vulnerable coastal communities, and economic and environmental impact through measurable savings and lower carbon footprints.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships

See all projects funded under this funding scheme

Call for proposal

(opens in new window) HORIZON-MSCA-2025-PF

See all projects funded under this call

Coordinator

TECHNISCHE UNIVERSITEIT DELFT
Net EU contribution
€ 217 076,16
Total cost
No data

Partners (1)