Full Domain Analysis for Fluid Mechanics


Research project at a glance

Artificial intelligence methods can efficiently help us understand aftermath requirements, constraints, and decision-making processes at an early stage. Algorithms are typically used in late stages of engineering development projects. We want to reverse this and show engineers early on which types of solutions meet their requirements.

Funding type

Publicly funded research


01.09.2022 to 31.03.2024

Project manager at H-BRS

Project Description

The aim of the project is to apply AI-driven novel optimization algorithms and machine learning methods at different stages of decision-making processes in climate-adaptive urban design to model the late consequences of decisions. The algorithms are used to represent the variety of design and decision options in-silico and by example. Decisions are incorporated into the modeling - thus creating a toolset that accompanies the process. An open, free system is developed for the communication and decision-making processes of sustainable urban development where all stakeholders are involved and understand early in the construction project what impact requirements and constraints have on possible designs and can thus make more informed decisions. The system can be set up and extended with many climate adaptive factors.


Scarton, L., & Hagg, A. (2023). On the Suitability of Representations for Quality Diversity Optimization of Shapes. GECCO 2023 Lissabon.

Cooperation partners


Initial funding by Bonn-Rhein-Sieg University of Applied Sciences