This is a project which is currently making use of HPC facilities at Newcastle University. It is active.
For further information about this project, please contact:
This project uses high-performance computing to develop a multi-objective optimisation framework for identifying Pareto-optimal Nature-based Solution (NbS) strategies on a catchment.
Within the framework, NbS interventions are modelled and encoded into a genetic algorithm. Populations of different spatial and intervention parameters are input into SHETRAN's directory and the hydrological performance is evaluated. Populations are ranked by fitness for multiple objectives, then a subset is retained and modified for the next generation. This algorithm runs until a termination criterion (either early stopping: hypervolume convergence or max: N runs).
The Pareto-optimal solutions are saved and visualised on a performance space scatter plot. Each individual strategy (and corresponding placement of interventions) may also be visualised.