Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Multi-Objective Optimization Using Evolutionary Algorithms
Multi-Objective Optimization Using Evolutionary Algorithms
Diversity-Guided Evolutionary Algorithms
PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Building Blocks, Cohort Genetic Algorithms, and Hyperplane-Defined Functions
Evolutionary Computation
Environmental Modelling & Software
| Hi-index | 0.00 |
We employed genetic algorithms to investigate the relationship between stream topographies and their associated hyporheic residence time distributions. A hyporheic residence time is the time it takes a water particle to enter the sediments below a stream, travel through the sediment, and re-enter the surface water of the stream. This subsurface journey affects stream chemistry and water quality, and increased knowledge of this process could be helpful in addressing the environmental problems caused by excess nutrients and waterborne pollutants in riverine ecosystems. We used a multi-scale two-dimensional model, lightly adapted from three previous models, to calculate residence time distributions from system characteristics. Our primary goal is the investigation of the "RTD inverse problem" - discovering stream topographies that would generate a specified target residence time distribution (RTD). We used genetic algorithms to evolve the shape of stream topographies (represented by Fourier series) to discover shapes that yield RTDs that closely match the target RTD. Our contributions are: a) the specification of the RTD inverse problem, b) evidence that genetic algorithms provide an effective method for approaching this problem, and c) the discovery of some unanticipated patterns among the evolved topographies. This early work seems promising and should encourage further applications of evolutionary computing in this area, with eventual application to stream restoration projects.