Figure 5 - uploaded by Paul W. H. Chung
Content may be subject to copyright.
Mutation operator. a) Chromosome before the mutation; b) Chromosome after the mutation (the mutation transforms a gene and its closest neighbours)
Source publication
This paper describes an artificial intelligence (AI) system for estuarine model design. It is created by the combination of case-based reasoning and genetic algorithm techniques. This application aims to make the utilisation of complicated and expensive hydrodynamic models flexible, cost-effective and accessible to non-specialists. By organising th...
Context in source publication
Context 1
... the next population. The present scheme also contains different forms of the more common random mutation and crossover. The traditional genetic operators are modified according to the previously made observation of adjacent genes. The mutation routine implemented here operates by randomly changing the value of a gene and its closest neighbours. (fig. 5). The crossover operation consists of an exchange between the segments of two chromosomes associated with specific estuarine areas ( fig. 6). The number of cut points can be more than one. At each crossover it is randomly chosen by the GA program, together with the segments that the chromosomes must reciprocate. b) The offspring ...
Similar publications
A three-dimensional baroclinic circulation model was implemented and applied to simulate the hydrodynamics in the Danshuei River estuarine system and its adjacent coastal sea. The model employs a semi-implicit finite-element Eulerian-Lagrangian (SELFE) algorithm to solve the shallow water equations. The entire domain is discretized in the horizonta...
Citations
Model calibration is an essential step in physical process modelling. This paper describes an approach for model calibration support that combines heuristics and optimisation methods. In our approach, knowledge-based techniques have been used to complement standard numerical modelling ones in order to help end-users of simulation codes. We have both identified the knowledge involved in the calibration task and developed a prototype for calibration support dedicated to river hydraulics. We intend to rely on a generic platform to implement artificial intelligence tools dedicated to this task.
