Approximation of a marine ecosystem model by artificial neural networks. ETNA - Electronic Transactions on Numerical Analysis
Fiche du document
10 janvier 2022
- handle: 10670/1.mdz7rx
- issn: 1068-9613
- doi: 10.1553/etna_vol56s138
info:eu-repo/semantics/openAccess
Citer ce document
Markus Pfeil et al., « Approximation of a marine ecosystem model by artificial neural networks. ETNA - Electronic Transactions on Numerical Analysis », Elektronisches Publikationsportal der Österreichischen Akademie der Wissenschafte, ID : 10.1553/etna_vol56s138
Métriques
Partage / Export
Résumé
Marine ecosystem models are important to identify the processes that affect for example the global carbon cycle. Computation of an annually periodic solution (i.e., a steady annual cycle) for these models requires a high computational effort. To reduce this effort, we approximate an exemplary marine ecosystem model by different artificial neural networks (ANNs). We use a fully connected network (FCN), then apply the sparse evolutionary training (SET) procedure, and finally apply a genetic algorithm (GA) to optimize, inter alia, the network topology. With all three approaches, a direct approximation of the steady annual cycle is not sufficiently accurate. However, using the mass-corrected prediction of the ANN as initial concentration for additional model runs, the results are in very good agreement. In this way, we achieve a runtime reduction by about 15%. The results from the SET algorithm are comparable to those of the FCN. Further application of the GA may lead to an even higher reduction.