 |
| Titel |
Artificial neuralnetworks forestimating the atmospheric pollutant sources |
| VerfasserIn |
Haroldo Fraga de Campos Velho, Fabiana Paes, Fernando M. Ramos |
| Konferenz |
EGU General Assembly 2011
|
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| Digitales Dokument |
PDF |
| Erschienen |
In: GRA - Volume 13 (2011) |
| Datensatznummer |
250052519
|
|
|
|
|
|
| Zusammenfassung |
| Abstract:
A relevant issue for atmospheric environment is the estimation of
the area source pollutant strength. This issue is considered as an
inverse problem in the atmospheric pollution dispersion. For the
inverse analysis, an area source domain is considered,where the
strengthof such area source term is unknown. The inverse problem
is solved by using a supervised artificial neural network: multi-layer
perceptron. The connection weights of the neural network are
computed from the delta rule (the learning process).
In our numerical experiments, the forward problem is adressed by
a source-receptor scheme, where a regressive Lagrangian model is
applied to compute the transition matrix.
The inverse problem methodology is tested with synthetic observational
data, from measurements points in the physical domain. |
|
|
|
|
|
|