Aplicación de un modelo de red neuronal para la clasificación de sistemas lacunares pampeanos

Biología Acuática

View Publication Info
 
 
Field Value
 
Title Aplicación de un modelo de red neuronal para la clasificación de sistemas lacunares pampeanos
 
Creator Ferrati, Roxana
Vargas Russo, M.
Saavedra, P.
Canziani, Graciela
 
Subject artificial neural network
trophic chain
satellite images
lagos
redes neuronales
cadenas tróficas
imágenes satelitales
 
Description The pampean shallow lakes present different distributions in their trophic chains, the latter being cause and consequence of the state of the lacunar systems. In order to determine how each of the measured variables —climatic, edaphic, morphometric, physicochemical and biological— in contributes to the general state of the lake, an Artificial Neural Network (ANN) model is built. The ANN is capable of processing a large number of variables and returning a classification that will allow determining it’s the trophic state. The information from satellite images is one of the input variables. Hence, on a first stage, the construction of a ANN model is intended to obtain a weight for each one of the visible specter bands and near infrared bands from LANDSAT and to pick the most representative value that the image returns. This value will be used as input to the ANN that will be then trained to return a classification of the shallow lakes according to the three observed patterns in the relation between phytoplankton, zooplankton, fish and their link with to nutrient abundance and watershed management.
The pampean shallow lakes present different distributions in their trophic chains, the latter being cause and consequence of the state of the lacunar systems. In order to determine how each of the measured variables —climatic, edaphic, morphometric, physicochemical and biological— in contributes to the general state of the lake, an Artificial Neural Network (ANN) model is built. The ANN is capable of processing a large number of variables and returning a classification that will allow determining it’s the trophic state. The information from satellite images is one of the input variables. Hence, on a first stage, the construction of a ANN model is intended to obtain a weight for each one of the visible specter bands and near infrared bands from LANDSAT and to pick the most representative value that the image returns. This value will be used as input to the ANN that will be then trained to return a classification of the shallow lakes according to the three observed patterns in the relation between phytoplankton, zooplankton, fish and their link with to nutrient abundance and watershed management.
 
Publisher Instituto de Limnología "Raúl A. Ringuelet", Facultad de Ciencias Naturales y Museo (UNLP)
 
Date 2005-11-30
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
 
Identifier https://revistas.unlp.edu.ar/bacuatica/article/view/6826
 
Source Biología Acuática; Núm. 22 (2005): Trabajos completos del III Congreso de Ecología y Manejo de Ecosistemas Acuáticos Pampeanos (EMEAP); 111-117
Biología Acuática; No 22 (2005): Trabajos completos del III Congreso de Ecología y Manejo de Ecosistemas Acuáticos Pampeanos (EMEAP); 111-117
Biología Acuática; No 22 (2005): Trabajos completos del III Congreso de Ecología y Manejo de Ecosistemas Acuáticos Pampeanos (EMEAP); 111-117
Biología Acuática; n. 22 (2005): Trabajos completos del III Congreso de Ecología y Manejo de Ecosistemas Acuáticos Pampeanos (EMEAP); 111-117
1668-4869
 
Language spa
 
Relation https://revistas.unlp.edu.ar/bacuatica/article/view/6826/5784
 
Rights https://creativecommons.org/licenses/by-nc-sa/4.0
 

Contact Us

The PKP Index is an initiative of the Public Knowledge Project.

For PKP Publishing Services please use the PKP|PS contact form.

For support with PKP software we encourage users to consult our wiki for documentation and search our support forums.

For any other correspondence feel free to contact us using the PKP contact form.

Find Us

Twitter

Copyright © 2015-2018 Simon Fraser University Library