Multitask learning of environmental spatial data
Détails
ID Serval
serval:BIB_A718A88D7EA1
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Institution
Titre
Multitask learning of environmental spatial data
Titre de la conférence
International Congress on Environmental Modelling and Software: Managing resources of a limited planet, sixth biennial meeting, Leipzig, Germany
Organisation
International Environmental Modelling and Software Society
ISBN
978-88-9035-742-8
Statut éditorial
Publié
Date de publication
2012
Editeur⸱rice scientifique
Seppelt R., Voinov A.A., Lange S., Bankamp D.
Pages
1594-1602
Langue
anglais
Résumé
The present research deals with an application of artificial neural
networks for multitask learning from spatial environmental data.
The real case study (sediments contamination of Geneva Lake) consists
of 8 pollutants. There are different relationships between these
variables, from linear correlations to strong nonlinear dependencies.
The main idea is to construct a subsets of pollutants which can be
efficiently modeled together within the multitask framework. The
proposed two-step approach is based on: 1) the criterion of nonlinear
predictability of each variable ?k? by analyzing all possible models
composed from the rest of the variables by using a General Regression
Neural Network (GRNN) as a model; 2) a multitask learning of the
best model using multilayer perceptron and spatial predictions. The
results of the study are analyzed using both machine learning and
geostatistical tools.
networks for multitask learning from spatial environmental data.
The real case study (sediments contamination of Geneva Lake) consists
of 8 pollutants. There are different relationships between these
variables, from linear correlations to strong nonlinear dependencies.
The main idea is to construct a subsets of pollutants which can be
efficiently modeled together within the multitask framework. The
proposed two-step approach is based on: 1) the criterion of nonlinear
predictability of each variable ?k? by analyzing all possible models
composed from the rest of the variables by using a General Regression
Neural Network (GRNN) as a model; 2) a multitask learning of the
best model using multilayer perceptron and spatial predictions. The
results of the study are analyzed using both machine learning and
geostatistical tools.
Mots-clé
Machine learning algorithms, multitask learning, environmental multivariate, data, geostatistics
Création de la notice
25/11/2013 17:18
Dernière modification de la notice
20/08/2019 15:11
Données d'usage
