Multitask learning of environmental spatial data
Details
Serval ID
serval:BIB_A718A88D7EA1
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
Multitask learning of environmental spatial data
Title of the conference
International Congress on Environmental Modelling and Software: Managing resources of a limited planet, sixth biennial meeting, Leipzig, Germany
Organization
International Environmental Modelling and Software Society
ISBN
978-88-9035-742-8
Publication state
Published
Issued date
2012
Editor
Seppelt R., Voinov A.A., Lange S., Bankamp D.
Pages
1594-1602
Language
english
Abstract
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.
Keywords
Machine learning algorithms, multitask learning, environmental multivariate, data, geostatistics
Create date
25/11/2013 17:18
Last modification date
20/08/2019 15:11
Usage data
