Two Geoscience Applications by Optimal Neural Network Architecture

Nowadays, artificial neural networks have been successfully applied on several research and application fields. An appropriate configuration for a neural network is a complex task, and it often requires the knowledge of an expert on the application. A technique for automatic configuration for a neur...

Full description

Saved in:
Bibliographic Details
Published in:Pure and applied geophysics 2020-06, Vol.177 (6), p.2663-2683
Main Authors: Anochi, Juliana Aparecida, Hernández Torres, Reynier, de Campos Velho, Haroldo Fraga
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Climate prediction
Computer architecture
Configurations
Data assimilation
Data collection
Earth and Environmental Science
Earth science
Earth Sciences
Genetic algorithms
Geophysics/Geodesy
Multiple objective analysis
Neural networks
Optimization
Particle collisions
Precipitation
Seasonal precipitation
Sorting algorithms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowadays, artificial neural networks have been successfully applied on several research and application fields. An appropriate configuration for a neural network is a complex task, and it often requires the knowledge of an expert on the application. A technique for automatic configuration for a neural network is formulated as an optimization problem. Two strategies are considered: a mono-objective minimization problem, using multi-particle collision algorithm (MPCA); and a multi-objective minimization problem addressed by the non-dominated sorting genetic algorithm (NSGA-II). The proposed optimization approaches were tested for two application in geosciences: data assimilation for wave evolution equation, and the mesoscale seasonal climate prediction for precipitation. Better results with automatic configuration were obtained for data assimilation than those obtained by network defined by an expert. For climate seasonal precipitation, automatic configuration presented better predictions were presented than ones carried out by an expert. For the worked examples, the NSGA-II presented a superior result for the worked experiments.
ISSN:0033-4553
1420-9136
DOI:10.1007/s00024-019-02386-y