A parallel methodology using radial basis functions versus machine learning approaches applied to environmental modelling
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/126168
Título: | A parallel methodology using radial basis functions versus machine learning approaches applied to environmental modelling |
---|---|
Autor/es: | Migallón, Violeta | Navarro-González, Francisco J. | Penadés Migallón, Héctor | Penadés, Jose | Villacampa, Yolanda |
Grupo/s de investigación o GITE: | Computación de Altas Prestaciones y Paralelismo (gCAPyP) | Modelización Matemática de Sistemas |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | Universidad de Alicante. Departamento de Matemática Aplicada |
Palabras clave: | Numerical modelling | Parallel programming | Radial basis function | Machine learning |
Fecha de publicación: | 10-ago-2022 |
Editor: | Elsevier |
Cita bibliográfica: | Journal of Computational Science. 2022, 63: 101817. https://doi.org/10.1016/j.jocs.2022.101817 |
Resumen: | Parallel nonlinear models using radial kernels on local mesh support have been designed and implemented for application to real-world problems. Although this recently developed approach reduces the memory requirements compared with other methodologies suggested over the last few years, its computational cost makes parallelisation necessary, especially for big datasets with many instances or attributes. In this work, several strategies for the parallelisation of this methodology are proposed and compared. The MPI communication protocol and the OpenMP application programming interface are used to implement the algorithm. The performance of this methodology is compared with various machine learning methods, with particular consideration of techniques using radial basis functions (RBF). Different methods are applied to model the daily maximum air temperature from real meteorological data collected from the Agroclimatic Station Network of the Phytosanitary Alert and Information Network of Andalusia, an autonomous community of southern Spain. The obtained goodness-of-fit measures illustrate the effectiveness of this nonlinear methodology, and its training process is shown to be simpler than those of other powerful machine learning methods. |
Patrocinador/es: | This research was supported by the Spanish Ministry of Science, Innovation and Universities Grant RTI2018-098156-B-C54, co-financed by the European Commission (FEDER funds), and by the University of Alicante. |
URI: | http://hdl.handle.net/10045/126168 |
ISSN: | 1877-7503 (Print) | 1877-7511 (Online) |
DOI: | 10.1016/j.jocs.2022.101817 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1016/j.jocs.2022.101817 |
Aparece en las colecciones: | INV - gCAPyP - Artículos de Revistas INV - MMS - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Migallon_etal_2022_JComputSci.pdf | 4,21 MB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons