Comparison of Kernel Functions in the Classification of Irradiance Zones from Multispectral Satellite Images

Authors

DOI:

https://doi.org/10.19053/01211129.v30.n58.2021.13845

Keywords:

Kernel functions, multispectral satellite images, Landsat, Support Vector Machines, Classification, photovoltaic energy

Abstract

Due to the growing energy demand and the eminent global warming, there is special interest in the prediction of irradiance based on the reflectance obtained from satellites such as NASA Landsat, since it allows to know where it is more efficient to place photovoltaic receivers. Although there are studies for obtaining regression models with alternative Kernel functions, their performance for classification models is unknown and it is here where this research focuses. The study couples alternative Kernel functions to the support vector machines (SVM) algorithm for classification problems, where the best configuration for these algorithms is explored to finally obtain a set of irradiance maps zoned by class.

Downloads

Download data is not yet available.

Author Biographies

Dalila-Mercedes Pachajoa, Universidad de Nariño

Roles: Formal Analysis, Data Preprocessing, Research, Methodology, Software, Validation, Visualization, Writing-Original Draft, Writing-Revision and Editing.

Héctor Mora-Paz, Universidad CESMAG

Roles: Formal Analysis, Data Preprocessing, Research, Methodology, Software, Validation, Visualization, Writing-Original Draft, Writing-Revision and Editing.

Dagoberto Mayorca-Torres, Universidad Mariana

Roles: Conceptualization, Methodology, Validation, Writing-Original Draft, Writing-Revision and Editing.

References

M. Zorzi, A. Chiuso, "The harmonic analysis of kernel functions" Automatic, vol. 94, pp. 125-137, 2018. https://doi.org/10.1016/j.automatica.2018.04.015 DOI: https://doi.org/10.1016/j.automatica.2018.04.015

L. A. Belanche Muñoz, "Developments in kernel design", UPCommons, pp. 369-378, 2013. https://upcommons.upc.edu/handle/2117/23278

C. Spiegeler, J. I. Cifuentes, Definition and information on renewable energies, Grade Thesis, Universidad de San Carlos de Guatemala, Guatemala, 2016

J. Gómez Ramírez, Photovoltaic solar energy in Colombia: potentials, antecedents and perspectives, Grade Thesis, Universidad Santo Tomás, Bogotá D.C., Colombia, 2018. https://repository.usta.edu.co/handle/11634/10312

Unidad de Planeación Minero Energética, Integración de las energías renovables no convencionales en Colombia, Bogotá D.C., Colombia, 2015

O. E. Cabrera Rosero, A. D. Pantoja Bucheli, " Analysis of the wind resource using R in non-interconnected zones (ZNI) of the department of Nariño (Colombia)," in Latin American Conference on the Use of R in Research + Development, 2018. http://sedici.unlp.edu.ar/handle/10915/72585

H. A. Mora-Paz, Comparison of kernels on prediction of supply of alternative energy sources, Master Thesis, Universidad Internacional de la Rioja, Logroño, Spain, 2021. https://reunir.unir.net/handle/123456789/10020

O. Cabrera, B. Champutiz, A. Calderon, A. Pantoja, "Landsat and MODIS satellite image processing for solar irradiance estimation in the department of Narino-Colombia," in XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA), 2016, pp. 1-6. https://doi.org/10.1109/STSIVA.2016.7743306 DOI: https://doi.org/10.1109/STSIVA.2016.7743306

S. H. Monger, E. R. Morgan, A. R. Dyreson, T. L. Acker, "Applying the kriging method to predicting irradiance variability at a potential PV power plant", Renewable Energy, vol. 86, pp. 602-610, 2016. https://doi.org/10.1016/j.renene.2015.08.058 DOI: https://doi.org/10.1016/j.renene.2015.08.058

Downloads

Published

2021-12-20
Metrics
Views/Downloads
  • Abstract
    234
  • PDF
    132
  • XML
    29

How to Cite

Pachajoa, D-M, Mora-Paz, H, & Mayorca-Torres, D. (2021). Comparison of Kernel Functions in the Classification of Irradiance Zones from Multispectral Satellite Images. Revista Facultad de Ingeniería, 30(58), e13845. https://doi.org/10.19053/01211129.v30.n58.2021.13845