Machine Learning for Solar Resource Assessment Using Satellite Images
Understanding solar energy has become crucial for the development of modern societies. For this reason, significant effort has been placed on building models of solar resource assessment. Here, we analyzed satellite imagery and solar radiation data of three years (2012, 2013, and 2014) to build seve...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/11/3985 |
| _version_ | 1827665182061494272 |
|---|---|
| author | Luis Eduardo Ordoñez Palacios Víctor Bucheli Guerrero Hugo Ordoñez |
| author_facet | Luis Eduardo Ordoñez Palacios Víctor Bucheli Guerrero Hugo Ordoñez |
| author_sort | Luis Eduardo Ordoñez Palacios |
| collection | DOAJ |
| description | Understanding solar energy has become crucial for the development of modern societies. For this reason, significant effort has been placed on building models of solar resource assessment. Here, we analyzed satellite imagery and solar radiation data of three years (2012, 2013, and 2014) to build seven predictive models of the solar energy obtained at different altitudes above sea level. The performance of four machine learning algorithms was evaluated using four evaluation metrics, MBE, R<sup>2</sup>, RMSE, and MAPE. Random Forest showed the best performance in the model with data obtained at altitudes below 800 m.a.s.l. The results achieved by the algorithm were: 4.89, 0.82, 107.25, and 41.08%, respectively. In general, the differences in the results of the machine learning algorithms in the different models were not very significant; however, the results provide evidence showing that the estimation of solar radiation from satellite images anywhere on the planet is feasible. |
| first_indexed | 2024-03-10T01:21:49Z |
| format | Article |
| id | doaj.art-50c3a10ea1c64a7aa072047c2a67d7d8 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T01:21:49Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-50c3a10ea1c64a7aa072047c2a67d7d82023-11-23T13:58:23ZengMDPI AGEnergies1996-10732022-05-011511398510.3390/en15113985Machine Learning for Solar Resource Assessment Using Satellite ImagesLuis Eduardo Ordoñez Palacios0Víctor Bucheli Guerrero1Hugo Ordoñez2Escuela de Ingeniería de Sistemas y Computación (EISC), Facultad de Ingeniería, Universidad del Valle, Cali 760001, ColombiaEscuela de Ingeniería de Sistemas y Computación (EISC), Facultad de Ingeniería, Universidad del Valle, Cali 760001, ColombiaDepartamento de Sistemas, Facultad de Electrónica y Telecomunicaciones, Universidad del Cauca, Popayán 190001, ColombiaUnderstanding solar energy has become crucial for the development of modern societies. For this reason, significant effort has been placed on building models of solar resource assessment. Here, we analyzed satellite imagery and solar radiation data of three years (2012, 2013, and 2014) to build seven predictive models of the solar energy obtained at different altitudes above sea level. The performance of four machine learning algorithms was evaluated using four evaluation metrics, MBE, R<sup>2</sup>, RMSE, and MAPE. Random Forest showed the best performance in the model with data obtained at altitudes below 800 m.a.s.l. The results achieved by the algorithm were: 4.89, 0.82, 107.25, and 41.08%, respectively. In general, the differences in the results of the machine learning algorithms in the different models were not very significant; however, the results provide evidence showing that the estimation of solar radiation from satellite images anywhere on the planet is feasible.https://www.mdpi.com/1996-1073/15/11/3985satellite imagerymeteorological datarenewable energyphotovoltaic systemspredictive model |
| spellingShingle | Luis Eduardo Ordoñez Palacios Víctor Bucheli Guerrero Hugo Ordoñez Machine Learning for Solar Resource Assessment Using Satellite Images Energies satellite imagery meteorological data renewable energy photovoltaic systems predictive model |
| title | Machine Learning for Solar Resource Assessment Using Satellite Images |
| title_full | Machine Learning for Solar Resource Assessment Using Satellite Images |
| title_fullStr | Machine Learning for Solar Resource Assessment Using Satellite Images |
| title_full_unstemmed | Machine Learning for Solar Resource Assessment Using Satellite Images |
| title_short | Machine Learning for Solar Resource Assessment Using Satellite Images |
| title_sort | machine learning for solar resource assessment using satellite images |
| topic | satellite imagery meteorological data renewable energy photovoltaic systems predictive model |
| url | https://www.mdpi.com/1996-1073/15/11/3985 |
| work_keys_str_mv | AT luiseduardoordonezpalacios machinelearningforsolarresourceassessmentusingsatelliteimages AT victorbucheliguerrero machinelearningforsolarresourceassessmentusingsatelliteimages AT hugoordonez machinelearningforsolarresourceassessmentusingsatelliteimages |