Machine learning methods

We are developing and applying different Machine Learning techniques to extract information from the climatological and meteorological databases. The main tools used for the extraction of knowledge are evolutionary computing and neural networks, as well as different clustering-like methods.

Selected Publications

Kirchner-Bossi, N., García-Herrera, R., Prieto, L. and Trigo, R. M. (2014): A long-term perspective of wind power output variability. Int. J. Climatol.. doi: 10.1002/joc.4161

Salcedo-Sanz S., Pastor-Sanchez A., Prieto L., Blanco-Aguilera A., Garcia-Herrera R. (2014): Feature selection in wind speed prediction systems based on a hybrid coral reefs optimization - Extreme learning machine approach. Energy Conversion and Management , 87, 10-18, doi: 10.1016/j.enconman.2014.06.041

Kirchner-Bossi N., Prieto L., García-Herrera R., Carro-Calvo L., Salcedo-Sanz S. (2013): Multi-decadal variability in a centennial reconstruction of daily wind. Applied Energy. doi:10.1016/j.apenergy.2012.11.072

Carro-Calvo L., Salcedo-Sanz S., Prieto L., Kirchner-Bossi N., Portilla-Figueras A., Jiménez Fernández S (2012): Wind speed reconstruction from synoptic pressure patterns using an evolutionary algorithm.Applied Energy, 89, 347-354. doi: 10.1016/j.apenergy.2011.07.044

Carro-Calvo L., Salcedo-Sanz S., Kirchner-Bossi N., Portilla-Figueras A., Prieto L., García-Herrera R., Hernández E. (2011): Extraction of synoptic pressure patterns for long-term wind speed estimation in wind farms using evolutionary computing. Energy, 36, 1571-1581. doi:10.1016/j.energy.2011.01.001