@article{3084,
  author = {Alexandre Chesneau, Carlos Balsa, Carlos Veiga Rodrigues, Isabel Lopes},
  title = {Using Analog Ensembles Algorithms for Multistations},
  journal = {Journal of Intelligent Computing},
  year = {2020},
  volume = {11},
  number = {3},
  doi = {https://doi.org/10.6025/jic/2020/11/3/102-113},
  url = {http://www.dline.info/jic/fulltext/v11n3/jicv11n3_3.pdf},
  abstract = {In this work, many analog ensembles algorithms were used with the performance of multiple stations. We have deployed many techniques to analyse and benchmark inorder to change the prediction. This issue consists in leading the weather predictions for a location where no data is available, using meteorological time series from nearby stations. Many models are verified and explored. The preliminary one is described by Monache and co-workers, to methods using cosine similarity, normalization, and K-means clustering. Best results were obtained with the K-means metric, wielding between 3% and 30% of lower quadratic error when compared against the Monache metric. Increasing the predictors to two stations improved the performance of the hindcast, leading up to 16% of lower error, depending on the correlation between the predictor stations.},
}