Evaluation of Unsupervised Machine Learning Algorithms with Climate Data
Fuente:
Redalyc
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artículo científico |
| Sprache: | en |
| Veröffentlicht: |
Universidad del Norte
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1876449499883241472 |
|---|---|
| author | Juan Sebastián Ramírez |
| author_facet | Juan Sebastián Ramírez |
| contents | Evaluation of Unsupervised Machine Learning Algorithms with Climate Data Juan Sebastián Ramírez Néstor Duque-Méndez Ingeniería means Climate medoids clustering machine learning When using climate data, researchers have difficulty determining the clustering algorithm and the best performing parameters for processing a specific dataset. We evaluated of the following unsupervised machine learning algorithms: K-means, K-medoids and Linkage-complete, which are applied to three datasets with climatological variables (temperature, rainfall, relative humidity, and solar radiation) for three meteorological stations located in the department of Caldas, Colombia, at different heights above sea level. Five scenarios are defined for 2, 3, and 5 clusters for each of the two partitioned algorithms, and five scenarios for the hierarchical algorithm, in each one of the meteorological stations. Different quantities and groupings of variables are applied for the different scenarios by using Euclidean distance. Davis-Bouldin is the applied method of quality evaluation of clusters. Normalization with techniques such as range-transformation and Z-trans-formation, as well as some iterations of the algorithm and reduction of dimensionality with PCA. In addition, the computational cost is evaluated. This study can guide researchers on certain decisions in cluster analysis used in meteorological data, as well as identify the most important algorithm and parameters to take into consideration for the best performance, according to particular conditions and requirements. 2022 artículo científico 0122-3461 https://www.redalyc.org/articulo.oa?id=85275236002 https://www.redalyc.org/journal/852/85275236002/ https://www.redalyc.org/journal/852/85275236002/html/ https://www.redalyc.org/journal/852/85275236002/85275236002.epub https://www.redalyc.org/journal/852/85275236002/movil 10.14482/inde.40.02.622.553 en http://www.redalyc.org/revista.oa?id=852 Ingeniería y Desarrollo application/pdf Universidad del Norte Ingeniería y Desarrollo (Colombia) Num.2 Vol.40 |
| format | Artículo científico |
| id | redalyc_85275236002 |
| institution | Redalyc |
| language | en |
| publishDate | 2022 |
| publisher | Universidad del Norte |
| spellingShingle | Evaluation of Unsupervised Machine Learning Algorithms with Climate Data Juan Sebastián Ramírez Ingeniería means Climate medoids clustering machine learning Evaluation of Unsupervised Machine Learning Algorithms with Climate Data Juan Sebastián Ramírez Néstor Duque-Méndez Ingeniería means Climate medoids clustering machine learning When using climate data, researchers have difficulty determining the clustering algorithm and the best performing parameters for processing a specific dataset. We evaluated of the following unsupervised machine learning algorithms: K-means, K-medoids and Linkage-complete, which are applied to three datasets with climatological variables (temperature, rainfall, relative humidity, and solar radiation) for three meteorological stations located in the department of Caldas, Colombia, at different heights above sea level. Five scenarios are defined for 2, 3, and 5 clusters for each of the two partitioned algorithms, and five scenarios for the hierarchical algorithm, in each one of the meteorological stations. Different quantities and groupings of variables are applied for the different scenarios by using Euclidean distance. Davis-Bouldin is the applied method of quality evaluation of clusters. Normalization with techniques such as range-transformation and Z-trans-formation, as well as some iterations of the algorithm and reduction of dimensionality with PCA. In addition, the computational cost is evaluated. This study can guide researchers on certain decisions in cluster analysis used in meteorological data, as well as identify the most important algorithm and parameters to take into consideration for the best performance, according to particular conditions and requirements. 2022 artículo científico 0122-3461 https://www.redalyc.org/articulo.oa?id=85275236002 https://www.redalyc.org/journal/852/85275236002/ https://www.redalyc.org/journal/852/85275236002/html/ https://www.redalyc.org/journal/852/85275236002/85275236002.epub https://www.redalyc.org/journal/852/85275236002/movil 10.14482/inde.40.02.622.553 en http://www.redalyc.org/revista.oa?id=852 Ingeniería y Desarrollo application/pdf Universidad del Norte Ingeniería y Desarrollo (Colombia) Num.2 Vol.40 |
| title | Evaluation of Unsupervised Machine Learning Algorithms with Climate Data |
| topic | Ingeniería means Climate medoids clustering machine learning |
| url | https://www.redalyc.org/articulo.oa?id=85275236002 https://www.redalyc.org/journal/852/85275236002/ https://www.redalyc.org/journal/852/85275236002/html/ https://www.redalyc.org/journal/852/85275236002/85275236002.epub https://www.redalyc.org/journal/852/85275236002/movil |