Cluster-Based Analogue Ensembles for Hindcasting with Multistations
The Analogue Ensemble (AnEn) method enables the reconstruction of meteorological observations or deterministic predictions for a certain variable and station by using data from the same station or from other nearby stations. However, depending on the dimension and granularity of the historical datas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/10/6/91 |
| _version_ | 1797488644035969024 |
|---|---|
| author | Carlos Balsa Carlos Veiga Rodrigues Leonardo Araújo José Rufino |
| author_facet | Carlos Balsa Carlos Veiga Rodrigues Leonardo Araújo José Rufino |
| author_sort | Carlos Balsa |
| collection | DOAJ |
| description | The Analogue Ensemble (AnEn) method enables the reconstruction of meteorological observations or deterministic predictions for a certain variable and station by using data from the same station or from other nearby stations. However, depending on the dimension and granularity of the historical datasets used for the reconstruction, this method may be computationally very demanding even if parallelization is used. In this work, the classical AnEn method is modified so that analogues are determined using K-means clustering. The proposed combined approach allows the use of several predictors in a dependent or independent way. As a result of the flexibility and adaptability of this new approach, it is necessary to define several parameters and algorithmic options. The effects of the critical parameters and main options were tested on a large dataset from real-world meteorological stations. The results show that adequate monitoring and tuning of the new method allows for a considerable improvement of the computational performance of the reconstruction task while keeping the accuracy of the results. Compared to the classical AnEn method, the proposed variant is at least 15-times faster when processing is serial. Both approaches benefit from parallel processing, with the K-means variant also being always faster than the classic method under that execution regime (albeit its performance advantage diminishes as more CPU threads are used). |
| first_indexed | 2024-03-10T00:05:14Z |
| format | Article |
| id | doaj.art-5df9573db49f4677aed76ef6e860e4cd |
| institution | Directory Open Access Journal |
| issn | 2079-3197 |
| language | English |
| last_indexed | 2024-03-10T00:05:14Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computation |
| spelling | doaj.art-5df9573db49f4677aed76ef6e860e4cd2023-11-23T16:09:36ZengMDPI AGComputation2079-31972022-06-011069110.3390/computation10060091Cluster-Based Analogue Ensembles for Hindcasting with MultistationsCarlos Balsa0Carlos Veiga Rodrigues1Leonardo Araújo2José Rufino3Research Centre in Digitalization and Intelligent Robotics (CeDRI), Instituto Politécnico de Bragança, 5300-253 Bragança, PortugalVestas Wind Systems A/S, Vestas Technology Centre Porto, 4465-671 Leça do Balio, PortugalUniversidade Tecnológica Federal do Paraná, Campus de Ponta Grossa, Ponta Grossa 84017-220, BrazilResearch Centre in Digitalization and Intelligent Robotics (CeDRI), Instituto Politécnico de Bragança, 5300-253 Bragança, PortugalThe Analogue Ensemble (AnEn) method enables the reconstruction of meteorological observations or deterministic predictions for a certain variable and station by using data from the same station or from other nearby stations. However, depending on the dimension and granularity of the historical datasets used for the reconstruction, this method may be computationally very demanding even if parallelization is used. In this work, the classical AnEn method is modified so that analogues are determined using K-means clustering. The proposed combined approach allows the use of several predictors in a dependent or independent way. As a result of the flexibility and adaptability of this new approach, it is necessary to define several parameters and algorithmic options. The effects of the critical parameters and main options were tested on a large dataset from real-world meteorological stations. The results show that adequate monitoring and tuning of the new method allows for a considerable improvement of the computational performance of the reconstruction task while keeping the accuracy of the results. Compared to the classical AnEn method, the proposed variant is at least 15-times faster when processing is serial. Both approaches benefit from parallel processing, with the K-means variant also being always faster than the classic method under that execution regime (albeit its performance advantage diminishes as more CPU threads are used).https://www.mdpi.com/2079-3197/10/6/91hindcastingmeteorological datasetanalogue ensembleK-meanstime-series |
| spellingShingle | Carlos Balsa Carlos Veiga Rodrigues Leonardo Araújo José Rufino Cluster-Based Analogue Ensembles for Hindcasting with Multistations Computation hindcasting meteorological dataset analogue ensemble K-means time-series |
| title | Cluster-Based Analogue Ensembles for Hindcasting with Multistations |
| title_full | Cluster-Based Analogue Ensembles for Hindcasting with Multistations |
| title_fullStr | Cluster-Based Analogue Ensembles for Hindcasting with Multistations |
| title_full_unstemmed | Cluster-Based Analogue Ensembles for Hindcasting with Multistations |
| title_short | Cluster-Based Analogue Ensembles for Hindcasting with Multistations |
| title_sort | cluster based analogue ensembles for hindcasting with multistations |
| topic | hindcasting meteorological dataset analogue ensemble K-means time-series |
| url | https://www.mdpi.com/2079-3197/10/6/91 |
| work_keys_str_mv | AT carlosbalsa clusterbasedanalogueensemblesforhindcastingwithmultistations AT carlosveigarodrigues clusterbasedanalogueensemblesforhindcastingwithmultistations AT leonardoaraujo clusterbasedanalogueensemblesforhindcastingwithmultistations AT joserufino clusterbasedanalogueensemblesforhindcastingwithmultistations |