Black-box modeling for temperature prediction in weather forecasting

Zahra Karevan; Siamak Mehrkanoon; Johan A.K. Suykens

doi:10.1109/IJCNN.2015.7280671

Black-box modeling for temperature prediction in weather forecasting

Zahra Karevan, Siamak Mehrkanoon, Johan A.K. Suykens

Sub Algorithmic Data Analysis

KU Leuven

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Accurate weather forecasting is one of most challenging tasks that deals with a large amount of observations and features. In this paper, a black-box modeling technique is proposed for temperature forecasting. Due to the high dimensionality of data, feature selection is done in two steps with k-Nearest Neighbors and Elastic net. Next, Least Squares Support Vector Machine regression is applied to generate the forecasting model. In the experimental results, the influence of each part of this procedure on the performance is investigated and compared with 'Weather underground' results. For the case study, the prediction of the temperature in Brussels is considered. It is shown that black-box modeling has a good and competitive accuracy with current state-of-the-art methods for temperature prediction.

Original language	English
Title of host publication	2015 International Joint Conference on Neural Networks, IJCNN 2015
Publisher	IEEE
ISBN (Electronic)	9781479919604, 9781479919604, 9781479919604, 9781479919604
DOIs	https://doi.org/10.1109/IJCNN.2015.7280671
Publication status	Published - 28 Sept 2015
Event	International Joint Conference on Neural Networks, IJCNN 2015 - Killarney, Ireland Duration: 12 Jul 2015 → 17 Jul 2015

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2015-September

Conference

Conference	International Joint Conference on Neural Networks, IJCNN 2015
Country/Territory	Ireland
City	Killarney
Period	12/07/15 → 17/07/15

Keywords

Support vector machines

Access to Document

10.1109/IJCNN.2015.7280671

Cite this

@inproceedings{7a9b85738cf0423d983ad8b2eea8048d,

title = "Black-box modeling for temperature prediction in weather forecasting",

abstract = "Accurate weather forecasting is one of most challenging tasks that deals with a large amount of observations and features. In this paper, a black-box modeling technique is proposed for temperature forecasting. Due to the high dimensionality of data, feature selection is done in two steps with k-Nearest Neighbors and Elastic net. Next, Least Squares Support Vector Machine regression is applied to generate the forecasting model. In the experimental results, the influence of each part of this procedure on the performance is investigated and compared with 'Weather underground' results. For the case study, the prediction of the temperature in Brussels is considered. It is shown that black-box modeling has a good and competitive accuracy with current state-of-the-art methods for temperature prediction.",

keywords = "Support vector machines",

author = "Zahra Karevan and Siamak Mehrkanoon and Suykens, {Johan A.K.}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; International Joint Conference on Neural Networks, IJCNN 2015 ; Conference date: 12-07-2015 Through 17-07-2015",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/IJCNN.2015.7280671",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "IEEE",

booktitle = "2015 International Joint Conference on Neural Networks, IJCNN 2015",

address = "United States",

}

Karevan, Z, Mehrkanoon, S & Suykens, JAK 2015, Black-box modeling for temperature prediction in weather forecasting. in 2015 International Joint Conference on Neural Networks, IJCNN 2015., 7280671, Proceedings of the International Joint Conference on Neural Networks, vol. 2015-September, IEEE, International Joint Conference on Neural Networks, IJCNN 2015, Killarney, Ireland, 12/07/15. https://doi.org/10.1109/IJCNN.2015.7280671

Black-box modeling for temperature prediction in weather forecasting. / Karevan, Zahra; Mehrkanoon, Siamak; Suykens, Johan A.K.
2015 International Joint Conference on Neural Networks, IJCNN 2015. IEEE, 2015. 7280671 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2015-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Black-box modeling for temperature prediction in weather forecasting

AU - Karevan, Zahra

AU - Mehrkanoon, Siamak

AU - Suykens, Johan A.K.

PY - 2015/9/28

Y1 - 2015/9/28

N2 - Accurate weather forecasting is one of most challenging tasks that deals with a large amount of observations and features. In this paper, a black-box modeling technique is proposed for temperature forecasting. Due to the high dimensionality of data, feature selection is done in two steps with k-Nearest Neighbors and Elastic net. Next, Least Squares Support Vector Machine regression is applied to generate the forecasting model. In the experimental results, the influence of each part of this procedure on the performance is investigated and compared with 'Weather underground' results. For the case study, the prediction of the temperature in Brussels is considered. It is shown that black-box modeling has a good and competitive accuracy with current state-of-the-art methods for temperature prediction.

AB - Accurate weather forecasting is one of most challenging tasks that deals with a large amount of observations and features. In this paper, a black-box modeling technique is proposed for temperature forecasting. Due to the high dimensionality of data, feature selection is done in two steps with k-Nearest Neighbors and Elastic net. Next, Least Squares Support Vector Machine regression is applied to generate the forecasting model. In the experimental results, the influence of each part of this procedure on the performance is investigated and compared with 'Weather underground' results. For the case study, the prediction of the temperature in Brussels is considered. It is shown that black-box modeling has a good and competitive accuracy with current state-of-the-art methods for temperature prediction.

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84951144702&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2015.7280671

DO - 10.1109/IJCNN.2015.7280671

M3 - Conference contribution

AN - SCOPUS:84951144702

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2015 International Joint Conference on Neural Networks, IJCNN 2015

PB - IEEE

T2 - International Joint Conference on Neural Networks, IJCNN 2015

Y2 - 12 July 2015 through 17 July 2015

ER -

Black-box modeling for temperature prediction in weather forecasting

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this