Improved Local Weather Forecasts Using Artificial Neural Networks

Morten Gill Wollsen; Bo Nørregaard Jørgensen

doi:10.1007/978-3-319-19638-1_9

Improved Local Weather Forecasts Using Artificial Neural Networks

Morten Gill Wollsen, Bo Nørregaard Jørgensen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Solar irradiance and temperature forecasts are used in many different control systems. Such as intelligent climate control systems in commercial greenhouses, where the solar irradiance affects the use of supplemental lighting. This paper proposes a novel method to predict the forthcoming weather using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show that the network outperforms the commercial forecast for lower step aheads (< 5). For larger step aheads the network’s performance is in the range of the commercial forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution.

Original language	English
Title of host publication	Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015
Editors	Sigeru Omatu, Qutaibah M. Malluhi, Grzegorz Bocewicz, Sara Rodríguez González, Edgardo Bucciarelli, Gianfranco Giulioni, Farkhund Iqba
Publisher	Springer
Publication date	3. Jun 2015
Pages	75-86
ISBN (Print)	978-3-319-19637-4
ISBN (Electronic)	9783319196374
DOIs	https://doi.org/10.1007/978-3-319-19638-1_9
Publication status	Published - 3. Jun 2015
Event	12th International Symposium on Distributed Computing and Artificial Intelligence - University of Salamanca, Spain Duration: 3. Jun 2015 → 5. Jun 2015 Conference number: DCAI

Conference

Conference	12th International Symposium on Distributed Computing and Artificial Intelligence
Number	DCAI
Location	University of Salamanca
Country/Territory	Spain
Period	03/06/2015 → 05/06/2015

Series	Advances in Intelligent Systems and Computing
Volume	373
ISSN	2194-5357

Documents & Links

10.1007/978-3-319-19638-1_9

Cite this

Wollsen, M. G., & Jørgensen, B. N. (2015). Improved Local Weather Forecasts Using Artificial Neural Networks. In S. Omatu, Q. M. Malluhi, G. Bocewicz, S. R. González, E. Bucciarelli, G. Giulioni, & F. Iqba (Eds.), Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015 (pp. 75-86). Springer. https://doi.org/10.1007/978-3-319-19638-1_9

Wollsen, Morten Gill ; Jørgensen, Bo Nørregaard. / Improved Local Weather Forecasts Using Artificial Neural Networks. Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015. editor / Sigeru Omatu ; Qutaibah M. Malluhi ; Grzegorz Bocewicz ; Sara Rodríguez González ; Edgardo Bucciarelli ; Gianfranco Giulioni ; Farkhund Iqba. Springer, 2015. pp. 75-86 (Advances in Intelligent Systems and Computing, Vol. 373).

@inproceedings{01a1fc84d5d849b9ac0f10e930b701f4,

title = "Improved Local Weather Forecasts Using Artificial Neural Networks",

abstract = "Solar irradiance and temperature forecasts are used in many different control systems. Such as intelligent climate control systems in commercial greenhouses, where the solar irradiance affects the use of supplemental lighting. This paper proposes a novel method to predict the forthcoming weather using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show that the network outperforms the commercial forecast for lower step aheads (< 5). For larger step aheads the network{\textquoteright}s performance is in the range of the commercial forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution.",

author = "Wollsen, {Morten Gill} and J{\o}rgensen, {Bo N{\o}rregaard}",

year = "2015",

month = jun,

day = "3",

doi = "10.1007/978-3-319-19638-1_9",

language = "English",

isbn = "978-3-319-19637-4",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "75--86",

editor = "Sigeru Omatu and Malluhi, {Qutaibah M.} and Grzegorz Bocewicz and Gonz{\'a}lez, {Sara Rodr{\'i}guez} and Edgardo Bucciarelli and Gianfranco Giulioni and Farkhund Iqba",

booktitle = "Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015",

address = "Germany",

note = "12th International Symposium on Distributed Computing and Artificial Intelligence ; Conference date: 03-06-2015 Through 05-06-2015",

}

Wollsen, MG & Jørgensen, BN 2015, Improved Local Weather Forecasts Using Artificial Neural Networks. in S Omatu, QM Malluhi, G Bocewicz, SR González, E Bucciarelli, G Giulioni & F Iqba (eds), Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015. Springer, Advances in Intelligent Systems and Computing, vol. 373, pp. 75-86, 12th International Symposium on Distributed Computing and Artificial Intelligence, Spain, 03/06/2015. https://doi.org/10.1007/978-3-319-19638-1_9

Improved Local Weather Forecasts Using Artificial Neural Networks. / Wollsen, Morten Gill; Jørgensen, Bo Nørregaard.
Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015. ed. / Sigeru Omatu; Qutaibah M. Malluhi; Grzegorz Bocewicz; Sara Rodríguez González; Edgardo Bucciarelli; Gianfranco Giulioni; Farkhund Iqba. Springer, 2015. p. 75-86 (Advances in Intelligent Systems and Computing, Vol. 373).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Improved Local Weather Forecasts Using Artificial Neural Networks

AU - Wollsen, Morten Gill

AU - Jørgensen, Bo Nørregaard

N1 - Conference code: DCAI

PY - 2015/6/3

Y1 - 2015/6/3

N2 - Solar irradiance and temperature forecasts are used in many different control systems. Such as intelligent climate control systems in commercial greenhouses, where the solar irradiance affects the use of supplemental lighting. This paper proposes a novel method to predict the forthcoming weather using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show that the network outperforms the commercial forecast for lower step aheads (< 5). For larger step aheads the network’s performance is in the range of the commercial forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution.

AB - Solar irradiance and temperature forecasts are used in many different control systems. Such as intelligent climate control systems in commercial greenhouses, where the solar irradiance affects the use of supplemental lighting. This paper proposes a novel method to predict the forthcoming weather using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show that the network outperforms the commercial forecast for lower step aheads (< 5). For larger step aheads the network’s performance is in the range of the commercial forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution.

U2 - 10.1007/978-3-319-19638-1_9

DO - 10.1007/978-3-319-19638-1_9

M3 - Article in proceedings

SN - 978-3-319-19637-4

T3 - Advances in Intelligent Systems and Computing

SP - 75

EP - 86

BT - Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015

A2 - Omatu, Sigeru

A2 - Malluhi, Qutaibah M.

A2 - Bocewicz, Grzegorz

A2 - González, Sara Rodríguez

A2 - Bucciarelli, Edgardo

A2 - Giulioni, Gianfranco

A2 - Iqba, Farkhund

PB - Springer

T2 - 12th International Symposium on Distributed Computing and Artificial Intelligence

Y2 - 3 June 2015 through 5 June 2015

ER -

Wollsen MG, Jørgensen BN. Improved Local Weather Forecasts Using Artificial Neural Networks. In Omatu S, Malluhi QM, Bocewicz G, González SR, Bucciarelli E, Giulioni G, Iqba F, editors, Distributed Computing and Artificial Intelligence, 12th International Conference, DCAI 2015. Springer. 2015. p. 75-86. (Advances in Intelligent Systems and Computing, Vol. 373). doi: 10.1007/978-3-319-19638-1_9