Application of Machine Learning for CIE Standard Sky Classification

Emmanuel Imuetinyan Aghimien; Danny Hin Wa Li; Ernest Kin Wai Tsang; Favour David Agbajor

doi:10.1007/978-981-19-9822-5_126

Application of Machine Learning for CIE Standard Sky Classification

Emmanuel Imuetinyan Aghimien^*
, Danny Hin Wa Li
, Ernest Kin Wai Tsang
, Favour David Agbajor

^*Corresponding author for this work

Department of Architecture and Civil Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

1 Citation (Scopus)

Abstract

The spectrum of skies in the world was classified into a range of 15 standard skies. These standard skies are crucial in estimating solar irradiance and daylight illuminance needed for energy-efficient building designs. Generally, using the sky luminance distributions to identify the standard skies is the most effective method, but these are sparingly measured. Alternatively, climatic variables can identify the standard skies. Nevertheless, it is necessary to determine if the available climatic variables could correctly identify these skies. Also, there are several climatic variables, but there is no criterion for selecting a climatic variable over the other. This study addresses the lack of luminance distributions measurement by classifying the standard skies using measured climatic data. Furthermore, sensitivity analysis was used to determine the relative importance of one variable over the other. Importantly, the proposed approach for classifying the standard skies was implemented using support vector machines (SVM). Findings showed that the SVM could classify the skies with an accuracy of 72.4% on the training data and 71.4% on the test data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

Original language	English
Title of host publication	Proceedings of the 5th International Conference on Building Energy and Environment
Editors	Liangzhu Leon Wang, Hua Ge, Zhiqiang John Zhai, Dahai Qi, Mohamed Ouf, Chanjuan Sun, Dengjia Wang
Place of Publication	Singapore
Publisher	Springer
Chapter	126
Pages	1201-1211
ISBN (Electronic)	978-981-19-9822-5
ISBN (Print)	978-981-19-9821-8, 978-981-19-9823-2
DOIs	https://doi.org/10.1007/978-981-19-9822-5_126
Publication status	Published - 2023
Event	5th International Conference on Building Energy And Environment (COBEE 2022) - Concordia University, Montreal, Canada Duration: 25 Jul 2022 → 29 Jul 2022 https://www.cobee2022.org/

Publication series

Name	Environmental Science and Engineering
ISSN (Print)	1863-5520
ISSN (Electronic)	1863-5539

Conference

Conference	5th International Conference on Building Energy And Environment (COBEE 2022)
Abbreviated title	COBEE2022
Place	Canada
City	Montreal
Period	25/07/22 → 29/07/22
Internet address	https://www.cobee2022.org/

Funding

Work described was fully supported by a General Research Fund from the Grant Council of HKSAR [Project no. 90421773 (CityU 11211719)]. Emmanuel Imuetinyan Aghimien was supported by a City University of Hong Kong Postgraduate Studentship.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Research Keywords

CIE Standard skies
sky luminance
Climatic indices
Machine learning
Sensitivity analysis

RGC Funding Information

RGC-funded

Access Output

10.1007/978-981-19-9822-5_126

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

GRF: Development of Comprehensive Solar Radiation and Daylight Illuminance Datasets by Ameliorating the Prediction Models and Categorizing Standard Skies Using Machine Learning Techniques
LI, H. W. (Principal Investigator / Project Coordinator), ALSHAIBANI, K. A. (Co-Investigator), GhaffarianHoseini, A. (Co-Investigator) & LEE, W. M. (Co-Investigator)
1/01/20 → 5/06/24
Project: Research

Cite this

Aghimien, E. I., Li, D. H. W., Tsang, E. K. W., & Agbajor, F. D. (2023). Application of Machine Learning for CIE Standard Sky Classification. In L. L. Wang, H. Ge, Z. J. Zhai, D. Qi, M. Ouf, C. Sun, & D. Wang (Eds.), Proceedings of the 5th International Conference on Building Energy and Environment (pp. 1201-1211). (Environmental Science and Engineering). Springer . https://doi.org/10.1007/978-981-19-9822-5_126

Aghimien, Emmanuel Imuetinyan ; Li, Danny Hin Wa ; Tsang, Ernest Kin Wai et al. / Application of Machine Learning for CIE Standard Sky Classification. Proceedings of the 5th International Conference on Building Energy and Environment . editor / Liangzhu Leon Wang ; Hua Ge ; Zhiqiang John Zhai ; Dahai Qi ; Mohamed Ouf ; Chanjuan Sun ; Dengjia Wang. Singapore : Springer , 2023. pp. 1201-1211 (Environmental Science and Engineering).

@inbook{f2b49ec92c0542bebb05305b34d46284,

title = "Application of Machine Learning for CIE Standard Sky Classification",

abstract = "The spectrum of skies in the world was classified into a range of 15 standard skies. These standard skies are crucial in estimating solar irradiance and daylight illuminance needed for energy-efficient building designs. Generally, using the sky luminance distributions to identify the standard skies is the most effective method, but these are sparingly measured. Alternatively, climatic variables can identify the standard skies. Nevertheless, it is necessary to determine if the available climatic variables could correctly identify these skies. Also, there are several climatic variables, but there is no criterion for selecting a climatic variable over the other. This study addresses the lack of luminance distributions measurement by classifying the standard skies using measured climatic data. Furthermore, sensitivity analysis was used to determine the relative importance of one variable over the other. Importantly, the proposed approach for classifying the standard skies was implemented using support vector machines (SVM). Findings showed that the SVM could classify the skies with an accuracy of 72.4\% on the training data and 71.4\% on the test data. {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.",

keywords = "CIE Standard skies, sky luminance, Climatic indices, Machine learning, Sensitivity analysis",

author = "Aghimien, \{Emmanuel Imuetinyan\} and Li, \{Danny Hin Wa\} and Tsang, \{Ernest Kin Wai\} and Agbajor, \{Favour David\}",

year = "2023",

doi = "10.1007/978-981-19-9822-5\_126",

language = "English",

isbn = "978-981-19-9821-8",

series = "Environmental Science and Engineering",

publisher = "Springer ",

pages = "1201--1211",

editor = "Wang, \{Liangzhu Leon\} and Hua Ge and Zhai, \{Zhiqiang John\} and Dahai Qi and Mohamed Ouf and Chanjuan Sun and Dengjia Wang",

booktitle = "Proceedings of the 5th International Conference on Building Energy and Environment",

note = "5th International Conference on Building Energy And Environment (COBEE 2022), COBEE2022 ; Conference date: 25-07-2022 Through 29-07-2022",

url = "https://www.cobee2022.org/",

}

Aghimien, EI , Li, DHW, Tsang, EKW & Agbajor, FD 2023, Application of Machine Learning for CIE Standard Sky Classification. in LL Wang, H Ge, ZJ Zhai, D Qi, M Ouf, C Sun & D Wang (eds), Proceedings of the 5th International Conference on Building Energy and Environment . Environmental Science and Engineering, Springer , Singapore, pp. 1201-1211, 5th International Conference on Building Energy And Environment (COBEE 2022), Montreal, Quebec, Canada, 25/07/22. https://doi.org/10.1007/978-981-19-9822-5_126

Application of Machine Learning for CIE Standard Sky Classification. / Aghimien, Emmanuel Imuetinyan ; Li, Danny Hin Wa; Tsang, Ernest Kin Wai et al.
Proceedings of the 5th International Conference on Building Energy and Environment . ed. / Liangzhu Leon Wang; Hua Ge; Zhiqiang John Zhai; Dahai Qi; Mohamed Ouf; Chanjuan Sun; Dengjia Wang. Singapore: Springer , 2023. p. 1201-1211 (Environmental Science and Engineering).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

TY - CHAP

T1 - Application of Machine Learning for CIE Standard Sky Classification

AU - Aghimien, Emmanuel Imuetinyan

AU - Li, Danny Hin Wa

AU - Tsang, Ernest Kin Wai

AU - Agbajor, Favour David

PY - 2023

Y1 - 2023

N2 - The spectrum of skies in the world was classified into a range of 15 standard skies. These standard skies are crucial in estimating solar irradiance and daylight illuminance needed for energy-efficient building designs. Generally, using the sky luminance distributions to identify the standard skies is the most effective method, but these are sparingly measured. Alternatively, climatic variables can identify the standard skies. Nevertheless, it is necessary to determine if the available climatic variables could correctly identify these skies. Also, there are several climatic variables, but there is no criterion for selecting a climatic variable over the other. This study addresses the lack of luminance distributions measurement by classifying the standard skies using measured climatic data. Furthermore, sensitivity analysis was used to determine the relative importance of one variable over the other. Importantly, the proposed approach for classifying the standard skies was implemented using support vector machines (SVM). Findings showed that the SVM could classify the skies with an accuracy of 72.4% on the training data and 71.4% on the test data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

AB - The spectrum of skies in the world was classified into a range of 15 standard skies. These standard skies are crucial in estimating solar irradiance and daylight illuminance needed for energy-efficient building designs. Generally, using the sky luminance distributions to identify the standard skies is the most effective method, but these are sparingly measured. Alternatively, climatic variables can identify the standard skies. Nevertheless, it is necessary to determine if the available climatic variables could correctly identify these skies. Also, there are several climatic variables, but there is no criterion for selecting a climatic variable over the other. This study addresses the lack of luminance distributions measurement by classifying the standard skies using measured climatic data. Furthermore, sensitivity analysis was used to determine the relative importance of one variable over the other. Importantly, the proposed approach for classifying the standard skies was implemented using support vector machines (SVM). Findings showed that the SVM could classify the skies with an accuracy of 72.4% on the training data and 71.4% on the test data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

KW - CIE Standard skies

KW - sky luminance

KW - Climatic indices

KW - Machine learning

KW - Sensitivity analysis

U2 - 10.1007/978-981-19-9822-5_126

DO - 10.1007/978-981-19-9822-5_126

M3 - RGC 12 - Chapter in an edited book (Author)

SN - 978-981-19-9821-8

SN - 978-981-19-9823-2

T3 - Environmental Science and Engineering

SP - 1201

EP - 1211

BT - Proceedings of the 5th International Conference on Building Energy and Environment

A2 - Wang, Liangzhu Leon

A2 - Ge, Hua

A2 - Zhai, Zhiqiang John

A2 - Qi, Dahai

A2 - Ouf, Mohamed

A2 - Sun, Chanjuan

A2 - Wang, Dengjia

PB - Springer

CY - Singapore

T2 - 5th International Conference on Building Energy And Environment (COBEE 2022)

Y2 - 25 July 2022 through 29 July 2022

ER -

Aghimien EI , Li DHW, Tsang EKW, Agbajor FD. Application of Machine Learning for CIE Standard Sky Classification. In Wang LL, Ge H, Zhai ZJ, Qi D, Ouf M, Sun C, Wang D, editors, Proceedings of the 5th International Conference on Building Energy and Environment . Singapore: Springer . 2023. p. 1201-1211. (Environmental Science and Engineering). Epub 2023 Sept 5. doi: 10.1007/978-981-19-9822-5_126

Application of Machine Learning for CIE Standard Sky Classification

Abstract

Publication series

Conference

Funding

UN SDGs

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Fingerprint

Projects

GRF: Development of Comprehensive Solar Radiation and Daylight Illuminance Datasets by Ameliorating the Prediction Models and Categorizing Standard Skies Using Machine Learning Techniques

Cite this