Year-ahead Ambient Temperature Forecasting in Pharmaceutical Transport Lanes Thermal Conditions

Annabel P.B. Van Den Berg; Lotte R. Bootsma; Thomas F.A. Bovenber; A. Rosa Moerbeek; Eelco De Jong; Sergey Khalil; Thomas Koch; Elenna R. Dugundji

doi:10.1016/j.procs.2022.03.035

Year-ahead Ambient Temperature Forecasting in Pharmaceutical Transport Lanes Thermal Conditions

Annabel P.B. Van Den Berg^*, Lotte R. Bootsma, Thomas F.A. Bovenber, A. Rosa Moerbeek, Eelco De Jong, Sergey Khalil, Thomas Koch, Elenna R. Dugundji

^*Corresponding author for this work

Mathematics

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

This research aims to predict year-ahead ambient temperature aggregated at monthly level per hour on airport locations using historical temperature data. In this research, an Extreme gradient boosting regression model, LSTM model and the benchmark model, a persistence model, are compared in accuracy. Models are fine-tuned on the cities with the highest variability in temperature and grid searches are implemented only for these cities (one per data source). Overall, we have seen that the LSTM model with output size 12 months x 24 hours predicts for the next year the best. The Persistence model is closely followed by the Extreme gradient boosting model, with a small deviation in the quantiles. The point predictions for each of the other models are a bit further of (with more than 3 degrees Celsius) and LSTM 365 days x 24 hours is the worst in this case. These models can be used to give an indication for the ambient temperature on lane level.

Original language	English
Pages (from-to)	255-264
Number of pages	10
Journal	Procedia Computer Science
Volume	201
Issue number	C
Early online date	27 Apr 2022
DOIs	https://doi.org/10.1016/j.procs.2022.03.035
Publication status	Published - 2022
Event	13th International Conference on Ambient Systems, Networks and Technologies, ANT 2022 / 5th International Conference on Emerging Data and Industry 4.0, EDI40 2022 - Porto, Portugal Duration: 22 Mar 2022 → 25 Mar 2022

Bibliographical note

Part of special issue: The 13th International Conference on Ambient Systems, Networks and Technologies (ANT) / The 5th International Conference on Emerging Data and Industry 4.0 (EDI40), Edited by Elhadi Shakshuki.

Publisher Copyright:
© 2022 Elsevier B.V.. All rights reserved.

Keywords

Air cargo
Ambient temperature
Extreme gradient boosting
Forecasting
LSTM
Packaging
Persistence model
Pharmaceutical products
Tarmac

Access to Document

10.1016/j.procs.2022.03.035

Persistent URL (handle)

Persistent link

Cite this

@article{2d7bc877b5ec418bbfb37a263027f55f,

title = "Year-ahead Ambient Temperature Forecasting in Pharmaceutical Transport Lanes Thermal Conditions",

abstract = "This research aims to predict year-ahead ambient temperature aggregated at monthly level per hour on airport locations using historical temperature data. In this research, an Extreme gradient boosting regression model, LSTM model and the benchmark model, a persistence model, are compared in accuracy. Models are fine-tuned on the cities with the highest variability in temperature and grid searches are implemented only for these cities (one per data source). Overall, we have seen that the LSTM model with output size 12 months x 24 hours predicts for the next year the best. The Persistence model is closely followed by the Extreme gradient boosting model, with a small deviation in the quantiles. The point predictions for each of the other models are a bit further of (with more than 3 degrees Celsius) and LSTM 365 days x 24 hours is the worst in this case. These models can be used to give an indication for the ambient temperature on lane level.",

keywords = "Air cargo, Ambient temperature, Extreme gradient boosting, Forecasting, LSTM, Packaging, Persistence model, Pharmaceutical products, Tarmac",

author = "{Van Den Berg}, {Annabel P.B.} and Bootsma, {Lotte R.} and Bovenber, {Thomas F.A.} and Moerbeek, {A. Rosa} and {De Jong}, Eelco and Sergey Khalil and Thomas Koch and Dugundji, {Elenna R.}",

note = "Part of special issue: The 13th International Conference on Ambient Systems, Networks and Technologies (ANT) / The 5th International Conference on Emerging Data and Industry 4.0 (EDI40), Edited by Elhadi Shakshuki. Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.. All rights reserved.; 13th International Conference on Ambient Systems, Networks and Technologies, ANT 2022 / 5th International Conference on Emerging Data and Industry 4.0, EDI40 2022 ; Conference date: 22-03-2022 Through 25-03-2022",

year = "2022",

doi = "10.1016/j.procs.2022.03.035",

language = "English",

volume = "201",

pages = "255--264",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier B.V.",

number = "C",

}

TY - JOUR

T1 - Year-ahead Ambient Temperature Forecasting in Pharmaceutical Transport Lanes Thermal Conditions

AU - Van Den Berg, Annabel P.B.

AU - Bootsma, Lotte R.

AU - Bovenber, Thomas F.A.

AU - Moerbeek, A. Rosa

AU - De Jong, Eelco

AU - Khalil, Sergey

AU - Koch, Thomas

AU - Dugundji, Elenna R.

N1 - Part of special issue: The 13th International Conference on Ambient Systems, Networks and Technologies (ANT) / The 5th International Conference on Emerging Data and Industry 4.0 (EDI40), Edited by Elhadi Shakshuki. Publisher Copyright: © 2022 Elsevier B.V.. All rights reserved.

PY - 2022

Y1 - 2022

N2 - This research aims to predict year-ahead ambient temperature aggregated at monthly level per hour on airport locations using historical temperature data. In this research, an Extreme gradient boosting regression model, LSTM model and the benchmark model, a persistence model, are compared in accuracy. Models are fine-tuned on the cities with the highest variability in temperature and grid searches are implemented only for these cities (one per data source). Overall, we have seen that the LSTM model with output size 12 months x 24 hours predicts for the next year the best. The Persistence model is closely followed by the Extreme gradient boosting model, with a small deviation in the quantiles. The point predictions for each of the other models are a bit further of (with more than 3 degrees Celsius) and LSTM 365 days x 24 hours is the worst in this case. These models can be used to give an indication for the ambient temperature on lane level.

AB - This research aims to predict year-ahead ambient temperature aggregated at monthly level per hour on airport locations using historical temperature data. In this research, an Extreme gradient boosting regression model, LSTM model and the benchmark model, a persistence model, are compared in accuracy. Models are fine-tuned on the cities with the highest variability in temperature and grid searches are implemented only for these cities (one per data source). Overall, we have seen that the LSTM model with output size 12 months x 24 hours predicts for the next year the best. The Persistence model is closely followed by the Extreme gradient boosting model, with a small deviation in the quantiles. The point predictions for each of the other models are a bit further of (with more than 3 degrees Celsius) and LSTM 365 days x 24 hours is the worst in this case. These models can be used to give an indication for the ambient temperature on lane level.

KW - Air cargo

KW - Ambient temperature

KW - Extreme gradient boosting

KW - Forecasting

KW - LSTM

KW - Packaging

KW - Persistence model

KW - Pharmaceutical products

KW - Tarmac

UR - http://www.scopus.com/inward/record.url?scp=85132206633&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85132206633&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2022.03.035

DO - 10.1016/j.procs.2022.03.035

M3 - Article

AN - SCOPUS:85132206633

SN - 1877-0509

VL - 201

SP - 255

EP - 264

JO - Procedia Computer Science

JF - Procedia Computer Science

IS - C

T2 - 13th International Conference on Ambient Systems, Networks and Technologies, ANT 2022 / 5th International Conference on Emerging Data and Industry 4.0, EDI40 2022

Y2 - 22 March 2022 through 25 March 2022

ER -

Year-ahead Ambient Temperature Forecasting in Pharmaceutical Transport Lanes Thermal Conditions

Abstract

Bibliographical note

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this