Seasonal-Trend Time Series Decomposition on Graphics Processing Units

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Seasonal-Trend Time Series Decomposition on Graphics Processing Units. / Serykh, Dmitry; Oehmcke, Stefan; Oancea, Cosmin; Masiliunas, Dainius; Verbesselt, Jan; Cheng, Yan; Horion, Stephanie; Gieseke, Fabian; Hinnerskov, Nikolaj.

Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023. red. / Jingrui He; Themis Palpanas; Xiaohua Hu; Alfredo Cuzzocrea; Dejing Dou; Dominik Slezak; Wei Wang; Aleksandra Gruca; Jerry Chun-Wei Lin; Rakesh Agrawal. IEEE, 2023. s. 5914-5923.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Serykh, D, Oehmcke, S, Oancea, C, Masiliunas, D, Verbesselt, J, Cheng, Y, Horion, S, Gieseke, F & Hinnerskov, N 2023, Seasonal-Trend Time Series Decomposition on Graphics Processing Units. i J He, T Palpanas, X Hu, A Cuzzocrea, D Dou, D Slezak, W Wang, A Gruca, JC-W Lin & R Agrawal (red), Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023. IEEE, s. 5914-5923, 2023 IEEE International Conference on Big Data, BigData 2023, Sorrento, Italien, 15/12/2023. https://doi.org/10.1109/BigData59044.2023.10386208

APA

Serykh, D., Oehmcke, S., Oancea, C., Masiliunas, D., Verbesselt, J., Cheng, Y., Horion, S., Gieseke, F., & Hinnerskov, N. (2023). Seasonal-Trend Time Series Decomposition on Graphics Processing Units. I J. He, T. Palpanas, X. Hu, A. Cuzzocrea, D. Dou, D. Slezak, W. Wang, A. Gruca, J. C-W. Lin, & R. Agrawal (red.), Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023 (s. 5914-5923). IEEE. https://doi.org/10.1109/BigData59044.2023.10386208

Vancouver

Serykh D, Oehmcke S, Oancea C, Masiliunas D, Verbesselt J, Cheng Y o.a. Seasonal-Trend Time Series Decomposition on Graphics Processing Units. I He J, Palpanas T, Hu X, Cuzzocrea A, Dou D, Slezak D, Wang W, Gruca A, Lin JC-W, Agrawal R, red., Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023. IEEE. 2023. s. 5914-5923 https://doi.org/10.1109/BigData59044.2023.10386208

Author

Serykh, Dmitry ; Oehmcke, Stefan ; Oancea, Cosmin ; Masiliunas, Dainius ; Verbesselt, Jan ; Cheng, Yan ; Horion, Stephanie ; Gieseke, Fabian ; Hinnerskov, Nikolaj. / Seasonal-Trend Time Series Decomposition on Graphics Processing Units. Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023. red. / Jingrui He ; Themis Palpanas ; Xiaohua Hu ; Alfredo Cuzzocrea ; Dejing Dou ; Dominik Slezak ; Wei Wang ; Aleksandra Gruca ; Jerry Chun-Wei Lin ; Rakesh Agrawal. IEEE, 2023. s. 5914-5923

Bibtex

@inproceedings{4c8c95f7292043ca99aa2fd1aea89b73,
title = "Seasonal-Trend Time Series Decomposition on Graphics Processing Units",
abstract = "In many domains, large amounts of time series data are being collected and analyzed in a semi-automatic manner. A prominent approach is the seasonal and trend decomposition using locally estimated scatterplot smoothing (STL) technique, which has been applied extensively in the past. However, STL quickly becomes computationally very expensive when applied to large data sets. In this work, we propose the first parallel implementation for the STL decomposition approach, which is tailored to the specific needs of graphics processing units (GPU). Our experimental evaluation on two global-scale case studies in temperature and vegetation trend analysis exhibits at least three-to-four orders of magnitude speed-up, demonstrating the effectiveness of the overall approach and the immense potential of the implementation in spatio-temporal data analyses. The source code is publicly available at https://github.com/diku-dk/hastl. An artifact that allows the experimental results to be reproduced is available at https://sid.erda.dk/sharelink/hOUrqJJ FfA. ",
keywords = "Climate Change, Parallel Implementation, Remote Sensing, Time Series Data, Trend Analysis",
author = "Dmitry Serykh and Stefan Oehmcke and Cosmin Oancea and Dainius Masiliunas and Jan Verbesselt and Yan Cheng and Stephanie Horion and Fabian Gieseke and Nikolaj Hinnerskov",
note = "Funding Information: This work has been supported by the Independent Research Fund Denmark (DFF) under the grant: High-performance Architectures and Monitoring Changes in Big Satellite Data via Massively Parallel AI, and by the UCPH Data+ grant: High-Performance Land Change Assessment. Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Big Data, BigData 2023 ; Conference date: 15-12-2023 Through 18-12-2023",
year = "2023",
doi = "10.1109/BigData59044.2023.10386208",
language = "English",
pages = "5914--5923",
editor = "Jingrui He and Themis Palpanas and Xiaohua Hu and Alfredo Cuzzocrea and Dejing Dou and Dominik Slezak and Wei Wang and Aleksandra Gruca and Lin, {Jerry Chun-Wei} and Rakesh Agrawal",
booktitle = "Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Seasonal-Trend Time Series Decomposition on Graphics Processing Units

AU - Serykh, Dmitry

AU - Oehmcke, Stefan

AU - Oancea, Cosmin

AU - Masiliunas, Dainius

AU - Verbesselt, Jan

AU - Cheng, Yan

AU - Horion, Stephanie

AU - Gieseke, Fabian

AU - Hinnerskov, Nikolaj

N1 - Funding Information: This work has been supported by the Independent Research Fund Denmark (DFF) under the grant: High-performance Architectures and Monitoring Changes in Big Satellite Data via Massively Parallel AI, and by the UCPH Data+ grant: High-Performance Land Change Assessment. Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - In many domains, large amounts of time series data are being collected and analyzed in a semi-automatic manner. A prominent approach is the seasonal and trend decomposition using locally estimated scatterplot smoothing (STL) technique, which has been applied extensively in the past. However, STL quickly becomes computationally very expensive when applied to large data sets. In this work, we propose the first parallel implementation for the STL decomposition approach, which is tailored to the specific needs of graphics processing units (GPU). Our experimental evaluation on two global-scale case studies in temperature and vegetation trend analysis exhibits at least three-to-four orders of magnitude speed-up, demonstrating the effectiveness of the overall approach and the immense potential of the implementation in spatio-temporal data analyses. The source code is publicly available at https://github.com/diku-dk/hastl. An artifact that allows the experimental results to be reproduced is available at https://sid.erda.dk/sharelink/hOUrqJJ FfA.

AB - In many domains, large amounts of time series data are being collected and analyzed in a semi-automatic manner. A prominent approach is the seasonal and trend decomposition using locally estimated scatterplot smoothing (STL) technique, which has been applied extensively in the past. However, STL quickly becomes computationally very expensive when applied to large data sets. In this work, we propose the first parallel implementation for the STL decomposition approach, which is tailored to the specific needs of graphics processing units (GPU). Our experimental evaluation on two global-scale case studies in temperature and vegetation trend analysis exhibits at least three-to-four orders of magnitude speed-up, demonstrating the effectiveness of the overall approach and the immense potential of the implementation in spatio-temporal data analyses. The source code is publicly available at https://github.com/diku-dk/hastl. An artifact that allows the experimental results to be reproduced is available at https://sid.erda.dk/sharelink/hOUrqJJ FfA.

KW - Climate Change

KW - Parallel Implementation

KW - Remote Sensing

KW - Time Series Data

KW - Trend Analysis

U2 - 10.1109/BigData59044.2023.10386208

DO - 10.1109/BigData59044.2023.10386208

M3 - Article in proceedings

AN - SCOPUS:85184984790

SP - 5914

EP - 5923

BT - Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023

A2 - He, Jingrui

A2 - Palpanas, Themis

A2 - Hu, Xiaohua

A2 - Cuzzocrea, Alfredo

A2 - Dou, Dejing

A2 - Slezak, Dominik

A2 - Wang, Wei

A2 - Gruca, Aleksandra

A2 - Lin, Jerry Chun-Wei

A2 - Agrawal, Rakesh

PB - IEEE

T2 - 2023 IEEE International Conference on Big Data, BigData 2023

Y2 - 15 December 2023 through 18 December 2023

ER -

ID: 385219280