Estimasi Kecepatan Angin Permukaan pada Jaringan Anemometer Menggunakan Temporal Convolutional Network

Haryas Wicaksana; Faqihza  Mukhlish; Naufal  Ananda; Irvan  Budiawan; Arif Nur  Khamdi; Abdul Hamid Al  Habib

doi:10.5614/joki.2024.16.1.5

Authors

Haryas Wicaksana (1) Program Studi Instrumentasi dan Kontrol, Fakultas Teknologi Industri, Institut Teknologi Bandung; (2) Pusat Instrumentasi, Kalibrasi dan Rekayasa, Badan Meteorologi Klimatologi dan Geofisika
Faqihza Mukhlish Kelompok Keahlian Fisika Teknik, Fakultas Teknologi Industri, Institut Teknologi Bandung
Naufal Ananda (1) Program Studi Instrumentasi dan Kontrol, Fakultas Teknologi Industri, Institut Teknologi Bandung; (2) Pusat Instrumentasi, Kalibrasi dan Rekayasa, Badan Meteorologi Klimatologi dan Geofisika
Irvan Budiawan Program Doktor Teknik Fisika, Fakultas Teknologi Industri, Institut Teknologi Bandung
Arif Nur Khamdi Stasiun Meteorologi Kelas I Juanda Surabaya, Badan Meteorologi Klimatologi dan Geofisika
Abdul Hamid Al Habib Program Studi Sains Kebumian, Fakultas Ilmu dan Teknologi Kebumian, Institut Teknologi Bandung

Keywords:

estimation, anemometer, wind speed, Temporal Convolutional Network

Abstract

Surface winds in various locations are measured simultaneously using a multisite anemometer network. This network is susceptible to system failures due to sensor damage, causing a data gap during sensor removal and reinstallation. This research develops a wind speed estimation model on a multisite anemometer using the Temporal Convolutional Network (TCN) algorithm. TCN processes time domain signals in parallel, thus significantly cutting the computation time. Minutely wind speed data set was obtained from four anemometers at Juanda International Airport in Surabaya from January 1, 2022 – December 24, 2023. The model design comprises data pre-processing, dominant wind direction analysis, hyperparameter determination, training, and testing on actual data. TCN estimation models are divided into easterly, westerly, transitional, and all-directional models. These wind speed estimation models strongly correlate with actual data, with correlation coefficients of 0.70, 0.77, and 0.87. Overall, the accuracy of the TCN-based estimation model conforms to World Meteorological Organization (WMO) requirements for wind speed measurements. It achieves RMSE<5 m/s and MAE<3 m/s. As for computation duration, TCN processes the training for 87 seconds per epoch and completes the estimation in 37 seconds, much faster than CNN-BiDLSTM’'s training duration of 2206 seconds per epoch and estimation completion of 548 seconds.

References

R. V. Rohli and A. J. Vega, Climatology. Jones & Bartlet Learning, 2018.

P. P. Battista, G. Maracchi, F. Sabatini, M. V. K. Sivakumar & A. Zaldei. Training Center Manual on Instrumentation and Operations for Automatic Weather Stations for Agrometeorological Application. 2000.

Badan Meteorologi Klimatologi dan Geofisika. Peraturan Kepala BMKG Nomor 7 Tahun 2014 tentang Standar Teknis dan Operasional Pemeliharaan Peralatan Pengamatan Meteorologi, Klimatologi dan Geofisika. 2014.

Badan Meteorologi Klimatologi dan Geofisika. Peraturan Kepala BMKG Nomor 23 Tahun 2015 tentang Tata Cara Tetap Pelaksanaan Kalibrasi Peralatan Pengamatan Meteorologi, Klimatologi dan Geofisika. 2015.

Y. Li, & X. Shen, “A Novel Wind Speed-Sensing Methodology for Wind Turbines Based on Digital Twin Technology.” IEEE Transactions on Instrumentation and Measurement, 71, 2022. https://doi.org/10.1109/TIM.2021.3139698.

S. Bai, J. Z. Kolter, & V. Koltun, An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. 2018. [Online]. Available: http://arxiv.org/abs/1803.01271.

P. Hewage, A. Behera, M. Trovati, E. Pereira, M. Ghahremani, F. Palmieri, & Y. Liu, “Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station.” Soft Computing, 24(21), 16453–16482, 2020. https://doi.org/10.1007/s00500-020-04954-0.

International Civil Aviation Organization. Manual on Low-level Wind Shear (1st ed., Vol. 1). ICAO. 2005. [Online]. Available: http://www.icao.int.

Tim Bidang Analisis Variabilitas Iklim Pusat Informasi Perubahan Iklim Kedeputian Klimatologi. Pemutakhiran Zona Musim Indonesia Periode 1991-2020. 2022.

T. B. Pepinsky, “A Note on Listwise Deletion versus Multiple Imputation.” Political Analysis, 26(4), 480–488, 2018. https://doi.org/10.1017/pan.2018.18.

T. Emmanuel, T. Maupong, D. Mpoeleng, T. Semong, B. Mphago, & O. Tabona, “A survey on missing data in machine learning.” Journal of Big Data, 8(1). 2021. https://doi.org/10.1186/s40537-021-00516-9.

S. van Buuren, & K. Groothuis-Oudshoorn, “MICE: Multivariate Imputation by Chained Equations in R,”. Journal of Statistical Software, 45(3), 1–67, 2011. https://doi.org/10.18637/jss.v045.i03.

A. Adib, S. S. O. Kalantarzadeh, M. M. Shoushtari, M. Lotfirad, A. Liaghat, & M. Oulapour, “Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration.” Applied Water Science, 13(3). 2023. https://doi.org/10.1007/s13201-023-01895-5.

Y. Lin, I. Koprinska & M. Rana, “Temporal Convolutional Attention Neural Networks for Time Series Forecasting,” Proceedings of the International Joint Conference on Neural Networks, 2021-July. https://doi.org/10.1109/IJCNN52387.2021.9534351.

R. Wan, S. Mei, J. Wang, M. Liu, & F. Yang, “Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting,” Electronics (Switzerland), 8(8), 2019. https://doi.org/10.3390/electronics8080876.

P. Lara-Benítez, M. Carranza-García, J. M. Luna-Romera & J. C. Riquelme, “Temporal convolutional networks applied to energy-related time series forecasting.” Applied Sciences (Switzerland), 10(7), 2020. https://doi.org/10.3390/app10072322.

F. Yu, & V. Koltun, “Multi-Scale Context Aggregation by Dilated Convolutions,”. ICLR, 2016, November 23. [Online]. Available: http://arxiv.org/abs/1511.07122.

K. He, X. Zhang, S. Ren & J. Sun, “Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, December 10. [Online]. Available: http://arxiv.org/abs/1512.03385.

A. Botchkarev, “A new typology design of performance metrics to measure errors in machine learning regression algorithms,” Interdisciplinary Journal of Information, Knowledge, and Management, 14, 45–76, 2019. https://doi.org/10.28945/4184.

P. Schober, & L. A. Schwarte, “Correlation coefficients: Appropriate use and interpretation,” Anesthesia and Analgesia, 126(5), 1763–1768, 2018. https://doi.org/10.1213/ANE.0000000000002864.

W. Meteorological Organization, Technical Guidelines for Regional WIGOS Centres on the WIGOS Data Quality Monitoring System. 2018. [Online]. Available: http://public.wmo.int/en/.

C. A. Fiebrich, Y. R. Morgan, A. G. McCombs, P. K. Hall & R. A. McPherson, “Quality assurance procedures for mesoscale meteorological data,” Journal of Atmospheric and Oceanic Technology, 27(10), 1565–1582. 2010. https://doi.org/10.1175/2010JTECHA1433.1.