Imputation of Missing Weather Data in Automatic Weather Station Using the GRU Algorithm
DOI:
https://doi.org/10.30871/jaic.v10i2.12301Keywords:
AWS, Imputation, Machine Learning, GRU, WeatherAbstract
Missing data in Automatic Weather Stations (AWS) due to sensor failure or communication errors poses a significant challenge to the accuracy of weather and climate modeling. Traditional imputation methods often struggle with the complex temporal patterns of meteorological data. This study evaluates the performance of the Gate Recurrent Unit (GRU) algorithm for imputing missing air temperature and humidity data. The research utilized meteorological data from three AWS locations in Banten Province (AWS Staklim Banten, Golf Modern, and BSD Serpong) collected between January 2022 and January 2024. The model was tested using simulated missing data scenarios ranging from 5% to 50% and evaluated using R2, RMSE, and MAPE metrics. The results demonstrate that the GRU model achieves high accuracy, maintaining a strong correlation (R2 > 0.9) with actual sensor data even at high missing rates. The average MAPE was recorded at 1.79% for air temperature and 3.92% for humidity. Furthermore, the RMSE values met the precision criteria and measurement uncertainty limits set by the World Meteorological Organization (WMO). The study concludes that the GRU algorithm is a computationally efficient and highly accurate method for handling missing time-series weather data.
Downloads
References
[1] T. T. K. Tran, S. M. Bateni, S. J. Ki, and H. Vosoughifar, “A Review of Neural Networks for Air Temperature Forecasting,” Water (Basel)., vol. 13, no. 9, p. 1294, May 2021, doi: 10.3390/w13091294.
[2] S. Naderi, S. Heslop, D. Chen, I. MacGill, and G. Pignatta, “Consumer cost savings, improved thermal comfort, and reduced peak air conditioning demand through pre-cooling in Australian housing,” Energy Build., vol. 271, p. 112172, Sep. 2022, doi: 10.1016/j.enbuild.2022.112172.
[3] A. F. Radjab, H. Akib, Rifdan, and Jasruddin, “Partnership in Weather Observation using the Crowdsourcing Method,” IOP Conf. Ser. Earth Environ. Sci., vol. 499, no. 1, p. 012019, Jun. 2020, doi: 10.1088/1755-1315/499/1/012019.
[4] A. Furqon, N. Ananda, and S. Soekirno, “Development of Vessel Automatic Weather Station Using Smart Weather Sensor Based on Internet of Things,” in 2025 International Conference on Smart-Green Technology in Electrical and Information Systems (ICSGTEIS), IEEE, Oct. 2025, pp. 123–127. doi: 10.1109/ICSGTEIS68532.2025.11284441.
[5] A. Ariffudin and P. Musa, “Analisa sistem komunikasi data berbasis Internet of Things (IoT) menggunakan metode PIECES pada Sistem Pengamatan Cuaca Otomatis di Badan Meteorologi Klimatologi dan Geofisika (BMKG),” Jurnal Meteorologi dan Geofisika, vol. 23, no. 2, p. 81, Jun. 2022, doi: 10.31172/jmg.v23i2.831.
[6] A. Kurniawan, “Evaluasi Pengukuran Curah Hujan Antara Hasil Pengukuran Permukaan (AWS, HELLMAN, OBS) dan Hasil Estimasi (Citra Satelit =GSMaP) Di Stasiun Klimatologi Mlati Tahun 2018,” Jurnal Geografi, Edukasi dan Lingkungan (JGEL), vol. 4, no. 1, pp. 1–7, Jan. 2020, doi: 10.29405/jgel.v4i1.3797.
[7] M. Vélez-Nicolás, S. García-López, V. Ruiz-Ortiz, S. Zazo, and J. L. Molina, “Precipitation Variability and Drought Assessment Using the SPI: Application to Long-Term Series in the Strait of Gibraltar Area,” Water (Basel)., vol. 14, no. 6, p. 884, Mar. 2022, doi: 10.3390/w14060884.
[8] A. Gharehbaghi, R. Ghasemlounia, F. Ahmadi, and M. Albaji, “Groundwater level prediction with meteorologically sensitive Gated Recurrent Unit (GRU) neural networks,” J. Hydrol. (Amst)., vol. 612, p. 128262, Sep. 2022, doi: 10.1016/j.jhydrol.2022.128262.
[9] D. M. Asad, M. Shahriar, and A. H. Chowdhury, “Load Forecasting for Dhaka City Using RNN, LSTM, and GRU Architectures with Meteorological and Temporal Data,” in 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), IEEE, Feb. 2025, pp. 1–6. doi: 10.1109/ECCE64574.2025.11013779.
[10] J. Liu et al., “Assessment of Flood Susceptibility Using Support Vector Machine in the Belt and Road Region,” May 25, 2021. doi: 10.5194/nhess-2021-80.
[11] C. Chen et al., “Forecast of rainfall distribution based on fixed sliding window long short-term memory,” Engineering Applications of Computational Fluid Mechanics, vol. 16, no. 1, pp. 248–261, 2022, doi: 10.1080/19942060.2021.2009374.
[12] H. S. Wicaksana, S. Winarko, and D. Kurniadi, “Treatment on Missing Data of Wind Speed Measurement in Automatic Weather Station Using Multivariate Imputation Chained Equation,” in 2023 8th International Conference on Instrumentation, Control, and Automation (ICA), IEEE, Aug. 2023, pp. 81–85. doi: 10.1109/ICA58538.2023.10273106.
[13] R. Pahlepi, S. Soekirno, and H. S. Wicaksana, “Solar Radiation Intensity Imputation in Pyranometer of Automatic Weather Station Based on Long Short Term Memory,” Ultima Computing : Jurnal Sistem Komputer, pp. 35–40, Dec. 2023, doi: 10.31937/sk.v15i2.3348.
[14] C. A. Fiebrich, C. R. Morgan, A. G. McCombs, P. K. Hall, and R. A. McPherson, “Quality Assurance Procedures for Mesoscale Meteorological Data,” J. Atmos. Ocean. Technol., vol. 27, no. 10, pp. 1565–1582, Oct. 2010, doi: 10.1175/2010JTECHA1433.1.
[15] WMO, “Guide to Instruments and Methods of Observation WMO-No. 8,” Geneva, 2021.
[16] S. Soekirno et al., “Design of drought early warning system based on standardized precipitation index prediction using hybrid ARIMA-MLP in Banten province,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 2, p. 1878, Jun. 2024, doi: 10.11591/ijai.v13.i2.pp1878-1887.
[17] G. Akbar, P. Prajitno, Ariffudin, and N. Ananda, “Multivariate Imputation Chained Equation on Solar Radiation in Automatic Weather Station,” Jurnal Penelitian Pendidikan IPA, vol. 10, no. 7, pp. 3633–3639, Jul. 2024, doi: 10.29303/jppipa.v10i7.7679.
[18] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623.
[19] W.-C. Lin and C.-F. Tsai, “Missing value imputation: a review and analysis of the literature (2006–2017),” Artif. Intell. Rev., vol. 53, no. 2, pp. 1487–1509, Feb. 2020, doi: 10.1007/s10462-019-09709-4.
[20] Z. S. Venter, T. Chakraborty, and X. Lee, “Crowdsourced air temperatures contrast satellite measures of the urban heat island and its mechanisms,” 2021. [Online]. Available: https://www.science.org
[21] F. R. G. Cruz, M. G. Binag, M. R. G. Ga, and F. A. A. Uy, “Multi-Layered Artificial Neural Network Flood Prediction System with Rain Gauge, Temperature Humidity Pressure Sensor, Ultrasonic Sensor, Soil Moisture Sensor and Anemometer,” in 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM ), IEEE, Nov. 2019, pp. 1–6. doi: 10.1109/HNICEM48295.2019.9072733.
[22] G. Teshome Nigatu, B. A. Abebe, B. Grum, M. G. Kebedew, and E. M. Semane, “Investigation of flood incidence causes and mitigation: Case study of Ribb river, northwestern Ethiopia,” Natural Hazards Research, vol. 3, no. 3, pp. 408–419, Sep. 2023, doi: 10.1016/j.nhres.2023.04.009.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Kustita Rhamadania, Makhsun Makhsun, Choirul Basir, Naufal Ananda
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
