Flatline Anomaly Detection in Automatic Weather Station Air Temperature Sensor Data Using LSTM Autoencoder
DOI:
10.29303/jppipa.v12i4.14486Published:
2026-04-25Downloads
Abstract
The quality of air temperature data from Automatic Weather Stations (AWS) is crucial for meteorological analysis, climatology, and early warning systems. However, flatline anomalies, a condition where sensor values tend to remain constant over a period of time, can degrade data quality and are often not optimally detected by conventional rule-based quality control (QC) methods. Previous research is also limited in specifically examining flatline detection, with most studies focusing on general anomalies and not integrating deep learning approaches with operational quality control systems. This study proposes a data-driven approach using a Long Short-Term Memory Autoencoder (LSTM-AE) combined with Level-1 QC. The novelty of this study lies in the use of a normal-only training scheme, anomaly threshold determination based on the reconstruction error distribution, and post-detection diagnosis to identify flatline characteristics. The methods include QC filtering, sliding window formation, model training, threshold determination, and anomaly detection. The results show stable model performance with an anomaly threshold value of 0.01177 (MSE). Of the 985,730 data windows, approximately 0.578% were detected as anomalies, indicating that flatline occurrences are relatively small but still significant to data quality. Most anomalies are short-lived and discontinuous, indicating localized sensor noise. This study demonstrates that LSTM-AE is effective as an adaptive flatline detection method and has the potential to be implemented as an automated QC module in AWS systems to improve data reliability.
Keywords:
Air temperature data Automatic Weather Station Flatline anomaly LSTM-AE Quality controlReferences
Afif, M., & Aly, D. (2023). Predictive Maintenance for Automatic Weather Station ( AWS ) Based on Anomaly Detection Using Autoencoder : A Literature Review. 3(2), 57–64.
Akbar, G., Prajitno, P., & Ananda, N. (2024). Multivariate Imputation Chained Equation on Solar Radiation in Automatic Weather Station. 10(7), 3633–3639. https://doi.org/10.29303/jppipa.v10i7.7679
Al, K. E. T., & Land, D. M. (2024). Near-Surface Air Temperature Records over the Past 30 Years in the Interior of. Near-Surface Air Temperature Records over the Past 30 Years in the Interior Of, 179–188. https://doi.org/10.1175/JTECH-D-23-0092.1
Angela, D., Nugroho, T. A., Gultom, B., & Yonata, Y. (2023). Perancangan Sensor Kecepatan dan Arah Angin untuk Automatic Weather Station ( AWS ). 12(1).
Attribution, C. C., & Republic, C. (2009). 8th EMS Annual Meeting and 7th European Conference on Applied Climatology 2008 Data quality control and homogenization of air temperature and precipitation series in the area of the Czech Republic in the period 1961 – 2007. 23–26.
Azad, M., Raghuwanshi, S., & Jain, M. (n.d.). Advances in Deep Learning for Multivariate Time-Series Anomaly Detection. 2024 International Conference on Communication, Control, and Intelligent Systems (CCIS), 1–6. https://doi.org/10.1109/CCIS63231.2024.10932064
Bashar, A., & Nayak, R. (2025). ALGAN : Time Series Anomaly Detection with Adjusted-LSTM GAN. International Journal of Data Science and Analytics, 20(6), 5719–5737. https://doi.org/10.1007/s41060-025-00810-2
Cerlini, P. B., Silvestri, L., & Saraceni, M. (2020). Quality control and gap-filling methods applied to hourly temperature observations over central Italy. December 2019, 1–15. https://doi.org/10.1002/met.1913
Costa, R. L., Duarte, D., Pinto, C., Lins, R., Gomes, H. B., Cristina, M., & Lu, D. (2021). Gap Filling and Quality Control Applied to Meteorological Variables Measured in the Northeast Region of Brazil. 1–21.
Ding, X. (2025). Multivariate Time Series Anomaly Detection Using Working Memory Connections in Bi-Directional Long Short-Term Memory Autoencoder Network.
Edkayasa, M. T., & Yuliza, E. (2025). Impact of El Niño - Southern Oscillation ( ENSO ) and Indian Ocean Dipole ( IOD ) on Air Temperature in Bengkulu City. 9(1), 59–77. https://doi.org/10.70561/geocelebes.v9i1.43409
Farooq, A., Zainab, I., Farooq, H., Datti, A. D., & Haider, H. (2025). Climatological Variability of Diurnal Temperature Range across Pakistan during Transitional Seasons and Its Link to Indian Ocean SST Anomalies ( 1980-2016 ). 13(5), 200–229. https://doi.org/10.4236/gep.2025.135014
Faybishenko, B., Pastorello, G., & Agarwal, D. (n.d.). Challenging Problems of Quality Assurance and Quality Control ( QA / QC ) of Meteorological Time Series Data.
Fitri, H. T. (2022). Validasi Data Pengamatan Pararel : Automatic Weather Station ( AWS ) dan Pengamatan Manual di Stasiun Meteorologi Hasanuddin Makassar Tahun 2019 Validation of Parallel Observation Data : Automatic Weather Station ( AWS ) and Manual Observation at the Hasanuddin Meteorology Station , Makassar in 2019. 2, 79–87.
Gao, H., Chen, Y., Li, K., Zhou, J., Member, S., Xia, H., & Ji, W. (2026). Method for Reconstruction of Hourly ∼ 1-km All-Weather Land Surface Temperature From FY-4A Geostationary Satellite Observations. IEEE Transactions on Geoscience and Remote Sensing, 64, 1–12. https://doi.org/10.1109/TGRS.2026.3673743
Givnan, S., Chalmers, C., Fergus, P., & Ortega-martorell, S. (2022). Anomaly Detection Using Autoencoder Reconstruction upon Industrial Motors.
González, G. G., Tagliafico, S. M., Fernández, A., Sena, G. G., Acuña, J., & Casas, P. (2024). One Model to Find Them All Deep Learning for Multivariate Time-Series Anomaly Detection in Mobile Network Data. 21(2), 1601–1616. https://doi.org/10.1109/TNSM.2023.3340146
Irfan, M., Saleh, K., Kurniawati, N., & Irfan, M. (2025). Dynamics of Daily Rainfall Characteristics in Sumatran Peatlands in Relation to El Niño – Southern Oscillation ( ENSO ) and Indian Ocean Dipole ( IOD ). 11(11), 1–8. https://doi.org/10.29303/jppipa.v11i11.13324
Isnianto, H. N., Puspitaningrum, E., Diploma, P., Elektro, T., & Vokasi, S. (2012). RANCANG BANGUN SISTEM TELEMETRI DAN MONITORING. 2012(semnasIF), 51–58.
Issn, E., & Issn, P. (2025). SYSTEM USABILITY EVALUATION OF THE DIGITAL AUTOMATIC WEATHER SYSTEM AT. 9(2), 107–113.
Jasra, S. K., Valentino, G., Muscat, A., & Camilleri, R. (2025). A Comparative Study of Unsupervised Deep Learning Methods for Anomaly Detection in Flight Data. 1–33.
Jo, E., Lee, J., Kim, M., Lee, J., Introduction, I., & Computing, A. C. (2025). A Deep Learning-Based Abnormal Detection Study Using Cloud Time Series. 19(2), 37–45.
Kanata, B., Zubaidah, T., Yadnya, M. S., & Zainuddin, A. (2024). Unraveling the Seismic Signal Anomaly at Mount Rinjani Station : In-Depth Exploration with the Detrended Fluctuation ( DFA ) Analysis Method in Connection with the 2018 Big Earthquake on Lombok Island , West Nusa Tenggara. 10(1), 116–123. https://doi.org/10.29303/jppipa.v10i1.6263
Karevan, Z., & Suykens, J. A. K. (2020). Transductive LSTM for time-series prediction : An application to weather forecasting. Neural Networks, 125, 1–9. https://doi.org/10.1016/j.neunet.2019.12.030
Kim, H., Park, S. M., Choi, B. J., Moon, S., & Kim, Y. (2020). Spatiotemporal Approaches for Quality Control and Error Correction of Atmospheric Data through Machine Learning. 2020.
Kiran, S. (2025). Real-Time Anomaly Detection in Streaming Sensor Data Using LSTM Autoencoders. October.
Kirichenko, L., Koval, Y., Yakovlev, S., & Chumachenko, D. (2024). Anomaly Detection in Fractal Time Series with LSTM Autoencoders.
Lee, Y., Park, C., Kim, N., & Ahn, J. (2024). LSTM-Autoencoder Based Anomaly Detection Using Vibration Data of Wind Turbines. 1–24.
Li, J., Malialis, K., & Polycarpou, M. M. (n.d.). Autoencoder-based Anomaly Detection in Streaming Data with Incremental Learning and Concept Drift Adaptation.
Liu, Q., Boniol, P., Palpanas, T., Paparrizos, J., Liu, Q., Boniol, P., Palpanas, T., Paparrizos, J., Detection, T. A., Boniol, P., & Paparrizos, J. (2024). Time-Series Anomaly Detection : Overview and New Trends To cite this version : HAL Id : hal-04708918 Time-Series Anomaly Detection : Overview and New Trends. https://doi.org/10.14778/3685800.3685842
Mardyansyah, R. Y., Kurniawan, B., Soekirno, S., & Nuryanto, D. E. (2024). Communication Satellite-Based Rainfall Estimation for Flood Mitigation in Papua. 10(12), 11326–11335. https://doi.org/10.29303/jppipa.v10i12.8409
Nsabagwa, M., Byamukama, M., Kondela, E., & Otim, J. S. (2024). Towards a robust and a ff ordable Automatic Weather Station. Development Engineering, 4(May 2018), 100040. https://doi.org/10.1016/j.deveng.2018.100040
Prada Wellyantama. (2021). Deteksi Dini Kesalahan Sistem Sensor Temperatur, Tekanan, Kelembaban Dan Curah Hujan Pada Automatic Weather Station (AWS) Berbasis Artificial Neural Network (ANN) = Sistem Sensor Suhu, Tekanan, Relative Humidity dan Curah Hujan Deteksi Kesalahan Dini Untu. Deteksi Dini Kesalahan Sistem Sensor Temperatur, Tekanan, Kelembaban Dan Curah Hujan Pada Automatic Weather Station (AWS) Berbasis Artificial Neural Network (ANN) = Sistem Sensor Suhu, Tekanan, Relative Humidity Dan Curah Hujan Deteksi Kesalahan Dini Untu.
Raihan, A. S., & Ahmed, I. (n.d.). A Bi-LSTM Autoencoder Framework for Anomaly Detection – A Case Study of a Wind Power Dataset.
Rohmah, D. Z., & Utomo, B. S. (2024). Development of an Automatic Portable Calibrator for Tipping Bucket Rain Gauge ( TBRG ) Using a Load Cell and Simple Water Sensor. 10(9), 6746–6755. https://doi.org/10.29303/jppipa.v10i9.7634
Setiyo, E. (2020). Development of mechanics techniques learning media-based three-dimensional flipbook. In Journal of Physics: Conference Series (Vol. 1446, Issue 1). https://doi.org/10.1088/1742-6596/1446/1/012046
Siregar, M. R. T., Multi, A., Wicaksana, H. S., No, J. A., & Pusat, J. (2023). Estimasi Sensor Temperatur Udara Automatic Weather Station Menggunakan Algoritma Hybrid Arima-MLP. 33(3), 42–48.
Sunusi, N. (2022). Bias of automatic weather parameter measurement in monsoon area , a case study in Makassar Coast. 10(June), 1–15. https://doi.org/10.3934/environsci.2023001
Tridaiana, S., & Marzuki, M. (2023). Exploring the Complex Dynamics of Tropical Cyclone Activity in the Southern Indian Ocean : A Multidecade Analysis. 9(11), 1069–1077. https://doi.org/10.29303/jppipa.v9i11.5601
Varet, H., Brillet-guéguen, L., Coppée, J., & Dillies, M. (2016). SARTools : A DESeq2- and EdgeR-Based R Pipeline for Comprehensive Differential Analysis of RNA-Seq Data. 1–9. https://doi.org/10.1371/journal.pone.0157022
Wahyusari, R., Wibowo, L., Studi Teknik Elektro, P., Tinggi Teknologi Ronggolawe Cepu Jln Kampus Ronggolawe Blok No, S. B., & Cepu, M. (2021). Pengembangan Media Pembelajaran Menggunakan Capasitive Sensor Dan Arduino Uno. Jurnal Informatika & Rekayasa Elektronika), 4(2), 155–162. http://e-journal.stmiklombok.ac.id/index.php/jireISSN.2620-6900
Wang, F., Jiang, Y., Zhang, R., Wei, A., Xie, J., & Pang, X. (2025). A Survey of Deep Anomaly Detection in Multivariate Time Series : Taxonomy , Applications , and Directions. I, 1–28.
Wei, Y., Jang-jaccard, J., Xu, W., Sabrina, F., Camtepe, S., & Boulic, M. (2024). LSTM-Autoencoder based Anomaly Detection for Indoor Air Quality Time Series Data.
Wibawanty, D. R. (2022). Verifikasi Kinerja Alat Automatic Weather System ( AWS ) dan Termometer Digital terhadap Observasi Manual di Stasiun Klimatologi Palembang Verification of The Performance of Automatic Weather Station ( AWS ) and Digital Thermometer Instruments towards Man. 6(2), 151–163.
Yahya, M. A., Moya, A. R., & Ventura, S. (2025). Deep learning for multivariate time series anomaly detection : an evaluation of reconstruction-based methods.
Yuniarto, A., & Septiadi, D. (2020). Jurnal Pengembangan Energi Nuklir Komparasi Data Pemantauan Cuaca antara Stasiun Meteorologi Di Tapak RDNK dan KNS untuk Proses Perizinan. 21(2), 115–124.
License
Copyright (c) 2026 Supriyatna, Santoso Soekirno, Martarizal, Djati Handoko
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with Jurnal Penelitian Pendidikan IPA, 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 4.0 International License (CC-BY License). This license allows authors to use all articles, data sets, graphics, and appendices in data mining applications, search engines, web sites, blogs, and other platforms by providing an appropriate reference. The journal allows the author(s) to hold the copyright without restrictions and will retain publishing rights without restrictions.
- 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 acknowledgment of its initial publication in Jurnal Penelitian Pendidikan IPA.
- 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).
