International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 18, No. 2, 8 Apr. 2026
Cover page and Table of Contents: PDF (size: 1492KB)
A Data-Driven Temporal Framework for Water Consumption Monitoring with Spatial Visualization Using K-Means and STL-LSTM
PDF (1492KB), PP.208-225
Views: 0 Downloads: 0
Author(s)
Salsabila Septi Sukmayanti
1
Sudianto Sudianto
1,*
Aminatus Saadah
1
Index Terms
Consumption Pattern, K-Means, STL-LSTM, Spatial Prediction, Water Consumption Forecasting
Abstract
The water distribution sector in Indonesia still faces challenges in detecting leaks early due to manual data checks that are time-consuming and labor-intensive. PDAM (Regional Water Company) Tirta Wijaya Cilacap, Indonesia, faces similar problems. This study aims to implement a spatial customer prediction model to detect customer water usage and support data-driven operational decision-making. K-Means clustering groups customers by consumption patterns and geographic location, achieving a Silhouette Score of 0.4473 and a Davies–Bouldin Index of 0.7658, which indicates reasonably well-separated clusters in real-world data. In addition, water consumption forecasting was carried out with Seasonal–Trend Decomposition using Loess–Long Short-Term Memory (STL–LSTM) to predict trends and seasonality of water usage for each Customer Connection ID (CCID). The forecasting performance varies across CCIDs; the best case achieves an R2 of up to 0.95, while low-performing cases are discussed to clarify conditions where STL–LSTM is less reliable. The forecasting and clustering outputs are presented through a spatial visualization (map) of water-consumption categories and model results to support identifying areas that may require closer inspection for potential leakage and waste. This research contributes to strengthening technology-based public infrastructure, in line with SDG 9: Industry, Innovation, and Infrastructure, to promote sustainable water management.
Cite This Paper
Salsabila Septi Sukmayanti, Sudianto Sudianto, Aminatus Sa'adah, "A Data-Driven Temporal Framework for Water Consumption Monitoring with Spatial Visualization Using K-Means and STL-LSTM", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.2, pp. 208-225, 2026. DOI:10.5815/ijigsp.2026.02.11
Reference
[1]Satija, K. and Chhatlani, M.: Infrastructure and industrialization: An SDG-9 study of Gujarat. International Journal of Science and Social Science Research 3(1), 310–315 (2025)
[2]J. C. Carrasco-Jime´nez, F. Baldaro, and F. Cucchietti, “Detection of Anomalous Patterns in Water Consumption: An Overview of Approaches,” in Intelligent Systems and Applications, vol. 1250, K. Arai, S. Kapoor, and R. Bhatia, Eds., Advances in Intelligent Systems and Computing. Cham: Springer International Publishing, 2021, pp. 19–33, doi: 10.1007/978-3-030-55180-3 2.
[3]F. Ali, D. L. Lestari, M. D. Putri, and K. N. Azmi, “Strategy Analysis for the Fulfilment of Clean Water Needs Through Piped-Water Service in Metropolitan City during the COVID-19 Pandemic,” International Journal of Technology, vol. 15, no. 5, p. 1237, Sep. 2024, doi: 10.14716/ijtech.v15i5.6160.
[4]“Tirta Wijaya – Siap melayani kebutuhan air bersih masyarakat Cilacap,” Accessed: Dec. 12, 2025. [Online]. Available: https://www.pdamcilacap.co.id/
[5]G. Rajan and S. Li, “A Systematic Literature Review on Flow Data-Based Techniques for Automated Leak Management in Water Distribution Systems,” Smart Cities, vol. 8, no. 3, p. 78, Apr. 2025, doi: 10.3390/smartcities8030078.
[6]H. Guo, X. Liu, and Q. Zhang, “Identifying daily water consumption patterns based on K-means Clustering, Agglomerative Hierarchical Clustering, and Spectral Clustering algorithms,” AQUA – Water Infrastructure, Ecosystems and Society, vol. 73, no. 5, pp. 870–887, May 2024, doi: 10.2166/aqua.2024.294.
[7]F. A. H. Irfansyah, Deteksi Anomali Pada Segmentasi Konsumsi Air Pelanggan PDAM dengan Metode K-Means Dalam bentuk buku karya ilmiah. Universitas Telkom, S1 Teknologi Informasi (Kampus Surabaya), 2024. Accessed: Oct. 30, 2025. [Online]. Available: https://openlibrary.telkomuniversity.ac.id/pustaka/213437/deteksi-anomali-padasegmentasi-konsumsi-air-pelanggan-pdam-dengan-metode-k-means-dalam-bentuk-buku-karya-ilmiah.html
[8]K.-M. Koo, K.-H. Han, K.-S. Jun, G. Lee, J.-S. Kim, and K.-T. Yum, “Performance Assessment for Short-Term Water Demand Forecasting Models on Distinctive Water Uses in Korea,” Sustainability, vol. 13, no. 11, p. 6056, May 2021, doi: 10.3390/su13116056.
[9]J. Liu, “Forecasting Short-Term Water Demands with an Ensemble deep learning Model for a Water Supply System,” unpublished manuscript (details to be completed).
[10]M. R. Jhaerol and S. Sudianto, “Implementation of Chatbot for Merdeka Belajar Kampus Merdeka Program using Long Short-Term Memory,” J. Nas. Pendidik. Tek. Inform. (JANAPATI), vol. 12, no. 2, pp. 253–262, Jul. 2023, doi: 10.23887/janapati.v12i2.58794.
[11]M. S. Rahim, K. A. Nguyen, R. A. Stewart, T. Ahmed, D. Giurco, and M. Blumenstein, “A clustering solution for analyzing residential water consumption patterns,” Knowledge-Based Systems, vol. 233, p. 107522, Dec. 2021, doi: 10.1016/j.knosys.2021.107522.
[12]D. Chen, J. Zhang, and S. Jiang, “Forecasting the Short-Term Metro Ridership With Seasonal and Trend Decomposition Using Loess and LSTM Neural Networks,” IEEE Access, vol. 8, pp. 91181–91187, 2020, doi: 10.1109/ACCESS.2020.2995044.
[13]N.-H. Duong, M.-T. Nguyen, T.-H. Nguyen, and T.-P. Tran, “Application of Seasonal Trend Decomposition using Loess and Long Short-Term Memory in Peak Load Forecasting Model in Tien Giang,” Engineering, Technology & Applied Science Research, vol. 13, no. 5, pp. 11628–11634, Oct. 2023, doi: 10.48084/etasr.6181.
[14]S. Gadal, R. Mokhtar, M. Abdelhaq, R. Alsaqour, E. S. Ali, and R. Saeed, “Machine Learning-Based Anomaly Detection Using K-Mean Array and Sequential Minimal Optimization,” Electronics, vol. 11, no. 14, p. 2158, Jul. 2022, doi: 10.3390/electronics11142158.
[15]J. Li, H. Izakian, W. Pedrycz, and I. Jamal, “Clustering-based anomaly detection in multivariate time series data,” Applied Soft Computing, vol. 100, p. 106919, Mar. 2021, doi: 10.1016/j.asoc.2020.106919.
[16]J. P. Llerena Can˜a, J. Garc´ıa Herrero, and J. M. Molina Lo´pez, “Forecasting Nonlinear Systems with LSTM: Analysis and Comparison with EKF,” Sensors, vol. 21, no. 5, p. 1805, Mar. 2021, doi: 10.3390/s21051805.
[17]Q. Yu, B. A. Tolson, H. Shen, M. Han, J. Mai, and J. Lin, “Enhancing long short-term memory (LSTM)-based streamflow prediction with a spatially distributed approach,” Hydrology and Earth System Sciences, vol. 28, no. 9, pp. 2107–2122, May 2024, doi: 10.5194/hess-28-2107-2024.
[18]“A hybrid approach combining the multi-dimensional time series k-means algorithm and long short-term memory networks to predict the monthly water demand according to the uncertainty in the dataset,” doi: 10.1007/s12145023-00976-y. (Online source details to be completed.)
[19]S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[20]S. M. Al-Selwi et al., “RNN-LSTM: From applications to modeling techniques and beyond—Systematic review,” Journal of King Saud University Computer and Information Sciences, vol. 36, no. 5, p. 102068, Jun. 2024, doi: 10.1016/j.jksuci.2024.102068.
[21]I. D. Mienye, T. G. Swart, and G. Obaido, “Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications,” Information, vol. 15, no. 9, p. 517, Aug. 2024, doi: 10.3390/info15090517.
[22]V. Permadi, S. Tahalea, and R. Agusdin, “K-MEANS AND ELBOW METHOD FOR CLUSTER ANALYSIS OF ELEMENTARY SCHOOL DATA,” PROGRES Pendidik., vol. 4, pp. 50–57, Jan. 2023, doi: 10.29303/prospek.v4i1.328.
[23]D. Chicco, A. Campagner, A. Spagnolo, D. Ciucci, and G. Jurman, “The Silhouette coefficient and the DaviesBouldin index are more informative than Dunn index, Calinski-Harabasz index, Shannon entropy, and Gap statistic for unsupervised clustering internal evaluation of two convex clusters,” PeerJ Computer Science, vol. 11, p. e3309, Nov. 2025, doi: 10.7717/peerj-cs.3309.
[24]Y. Zhou, X. He, S. Wang, S. Hu, X. Sun, and J. Huang, “Hybrid GNSS time-series prediction method based on ensemble empirical mode decomposition with long short-term memory,” Discover Applied Sciences, vol. 7, no. 1, p. 61, Jan. 2025, doi: 10.1007/s42452-024-06409-9.
[25]Z. Aziz and R. Bestak, “Insight into Anomaly Detection and Prediction and Mobile Network Security Enhancement Leveraging K-Means Clustering on Call Detail Records,” Sensors, vol. 24, no. 6, p. 1716, Jan. 2024, doi: 10.3390/s24061716.
[26]A. M. Ikotun, F. Habyarimana, and A. E. Ezugwu, “Cluster validity indices for automatic clustering: A comprehensive review,” Heliyon, vol. 11, no. 2, 2025, doi: 10.1016/j.heliyon.2025.e41953.
[27]B. A. Hassan, N. B. Tayfor, A. A. Hassan, A. M. Ahmed, T. A. Rashid, and N. N. Abdalla, “From A-to-Z review of clustering validation indices,” Neurocomputing, vol. 601, p. 128198, Oct. 2024, doi: 10.1016/j.neucom.2024.128198.