Rubiños et al. (2026) Monitoring the Dynamics of Water Consumption from Time Series Using Machine Learning Techniques

Identification

• Journal: Lecture notes in networks and systems
• Year: 2026
• Date: 2026-01-01
• Authors: Manuel Rubiños, Agustín García-Fischer, Noel Freire-Mahía, H.éctor Quintián
• DOI: 10.1007/978-3-032-05504-0_8

Research Groups

• Department of Industrial Engineering, University of A Coruña, CTC, CITIC, Ferrol, A Coruña, Spain

Short Summary

This study applies machine learning techniques, specifically dimensionality reduction and clustering, to analyze the dynamics of urban water consumption from time series data over an entire year, aiming to improve resource management in the face of water scarcity.

Objective

• To analyze the dynamics of water consumption in urban areas using machine learning techniques (dimensionality reduction and clustering) to support more efficient resource management and prediction.

Study Configuration

• Spatial Scale: Urban areas, specifically within a water grid.
• Temporal Scale: An entire year.

Methodology and Data

• Models used: Dimensionality reduction techniques, clustering techniques.
• Data sources: Time series data of water consumption, likely from smart meters.

Main Results

• The study successfully applied dimensionality reduction and clustering techniques to monitor and analyze the dynamics of water consumption throughout an entire year.
• This analysis provides insights into user behavior patterns within a water grid, which is crucial for efficient resource management.

Contributions

• The article contributes by demonstrating the application of machine learning for characterizing water consumption dynamics from time series data, offering a foundational step towards predictive and anticipatory water resource management in urban environments.

Funding

• CITIC (Galician University System, CIGUS Network) subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia, co-financed by the EU through the FEDER Galicia 2021–27 operational program (Ref. ED431G 2023/01).
• Strategic Project “Critical infrastructures cybersecure through intelligent modeling of attacks, vulnerabilities and increased security of their IoT devices for the water supply sector” (C061/23), funded by the National Institute of Cybersecurity (INCIBE) and the University of A Coruña, within the framework of the Recovery Plan, Transformation and Resilience Plan funds, financed by the European Union (Next Generation).
• Xunta de Galicia, Grants for the consolidation and structuring of competitive research units, GPC (ED431B 2023/49).
• Grant PID2022-137152NB-I00 funded by MICIU/AEI/10.13039/501100011033 and by ERDF/EU.

Citation

@article{Rubiños2026Monitoring,
  author = {Rubiños, Manuel and García-Fischer, Agustín and Freire-Mahía, Noel and Quintián, H.éctor},
  title = {Monitoring the Dynamics of Water Consumption from Time Series Using Machine Learning Techniques},
  journal = {Lecture notes in networks and systems},
  year = {2026},
  doi = {10.1007/978-3-032-05504-0_8},
  url = {https://doi.org/10.1007/978-3-032-05504-0_8}
}