Hybrid Attention Networks for Flow and Pressure Forecasting in Water Distribution Systems

• Published in: IEEE geoscience and remote sensing letters Vol. 19; pp. 1 - 5
• Main Authors: Ma, Ziqing, Liu, Shuming, Guo, Guancheng, Yu, Xipeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anomalies; Coders; Correlation; Decision making; Decoding; Deep learning; Distribution; Forecasting; Mathematical models; Monitoring; Neural networks; Predictive models; Pressure; Recurrent neural networks; Sensors; spatial–temporal attention networks; Time series; Time series analysis; time series prediction; Water distribution; Water distribution systems; water distribution systems (WDSs); Water engineering
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2020.3030839

Multivariate geo-sensory time series prediction is challenging because of the complex spatial and temporal correlations. In urban water distribution systems (WDSs), numerous spatial-correlated sensors have been deployed to continuously collect hydraulic data. Forecasts of the monitored flow and pressure time series are of vital importance for operational decision making, alerts, and anomaly detection. To address this issue, we proposed a hybrid dual-stage spatial-temporal attention-based recurrent neural networks (hDS-RNN). Our model consists of two stages: a spatial attention-based encoder and a temporal attention-based decoder. Specifically, a hybrid spatial attention mechanism that employs inputs along the temporal and spatial axes is proposed. Experiments on a real-world data set are conducted, which demonstrate that our model outperformed seven baseline models in flow and pressure predictions in WDS.