Ensemble Empirical Mode Decomposition Granger Causality Test Dynamic Graph Attention Transformer Network: Integrating Transformer and Graph Neural Network Models for Multi-Sensor Cross-Temporal Granularity Water Demand Forecasting
Source abstract
Abstract
Accurate water demand forecasting is crucial for optimizing the strategies across multiple water sources. This paper proposes the Ensemble Empirical Mode Decomposition Granger causality test Dynamic Graph Attention Transformer Network (EG-DGATN) for multi-sensor cross-temporal granularity water demand forecasting, which combines the Transformer and Graph Neural Networks. It employs the EEMD–Granger test to delineate the interconnections among sensors and extracts the spatiotemporal features within the causal domain by stacking dynamical graph spatiotemporal attention layers. The experimental results demonstrate that compared to baseline models, the EG-DGATN improves the MAPE metrics by 2.12%, 4.33%, and 6.32% in forecasting intervals of 15 min, 45 min, and 90 min, respectively. The model achieves an R2 score of 0.97, indicating outstanding predictive accuracy and exceptional explanatory power for the target variable. This research highlights significant potential applications in predictive tasks within smart water management systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Hydrological Forecasting Using AI · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, China
Henan Province Water Distribution Network Intelligent Management Engineering Research Center, Zhengzhou 450046, China
References (30)
Show source-provided references
1. Menapace, A., Zanfei, A., Felicetti, M., Avesani, D., Righetti, M., and Gargano, R. (2020). Burst Detection in Water Distribution Systems: The Issue of Dataset Collection. Appl. Sci., 10.10.3390/app10228219 ↗
2. An Artificial Intelligence Approach for Managing Water Demand in Water Supply Systems10.1088/1755-1315/1136/1/012004 ↗
3. Parameter Estimation of Seasonal ARIMA Models for Water Demand Forecasting Using the Harmony Search Algorithm10.1016/j.proeng.2017.03.225 ↗
4. Guo, B.T. (2019). Research on Irrigation Water Forecasting in Irrigation Districts Based on VAR and VEC Models, Chinese Hydraulic Engineering Society.
5. Li, Y., Wei, K.K., Chen, K., He, J.Q., Zhao, Y., Yang, G., Yao, N., Niu, B., Wang, B., and Wang, L. (2023). Forecasting monthly water deficit based on multi-variable linear regression and random forest models. Water, 15.10.3390/w15061075 ↗
6. Tuning hyperparameters of a SVM-based water demand forecasting system through parallel global optimization10.1016/j.cor.2018.01.013 ↗
7. Hourly and daily urban water demand predictions using a long short-term memory based model10.1061/(ASCE)WR.1943-5452.0001276 ↗
8. An Ensemble Neural Network Model to Forecast Drinking Water Consumption10.1061/(ASCE)WR.1943-5452.0001540 ↗
9. Hu, P., Tong, J., Wang, J.C., Yang, Y., and Turci, L.D. (2019, January 10–13). A hybrid model based on CNN and Bi-LSTM for urban water demand prediction. Proceedings of the 2019 IEEE Congress on Evolutionary Computation, Wellington, New Zealand.10.1109/CEC.2019.8790060 ↗
10. Graph Deep Learning: Application on Water Distribution Network ShortTerm Water Demand Forecasting
11. Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., and Sun, L. (2022). Transformers in time series: A survey. arXiv.10.24963/ijcai.2023/759 ↗
12. Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2023). A Time Series Is Worth 64 Words: Long-Term Forecasting with Transformers. arXiv.
13. Xu, M., Dai, W., Liu, C., Gao, X., Lin, W., Qi, G., and Xiong, H. (2021). Spatial-Temporal Transformer Networks for Traffic Flow Forecasting. arXiv.
14. Fang, Z., Long, Q., Song, G., and Xie, K. (2021, January 14–18). Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore.10.1145/3447548.3467430 ↗
15. Jin, G., Liang, Y., Fang, Y., Huang, J., Zhang, J., and Zheng, Y. (2023). Spatio-temporal graph neural networks for predictive learning in urban computing: A survey. arXiv.10.1109/TKDE.2023.3333824 ↗
16. Analyzing the dynamic sectoral influence in Chinese and American stock markets10.1016/j.physa.2019.04.158 ↗
17. Zhu, Y., Gao, Y., Wang, Z., Cao, G., Wang, R., Lu, S., Li, W., Nie, W., and Zhang, Z. (2022). A Tailings Dam Long-Term Deformation Prediction Method Based on Empirical Mode Decomposition and LSTM Model Combined with Attention Mechanism. Water, 14.10.3390/w14081229 ↗
18. Hou, C., Wei, Y., Zhang, H., Zhu, X., Tan, D., Zhou, Y., and Hu, Y. (2023). Stress Prediction Model of Super-High Arch Dams Based on EMD-PSO-GPR Model. Water, 15.10.3390/w15234087 ↗
19. Investigating causal relations by econometric models and cross-spectral methods10.2307/1912791 ↗
20. Grover, A., and Leskovec, J. (2016, January 13–17). Node2vec: Scalable Feature Learning for Networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD’16, San Francisco, CA, USA.10.1145/2939672.2939754 ↗
21. Jia, Z., Li, H., Yan, J., Sun, J., Han, C., and Qu, J. (2023). Dynamic Graph Convolution-Based Spatio-Temporal Feature Network for Urban Water Demand Forecasting. Appl. Sci., 13.10.3390/app131810014 ↗
22. Jang, E., Gu, S., and Poole, B. (2016). Categorical reparameterization with gumbel-softmax. arXiv.
23. Feng, A., and Leandros, T. (2022). Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting. arXiv.10.1145/3511808.3557540 ↗
24. Yu, B., Yin, H.T., and Zhu, Z.X. (2018, January 13–19). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/505 ↗
25. Guo, S.N., Lin, Y.F., Feng, N., Song, C., and Wan, H.Y. (February, January 27). Attention based spatio-temporal graph convolutional networks for traffic flow forecasting. Proceedings of the 33rd AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.10.1609/aaai.v33i01.3301922 ↗
26. Li, Y.G., Yu, R., Shahabi, C., and Liu, Y. (2018). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv.
27. A Deep Learning Model with Spatio-Temporal Graph Convolutional Networks for River Water Quality Prediction10.2166/ws.2023.164 ↗
28. Wu, Z., Pan, S., Long, G., Jiang, J., and Zhang, C. (2019). Graph WaveNet for Deep Spatial-Temporal Graph Modeling. arXiv.10.24963/ijcai.2019/264 ↗
29. Shan, S., Ni, H., Chen, G., Lin, X., and Li, J. (2023). A Machine Learning Framework for Enhancing ShortTerm Water Demand Forecasting Using Attention-BiLSTM Networks Integrated with XGBoost Residual Correction. Water, 15.10.3390/w15203605 ↗
30. The Extension of EPANET Source Code to Simulate Unsteady Flow in Water Distribution Networks with Variable Head Tanks10.2166/hydro.2012.013 ↗