Enhanced Artificial Neural Networks for Salinity Estimation and Forecasting in the Sacramento-San Joaquin Delta of California
Publication: Journal of Water Resources Planning and Management
Volume 147, Issue 10
Abstract
Domain-specific architectures of artificial neural networks (ANNs) have been developed to estimate salinity levels for planning at key monitoring stations in the Sacramento-San Joaquin Delta, California. In this work, we propose three major enhancements to existing ANN architectures for purposes of training time reduction, estimation error reduction, and better feature extraction. Specifically, we design a novel multitask ANN architecture with shared hidden layers for joint salinity estimation at multiple stations, achieving a reduction of 90% training and inference time. As another major structural redesign, we replace predetermined preprocessing on input data by a trainable convolution layer. We further enhance the multitask ANN design and training for salinity forecasting. Test results indicate that these enhancements substantially improve the efficiency and expand the capacity of the current salinity modeling ANNs in the Delta. Our enhanced ANN design methodologies have the potential for incorporation into the current modeling practice and provide more robust and timely information to guide water resource planning and management in the Delta.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The following code and data that support the findings of this study are available from the corresponding author by request: Python code for training and evaluating the ANNs; input and output data used in ANN training and evaluation.
Acknowledgments
This work was supported in part by the research agreement No. 4600013184 from the California Department of Water Resources. The views and opinions expressed in this article are those of the authors and do not reflect the policy or position of their employers.
References
Abadi, M., et al. 2015. “TensorFlow: Large-scale machine learning on heterogeneous systems.” Accessed March 21, 2019. https://www.tensorflow.org/.
Banerjee, P., V. Singh, K. Chatttopadhyay, P. Chandra, and B. Singh. 2011. “Artificial neural network model as a potential alternative for groundwater salinity forecasting.” J. Hydrol. 398 (3–4): 212–220. https://doi.org/10.1016/j.jhydrol.2010.12.016.
Bata, M. H., R. Carriveau, and D. S.-K. Ting. 2020. “Short-term water demand forecasting using nonlinear autoregressive artificial neural networks.” J. Water Resour. Plann. Manage. 146 (3): 04020008. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001165.
Bhaskaran, P. K., R. R. Kumar, R. Barman, and R. Muthalagu. 2010. “A new approach for deriving temperature and salinity fields in the Indian Ocean using artificial neural networks.” J. Mar. Sci. Technol. 15 (2): 160–175. https://doi.org/10.1007/s00773-009-0081-2.
Bohorquez, J., B. Alexander, A. R. Simpson, and M. F. Lambert. 2020. “Leak detection and topology identification in pipelines using fluid transients and artificial neural networks.” J. Water Resour. Plann. Manage. 146 (6): 04020040. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001187.
Bowden, G. J., H. R. Maier, and G. C. Dandy. 2005. “Input determination for neural network models in water resources applications. Part 2. Case study: Forecasting salinity in a river.” J. Hydrol. 301 (1–4): 93–107. https://doi.org/10.1016/j.jhydrol.2004.06.020.
Caruana, R. 1995. “Learning many related tasks at the same time with backpropagation.” In Advances in neural information processing systems, 657–664. Denver: MIT Press.
Caruana, R. A. 1993. “Multitask connectionist learning.” In Proc., 1993 Connectionist Models Summer School. Greene County, OH: Wright-Patterson AFB.
CDWR (California Department of Water Resources). 2019. DSM2: Delta simulation model II. Sacramento, CA: Bay Delta Office, CDWR.
Chandramouli, V., and H. Raman. 2001. “Multireservoir modeling with dynamic programming and neural networks.” J. Water Resour. Plann. Manage. 127 (2): 89–98. https://doi.org/10.1061/(ASCE)0733-9496(2001)127:2(89).
Chen, L., S. B. Roy, and P. H. Hutton. 2018. “Emulation of a process-based estuarine hydrodynamic model.” Hydrol. Sci. J. 63 (5): 783–802. https://doi.org/10.1080/02626667.2018.1447112.
Chen, L.-H., C.-T. Chen, and D.-W. Lin. 2011. “Application of integrated back-propagation network and self-organizing map for groundwater level forecasting.” J. Water Resour. Plann. Manage. 137 (4): 352–365. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000121.
Chen, S., and C. Hu. 2017. “Estimating sea surface salinity in the northern Gulf of Mexico from satellite ocean color measurements.” Remote Sens. Environ. 201 (Nov): 115–132. https://doi.org/10.1016/j.rse.2017.09.004.
Dai, X., Z. Huo, and H. Wang. 2011. “Simulation for response of crop yield to soil moisture and salinity with artificial neural network.” Field Crops Res. 121 (3): 441–449. https://doi.org/10.1016/j.fcr.2011.01.016.
Denton, R., and G. Sullivan. 1993. Antecedent flow-salinity relations: Application to Delta planning models. Concord, CA: Contra Costa Water District.
Denton, R. A. 1993. “Accounting for antecedent conditions in seawater intrusion modeling–Applications for the San Francisco Bay-Delta.” In Hydraulic engineering, 448–453. Reston, VA: ASCE.
DeSilet, L., B. Golden, Q. Wang, and R. Kumar. 1992. “Predicting salinity in the Chesapeake Bay using backpropagation.” Comput. Oper. Res. 19 (3–4): 277–285. https://doi.org/10.1016/0305-0548(92)90049-B.
Draper, A. J., A. Munevar, S. K. Arora, E. Reyes, N. L. Parker, F. I. Chung, and L. E. Peterson. 2004. “CalSim: Generalized model for reservoir system analysis.” J. Water Resour. Plann. Manage. 130 (6): 480–489. https://doi.org/10.1061/(ASCE)0733-9496(2004)130:6(480).
Foresee, F. D., and M. T. Hagan. 1997. “Gauss-Newton approximation to Bayesian learning.” In Vol. 3 of Proc., Int. Conf. on Neural Networks (ICNN’97), 1930–1935. New York: IEEE.
Guijo-Rubio, D., A. M. Gómez-Orellana, P. A. Gutiérrez, and C. Hervás-Martínez. 2020. “Short-and long-term energy flux prediction using multi-task evolutionary artificial neural networks.” Ocean Eng. 216 (Nov): 108089. https://doi.org/10.1016/j.oceaneng.2020.108089.
Hajgató, G., G. Paál, and B. Gyires-Tóth. 2020. “Deep reinforcement learning for real-time optimization of pumps in water distribution systems.” J. Water Resour. Plann. Manage. 146 (11): 04020079. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001287.
He, M., L. Zhong, P. Sandhu, and Y. Zhou. 2020. “Emulation of a process-based salinity generator for the Sacramento–San Joaquin Delta of California via deep learning.” Water 12 (8): 2088. https://doi.org/10.3390/w12082088.
Huang, W., and S. Foo. 2002. “Neural network modeling of salinity variation in Apalachicola River.” Water Res. 36 (1): 356–362. https://doi.org/10.1016/S0043-1354(01)00195-6.
Hunter, J. M., H. R. Maier, M. S. Gibbs, E. R. Foale, N. A. Grosvenor, N. P. Harders, and T. C. Kikuchi-Miller. 2018. “Framework for developing hybrid process-driven, artificial neural network and regression models for salinity prediction in river systems.” Hydrol. Earth Syst. Sci. 22 (5): 2987–3006. https://doi.org/10.5194/hess-22-2987-2018.
Jayasundara, N. C., S. A. Seneviratne, E. Reyes, and F. I. Chung. 2020. “Artificial neural network for Sacramento–San Joaquin Delta flow–salinity relationship for CalSim 3.0.” J. Water Resour. Plann. Manage. 146 (4): 04020015. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001192.
Jiang, H., Y. Rusuli, T. Amuti, and Q. He. 2019. “Quantitative assessment of soil salinity using multi-source remote sensing data based on the support vector machine and artificial neural network.” Int. J. Remote Sens. 40 (1): 284–306. https://doi.org/10.1080/01431161.2018.1513180.
Kang, G., J. Z. Gao, and G. Xie. 2017. “Data-driven water quality analysis and prediction: A survey.” In Proc., 2017 IEEE 3rd Int. Conf. on Big Data Computing Service and Applications (BigDataService), 224–232. New York: IEEE.
Kingma, D. P., and J. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted December 22, 2014. http://arxiv.org/abs/1412.6980.
Le, D., W. Huang, and E. Johnson. 2019. “Neural network modeling of monthly salinity variations in oyster reef in Apalachicola Bay in response to freshwater inflow and winds.” Neural Comput. Appl. 31 (10): 6249–6259. https://doi.org/10.1007/s00521-018-3436-y.
Levenberg, K. 1944. “A method for the solution of certain non-linear problems in least squares.” Q. Appl. Math. 2 (2): 164–168. https://doi.org/10.1090/qam/10666.
Liu, Y., Y. Liang, K. Ouyang, S. Liu, D. Rosenblum, and Y. Zheng. 2020. “Predicting urban water quality with ubiquitous data-a data-driven approach.” In Proc., IEEE Transactions on Big Data. New York: IEEE.
Maas, A. L., A. Y. Hannun, and A. Y. Ng. 2013. “Rectifier nonlinearities improve neural network acoustic models.” In Vol. 30 of Proc., ICML, 3. Alexandria, VA: National Science Foundation.
Maier, H. R., and G. C. Dandy. 1999. “Empirical comparison of various methods for training feed-forward neural networks for salinity forecasting.” Water Resour. Res. 35 (8): 2591–2596. https://doi.org/10.1029/1999WR900150.
Marquardt, D. W. 1963. “An algorithm for least-squares estimation of nonlinear parameters.” J. Soc. Ind. Appl. Math. 11 (2): 431–441. https://doi.org/10.1137/0111030.
Qiu, M., P. Zhao, K. Zhang, J. Huang, X. Shi, X. Wang, and W. Chu. 2017. “A short-term rainfall prediction model using multi-task convolutional neural networks.” In Proc., 2017 IEEE Int. Conf. on Data Mining (ICDM), 395–404. New York: IEEE.
Ranjithkumar, M., and L. Robert. 2021. “Machine learning techniques and cloud computing to estimate river water quality–survey.” In Inventive communication and computational technologies, 387–396. Singapore: Springer.
Rath, J. S., P. H. Hutton, L. Chen, and S. B. Roy. 2017. “A hybrid empirical-Bayesian artificial neural network model of salinity in the San Francisco Bay-Delta estuary.” Environ. Modell. Software 93 (Jul): 193–208. https://doi.org/10.1016/j.envsoft.2017.03.022.
Ruder, S. 2017. “An overview of multi-task learning in deep neural networks.” Preprint, submitted June 15, 2017. http://arxiv.org/abs/1706.05098.
Sreekanth, J., and B. Datta. 2010. “Multi-objective management of saltwater intrusion in coastal aquifers using genetic programming and modular neural network based surrogate models.” J. Hydrol. 393 (3–4): 245–256. https://doi.org/10.1016/j.jhydrol.2010.08.023.
Swain, E. D., J. Gómez-Fragoso, and S. Torres-Gonzalez. 2017. “Projecting impacts of climate change on water availability using artificial neural network techniques.” J. Water Resour. Plann. Manage. 143 (12): 04017068. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000844.
SWRCB (California State Water Resources Control Board). 2000. Revised water right decision 1641. Sacramento, CA: SWRCB.
Tealab, A. 2018. “Time series forecasting using artificial neural networks methodologies: A systematic review.” Future Comput. Inf. J. 3 (2): 334–340. https://doi.org/10.1016/j.fcij.2018.10.003.
Tung, T. M., and Z. M. Yaseen. 2020. “A survey on river water quality modelling using artificial intelligence models: 2000–2020.” J. Hydrol. 585 (Jun): 124670. https://doi.org/10.1016/j.jhydrol.2020.124670.
Wilamowski, B. M., S. Iplikci, O. Kaynak, and M. O. Efe. 2001. “An algorithm for fast convergence in training neural networks.” In Vol. 3 of Proc., Int. Joint Conf. on Neural Networks (Cat. No. 01CH37222), 1778–1782. New York: IEEE.
Zhou, F., B. Liu, and K. Duan. 2020. “Coupling wavelet transform and artificial neural network for forecasting estuarine salinity.” J. Hydrol. 588 (Sep): 125127. https://doi.org/10.1016/j.jhydrol.2020.125127.
Information & Authors
Information
Published In
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Aug 22, 2020
Accepted: Apr 29, 2021
Published online: Aug 9, 2021
Published in print: Oct 1, 2021
Discussion open until: Jan 9, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Siyu Qi, Minxue He, Zhaojun Bai, Zhi Ding, Prabhjot Sandhu, Francis Chung, Peyman Namadi, Yu Zhou, Raymond Hoang, Bradley Tom, Jamie Anderson, Dong Min Roh, Novel Salinity Modeling Using Deep Learning for the Sacramento–San Joaquin Delta of California, Water, 10.3390/w14223628, 14, 22, (3628), (2022).
- Siyu Qi, Minxue He, Zhaojun Bai, Zhi Ding, Prabhjot Sandhu, Yu Zhou, Peyman Namadi, Bradley Tom, Raymond Hoang, Jamie Anderson, Multi-Location Emulation of a Process-Based Salinity Model Using Machine Learning, Water, 10.3390/w14132030, 14, 13, (2030), (2022).
- Jiramate Changklom, Phakawat Lamchuan, Adichai Pornprommin, Salinity Forecasting on Raw Water for Water Supply in the Chao Phraya River, Water, 10.3390/w14050741, 14, 5, (741), (2022).