Forecasting Sediment Accumulation in the Southwest Pass with Machine-Learning Models
Publication: Journal of Waterway, Port, Coastal, and Ocean Engineering
Volume 150, Issue 2
Abstract
Connecting the Mississippi River and the Gulf of Mexico, the Southwest Pass (SWP) is one of the most highly utilized commercial waterways in the United States. Hard-to-predict accumulation of sediments in the SWP affects the access of deep-draft vessels to four of the nation’s top 15 ports measured by tonnage. The U.S. Army Corps of Engineers (USACE) spends approximately 100 Million USD annually on dredging operations to maintain SWP at a 14.2-meter (50-ft.) depth. Presently, USACE project managers rely on rules-of-thumb with seasonal river stage trends and thresholds to get 10–14 days of lead time for shoaling conditions at the SWP. This work presents the development of a machine learning modeling framework to increase lead times and accuracy of shoaling forecasts in the SWP. Within a multivariate multistep timeseries forecasting framework, several regression models, input variables, and forecasting days are explored. All multivariate machine learning models outperformed an univariate ARIMA model used as baseline. A multilayered perceptron regressor implemented on a 60-day in-lag scenario was found to be the best model to forecast shoaling in the upcoming 45 days. The proposed model may be applied to forecast dredging needs at other critical waterways.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code used during the study were provided by a third party. Direct requests for these materials may be made to the provider as indicated in the Acknowledgements. Input data for the model were obtained from CSAT Tool (https://cirp.usace.army.mil/products/csat.php), RiverGages.com, and USGS National Water Information System (https://nwis.waterdata.usgs.gov/nwis).
Acknowledgments
This study was funded by the USACE Mississippi Valley Division and the USACE – Engineer Research and Development Center (ERDC) Dredging Innovations Group (DIG). The authors thank the USACE New Orleans District for their support and expert knowledge of the SWP, the team at the ERDC Coastal and Hydraulics Laboratory and Information Technology Laboratory, and data providers. Input data for the model were obtained from CSAT Tool (https://cirp.usace.army.mil/products/csat.php), RiverGages.com, and USGS National Water Information System (https://nwis.waterdata.usgs.gov/nwis).
References
Abadi, M., et al. 2015. “TensorFlow: Large-scale machine learning on heterogeneous distributed systems.” Preprint, submitted March 14, 2016. https://doi.org/10.48550/arXiv.1603.04467.
Afan, H. A., A. El-Shafie, W. H. M. W. Mohtar, and Z. M. Yaseen. 2016. “Past, present and prospect of an Artificial Intelligence (AI) based model for sediment transport prediction.” J. Hydrol. 541 (B): 902–913. https://doi.org/10.1016/j.jhydrol.2016.07.048.
Bhattacharya, B., and D. P. Solomatine. 2006. “Machine learning in sedimentation modelling.” Neural Networks 19 (2): 208–214. https://doi.org/10.1016/j.neunet.2006.01.007.
Bishop, C. M. 2006. Pattern recognition and machine learning. New York: Springer.
Biswas, A., S. Ahmed, T. Bankefa, P. Ranganathan, and H. Salehfar. 2021. “Performance analysis of short and mid-Term Wind Power prediction using ARIMA and Hybrid Models.” In Proc., 2021 IEEE Power and Energy Conf., 1–7. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE).
Breiman, L. 2001. “Random forests.” Mach. Learn. 45: 5–32. https://doi.org/10.1023/A:1010933404324.
Brezak, D., T. Bacek, D. Majetic, J. Kasac, and B. Novakovic. 2012. “A comparison of feed-forward and recurrent neural networks in time series forecasting.” In Proc., IEEE Conf. on Computational Intelligence for Financial Engineering & Economics, 1–6. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE).
Castro, W., J. Oblitas, R. Santa-Cruz, and H. Avila-George. 2017. “Multilayer perceptron architecture optimization using parallel computing techniques.” PLoS One 12 (12): e0189369. https://doi.org/10.1371/journal.pone.0189369.
Chou, J.-S., and J.-W. Lin. 2020. “Risk-Informed Prediction of Dredging Project Duration Using Stochastic Machine Learning.” Water 12 (6): 1643. doi:https://doi.org/10.3390/w12061643.
De Figueiredo, N. M., and C. J. Cavalcante Blanco. 2016. “Water level forecasting and navigability conditions of the tapajós river – Amazon - Brazil.” La Houille Blanche 102: 53–64. https://doi.org/10.1051/lhb/2016031.
DOT, Bureau of Transportation Statistics. 2022. Port data catalog. Port performance freight statistics program: Annual report. Washington, DC: DOT.
Dudek, G. 2015. “Short-term load forecasting using random forests.” Adv. Intell. Syst. Comput. 323: 821–828. https://doi.org/10.1007/978-3-319-11310-4_71.
Dunkin, L. M., L. A. Coe, and J. J. Ratcliff. 2018. Corps shoaling analysis tool: Predicting channel shoaling. Vicksburg, MS: U.S. Army Engineer Research and Development Center.
Esteves, J. G., G. de Souza Rolim, and A. Ferraudo. 2019. “Rainfall prediction methodology with binary multilayer perceptron neural networks.” Clim. Dyn. 52: 2319–2331. https://doi.org/10.1007/s00382-018-4252-x.
Gonzalez, J., and W. Yu. 2018. “Non-linear system modeling using LSTM neural networks.” IFAC 51: 485–489.
Goyal, P., S. Pandey, and K. Jain. 2018. “Unfolding recurrent neural networks.” Springer. Accessed January 19, 2023. https://link.springer.com/chapter/10.1007/978-1-4842-3685-7_3.
Graw, J. H., W. T. Wood, and B. J. Phrampus. 2021. “Predicting global marine sediment density using the random forest regressor machine learning algorithm.” J. Geophys. Res.: Solid Earth 126. https://doi.org/10.1029/2020JB020135.
Gupta, H. V., and H. Kling. 2011. “On typical range, sensitivity, and normalization of Mean Squared Error and Nash-Sutcliffe Efficiency type metrics.” Water Resour. Res. 47. https://doi.org/10.1029/2011WR010962.
Hartman, M. A., K. N. Mitchell, L. M. Dunkin, J. Lewis, B. Emery, N. F. Lenssen, and R. Copeland. 2022. “Southwest pass sedimentation and dredging data analysis.” J. Waterw. Port Coastal Ocean Eng. 148 (2): 05021017. https://doi.org/10.1061/(ASCE)WW.1943-5460.0000684.
Hochreiter, S., and J. Schmidhuber. 1997. “Long short-term memory.” Neural Comput. 9: 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Hunter, J. D. 2007. “Matplotlib: A 2D graphics environment.” Comput. Sci. Eng. 9 (3): 90–95. https://doi.org/10.1109/MCSE.2007.55.
Kress, M. 2021. “Hydrosurvey data archive for federal navigation projects.” Data.gov Accessed February 21, 2023. https://data.gov/maritime/hydrosurvey-data-archive-for-federal-navigation-projects/index.html.
Mateo-Pérez, V., M. Corral-Bobadilla, F. Ortega-Fernández, and V. Rodríguez-Montequín. 2021. “Determination of water depth in ports using satellite data based on machine learning algorithms.” Energies 14 (9): 2486. https://doi.org/10.3390/en14092486.
Murat, M., I. Malinowska, M. Gos, and J. Krzyszczak. 2018. “Forecasting daily meteorological time series using ARIMA and regression models.” Int. Agrophys. 32 (2): 253–264. https://doi.org/10.1515/intag-2017-0007.
Mussumeci, E., and F. Codeco Coelho. 2020. “Large-scale multivariate forecasting models for Dengue - LSTM versus random forest regression.” Spatial Spatio-temporal Epidemiol. 35: 100372. https://doi.org/10.1016/j.sste.2020.100372.
Nel, H. A., T. Dalu, and R. J. Wasserman. 2018. “Sinks and sources: Assessing microplastic abundance in river sediment and deposit feeders in an Austral temperate urban river system.” Sci. Total Environ. 612: 950–956. https://doi.org/10.1016/j.scitotenv.2017.08.298.
Pedregosa, F., et al. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (85): 2825–2830.
Pektas, A. O., and H. K. Cigizoglu. 2017. “Long-range forecasting of suspended sediment.” Hydrol. Sci. J. 62 (14): 2415–2425. https://doi.org/10.1080/02626667.2017.1383607.
PyPI. 2021. “xgboost 1.5.0.” pypi.org. Accessed December 19, 2022. https://pypi.org/project/xgboost/1.5.0/.
Rady, E. A., H. Fawzy, and A. Fattah. 2021. “Time series forecasting using tree based methods.” J. Stat. Appl. Probab. 10: 229–244. https://doi.org/10.18576/jsap/100121.
Seabold, S., and J. Perktold. 2010. “Statsmodels: Econometric and statistical modeling with Python.” In Proc., of the 9th Python in Science Conf. Austin, TX: Enthought.
Shcherbakov, M., A. Brebels, N. Shcherbakova, A. Tyukov, T. Janovsky, and V. Kamaev. 2013. “A survey of forecast error measures.” World Appl. Sci. J. 24: 171–176.
Siami-Namini, S., N. Tavakoli, and A. Siami Namin. 2018. “A comparison of ARIMA and LSTM in forecasting time series.” In Proc., 17th IEEE Int. Conf. on Machine Learning and Applications, 1394–1401. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE).
Tyralis, H. 2017. “Variable selection in time series forecasting using random forests.” Algorithms 10 (114): 114. https://doi.org/10.3390/a10040114.
USACE. 2022. “National channel framework.” USACE Geospatial. Accessed October 19, 2022. https://geospatial-usace.opendata.arcgis.com/maps/9227967a2748410983352b501c0c7b39/about.
USGS. 2018. “Sediment and sustpended sediment.” Water Science School. Accessed September 19, 2022 https://www.usgs.gov/special-topics/water-science-school/science/sediment-and-suspended-sediment.
USGS. 2022. “National water information system: Web interface.” Water Data for the Nation. Accessed December 21, 2022. https://nwis.waterdata.usgs.gov/nwis.
Washington, S., M. Karlaftis, F. Mannering, and P. Anastasopoulos. 2020. Statistical and econometric methods for transportation data analysis. 3rd ed. New York: Taylor & Francis Group.
Wei, R., J. Wang, M. Su, E. Jia, S. Chen, T. Chen, and Y. Ni. 2018. “Missing value imputation approach for mass spectrometry-based metabolomics data.” Sci. Rep. 8: 663. https://doi.org/10.1038/s41598-017-19120-0.
Wheatcroft, R. A., and C. K. Sommerfield. 2005. “River sediment flux and shelf sediment accumulation rates on the Pacific Northwest margin.” Cont. Shelf Res. 25 (3): 311–332. https://doi.org/10.1016/j.csr.2004.10.001.
Yeates, E., A. Tavakoly, K. Mitchell, G. Dreaper, and S. Afshari. 2020. “Utilizing stream flows to forecast dredging requirements.” USACE-ERDC. Accessed January 20, 2023. https://apps.dtic.mil/sti/pdfs/AD1105836.pdf.
Zhang, Y., H. Yang, H. Cui, and Q. Chen. 2020. “Comparison of the ability of ARIMA, WNN and SVM models for drought forecasting in the Sanjiang Plain, China.” Nat. Resour. Res. 29: 1447–1464. https://doi.org/10.1007/s11053-019-09512-6.
Zheng, H., J. Yuan, and L. Chen. 2017. “Short-Term load forecasting using EMD-LSTM neural networks with a xgboost algorithm for feature importance evaluation.” Energies 10 (8): 1168. https://doi.org/10.3390/en10081168.
Zhou, T., Z. Jiang, X. Liu, and K. Tan. 2020. “Research on the long-term and short-term forecasts of navigable river’s water-level fluctuation based on the adaptive multilayer perceptron.” J. Hydrol. 591: 125285. https://doi.org/10.1016/j.jhydrol.2020.125285.
Information & Authors
Information
Published In
Journal of Waterway, Port, Coastal, and Ocean Engineering
Volume 150 • Issue 2 • March 2024
Copyright
© 2023 Published by American Society of Civil Engineers.
History
Received: Mar 13, 2023
Accepted: Nov 13, 2023
Published online: Dec 29, 2023
Published in print: Mar 1, 2024
Discussion open until: May 29, 2024
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.