Abstract
Measured tidal height time-series are critical for establishing initial and boundary conditions for hydrodynamic models of estuaries. The inexistence of tidal stations in the developing world is more evident than in other parts of the world. The lack of tidal height time-series data oftentimes forces modelers to interpolate or extrapolate these critical data, introducing important uncertainty bounds in the output of hydrodynamic models of estuaries. This paper assesses the feasibility of using gridded multi-mission sea surface height data for estimating tidal heights for the Columbia River estuary located in Northwestern USA. Ocean surface anomaly and geostrophic velocities gridded data, along with historical measured tidal heights are used for training and calibration of the ANN model. A nonlinear autoregressive exogenous neural network is used to predict tidal heights at a 14-min time step. Statistical comparison between measured and predicted data showed that the quality of predicted values was good. Regression analysis for goodness of fit showed the applicability of the proposed method: R2 = 0.93, significance-F = 4.57 * 10−18, F = 370.80, P-value for the intercept = 0.13, standard error = 0.26 m. Overall, the neural network provides good estimations of tidal heights, considering that it uses coarse-spatial-resolution ocean surface and water velocity data with daily temporal resolution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Le Provost, C., Lyard, F., Molines, J.M., Genco, M.L., Rabilloud, F.: A hydrodynamic ocean tide model improved by assimilating a satellite altimeter-derived data set. J. Geophys. Res. 103, 5513–5529 (2018)
Matsumoto, K., Takanezawa, T., Ooe, M.: Ocean tide models developed by assimilating TOPEX/POSEIDON altimeter data into hydrodynamical model: a global model and a regional model around Japan. J. Oceanogr. 56(5), 567–581 (2018). https://doi.org/10.1023/A:1011157212596
Egbert, G.D., Erofeeva, S.: Efficient inverse modelling of barotropic ocean tides. J. Atmos. Ocean. Technol. 19, 183–204 (2002). http://volkov.oce.orst.edu/tides/
Foreman, M.G.G., Thomson, R.E., Smith, C.L.: Seasonal current simulations for the western continental margin of Vancouver Island. J. Geophys. Res. 105(C8), 19665–19698 (2000)
Han, G., Paturi, S., de Young, B., Yi, Y., Shum, C.-K.: A 3-D data-assimilative tidal model of the Northwest Atlantic. Atmos. Ocean 48(1), 39–57 (2010). https://doi.org/10.3137/OC303.2010
Qiang, L., Bing-Dong, Y., Bi-Guang, H.: Calculation and measurement of tide height for the navigation of ship at high tide using artificial neural network. Pol. Marit. Res. 25(s3), 99–110 (2018). https://doi.org/10.2478/pomr-2018-0118
Wang, J., Deng, Z.: Development of a MODIS data-based algorithm for retrieving gage height in nearshore waters along the Louisiana Gulf Coast. J. Coast. Res. 34(1), 220–228 (2018). https://doi.org/10.2112/jcoastres-d-16-00161.1
Anh, N., Prasad, M., Srikanth, N., Sundaram, S.: Wave forecasting using meta-cognitive interval type-2 fuzzy inference system. Procedia Comput. Sci. 144, 33–41 (2018). https://doi.org/10.1016/j.procs.2018.10.502
Kaveh, N.A., Ghaheri, A., Chegini, V., Nazarali, M.: Application of a hybrid approach for tide-surge modeling in the Persian Gulf. J. Coast. Res. 32(5), 1126–1134 (2016). https://doi.org/10.2112/JCOASTRES-D-15-00033.1
López, M., López, I., Iglesias, G.: Hindcasting long waves in a port: an ANN approach. Coast. Eng. J. 57(4), Article no. 1550019 (2015). https://doi.org/10.1142/s0578563415500199
Kim, D.H., Kim, Y.J., Hur, D.S.: Artificial neural network based breakwater damage estimation considering tidal level variation. Ocean Eng. 87, 185–190 (2014). https://doi.org/10.1016/j.oceaneng.2014.06.001
Chen, W.-B., Liu, W.-C., Hsu, M.-H.: Predicting typhoon-induced storm surge tide with a two-dimensional hydrodynamic model and artificial neural network model. Nat. Hazards Earth Syst. Sci. 12(12), 3799–3809 (2012). https://doi.org/10.5194/nhess-12-3799-2012
Sertel, E., Cigizoglu, H.K., Sanli, D.U.: Estimating daily mean sea level heights using artificial neural networks. J. Coast. Res. 24(3), 727–734 (2008). https://doi.org/10.2112/06-742.1
El-Rabbany, A., El-Diasty, M.: A new approach to sequential tidal prediction. J. Navig. 56(2), 305–314 (2003). https://doi.org/10.1017/S0373463303002285
NASA Jet Propulsion Laboratory: Physical Oceanography Distributed Active Archive Center (PODAAC). NASA EOSDIS PO.DAAC, Pasadena, CA (2015). https://podaac.jpl.nasa.gov/
Boussaada, Z., Curea, O., Ahmed, R., Camblong, H., Najiba, M.B.: A nonlinear autoregressive exogenous (NARX) neural network model for the prediction of the daily direct solar radiation. Energies 11, 620 (2018). https://doi.org/10.3390/en11030620
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Alarcon, V.J. (2019). Using Gridded Multi-mission Sea Surface Height Data to Estimate Tidal Heights at Columbia River Estuary. In: Misra, S., et al. Computational Science and Its Applications – ICCSA 2019. ICCSA 2019. Lecture Notes in Computer Science(), vol 11621. Springer, Cham. https://doi.org/10.1007/978-3-030-24302-9_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-24302-9_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24301-2
Online ISBN: 978-3-030-24302-9
eBook Packages: Computer ScienceComputer Science (R0)