Abstract
Accurate inundation level forecasting during typhoon invasion is crucial for organizing response actions such as the evacuation of people from areas that could potentially flood. This paper explores the ability of nonlinear autoregressive neural networks with exogenous inputs (NARX) to predict inundation levels induced by typhoons. Two types of NARX architecture were employed: series-parallel (NARX-S) and parallel (NARX-P). Based on cross-correlation analysis of rainfall and water-level data from historical typhoon records, 10 NARX models (five of each architecture type) were constructed. The forecasting ability of each model was assessed by considering coefficient of efficiency (CE), relative time shift error (RTS), and peak water-level error (PE). The results revealed that high CE performance could be achieved by employing more model input variables. Comparisons of the two types of model demonstrated that the NARX-S models outperformed the NARX-P models in terms of CE and RTS, whereas both performed exceptionally in terms of PE and without significant difference. The NARX-S and NARX-P models with the highest overall performance were identified and their predictions were compared with those of traditional ARX-based models. The NARX-S model outperformed the ARX-based models in all three indexes, whereas the NARX-P model exhibited comparable CE performance and superior RTS and PE performance.
Similar content being viewed by others
References
Bazartseren, B., Hildebrandt, G., & Holz, K. P. (2003). Short-term water level prediction using neural networks and neuro-fuzzy approach. Neurocomputing, 55(3), 439–450.
Box, G.E., and Jenkins, G.M. 1976. Time Series Analysis: Forecasting and Control. revised ed. Holden-Day.
Campolo, M., Soldati, A., & Andreussi, P. (2003). Artificial neural network approach to flood forecasting in the river Arno. Hydrological Sciences Journal, 48(3), 381–398.
Chang, F. J., & Tsai, M. J. (2016). A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques. Journal of Hydrology, 535, 256–269.
Chang, L. C., Shen, H. Y., Wang, Y. F., Huang, J. Y., & Lin, Y. T. (2010). Clustering-based hybrid inundation model for forecasting flood inundation depths. Journal of Hydrology, 385(1), 257–268.
Chang, L. C., Shen, H. Y., & Chang, F. J. (2014). Regional flood inundation nowcast using hybrid SOM and dynamic neural networks. Journal of Hydrology, 519, 476–489.
Chang, F. J., Chiang, Y. M., & Ho, Y. H. (2015). Multistep-ahead flood forecasts by neuro-fuzzy networks with effective rainfall–run-off patterns. Journal of Flood Risk Management, 8(3), 224–236.
Chen, S., Billings, S. A., & Grant, P. M. (1990). Non-linear system identification using neural networks. International Journal of Control, 51(6), 1191–1214.
Del Giudice, D., Reichert, P., Bareš, V., Albert, C., & Rieckermann, J. (2015). Model bias and complexity—understanding the effects of structural deficits and input errors on runoff predictions. Environmental Modelling & Software, 64, 205–214.
Gayen, A. K. (1951). The frequency distribution of the product-moment correlation coefficient in random samples of any size drawn from non-normal universes. Biometrika, 38(1/2), 219–247.
Gourley, J. J., Maddox, R. A., Howard, K. W., & Burgess, D. W. (2002). An exploratory multisensor technique for quantitative estimation of stratiform rainfall. Journal of Hydrometeorology, 3(2), 166–180.
Johnson, J. T., MacKeen, P. L., Witt, A., Mitchell, E. D. W., Stumpf, G. J., Eilts, M. D., & Thomas, K. W. (1998). The storm cell identification and tracking algorithm: an enhanced WSR-88D algorithm. Weather and Forecasting, 13(2), 263–276.
Keskin, M. E., Taylan, D., & Terzi, O. (2006). Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series. Hydrological Sciences Journal, 51(4), 588–598.
Levenberg, K. (1944). A method for the solution of certain non-linear problems in least squares. Quarterly of Applied Mathematics., 2, 164–168.
Lin, T., Horne, B. G., & Giles, C. L. (1998). How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies. Neural Networks, 11(5), 861–868.
Marquardt, D. (1963). An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal on Applied Mathematics, 11(2), 431–441.
Menezes Jr., J. M. P., & Barreto, G. A. (2008). Long-term time series prediction with the NARX network: an empirical evaluation. Neurocomputing, 71(16–18), 3335–3343.
Narendra, K. S., & Parthasarathy, K. (1990). Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1(1), 4–27.
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I—a discussion of principles. Journal of Hydrology, 10(3), 282–290.
Nguyen, P. K.-T., & Chua, L. H.-C. (2012). The data-driven approach as an operational real-time flood forecasting model. Hydrological Processes, 26(19), 2878–2893.
Ouyang, H. T. (2016a). Multi-objective optimization of typhoon inundation forecast models with cross-site architectures for a water-level gauging network by integrating ARMAX with a genetic algorithm. Natural Hazards and Earth System Sciences, 16(8), 1897–1909.
Ouyang, H. T. (2016b). Optimization of autoregressive, exogenous inputs-based typhoon inundation forecasting models using a multi-objective genetic algorithm. Engineering Optimization. doi:10.1080/0305215X.2016.1230207.
Pan, T. Y., Chang, L. Y., Lai, J. S., Chang, H. K., Lee, C. S., & Tan, Y. C. (2014). Coupling typhoon rainfall forecasting with overland-flow modeling for early warning of inundation. Natural Hazards, 70(3), 1763–1793.
Rajurkar, M. P., Kothyari, U. C., & Chaube, U. C. (2002). Artificial neural networks for daily rainfall—runoff modelling. Hydrological Sciences Journal, 47(6), 865–877.
Sehgal, V., Sahay, R. R., & Chatterjee, C. (2014). Effect of utilization of discrete wavelet components on flood forecasting performance of wavelet based ANFIS models. Water Resources Management, 28(6), 1733–1749.
Shen, H. Y., & Chang, L. C. (2013). Online multistep-ahead inundation depth forecasts by recurrent NARX networks. Hydrology and Earth System Sciences, 17(3), 935–945.
Talei, A., & Chua, L. H. (2012). Influence of lag time on event-based rainfall–runoff modeling using the data driven approach. Journal of Hydrology, 438, 223–233.
Thirumalaiah, K., & Deo, M. C. (1998). Real-time flood forecasting using neural networks. Computer-Aided Civil and Infra-architecture Engineering, 13(2), 101–111.
Van Ooyen, A., & Nienhuis, B. (1992). Improving the convergence of the back-propagation algorithm. Neural Networks, 5(3), 465–471.
Witt, A., Eilts, M. D., Stumpf, G. J., Johnson, J. T., Mitchell, E. D. W., & Thomas, K. W. (1998). An enhanced hail detection algorithm for the WSR-88D. Weather and Forecasting, 13(2), 286–303.
Yu, P. S., Chen, S. T., & Chang, I. F. (2006). Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328(3), 704–716.
Acknowledgements
This research was supported by the Ministry of Science and Technology in Taiwan under Grant No. MOST 105-2625-M-197-001. Support from the Water Resources Agency in Taiwan is also acknowledged.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ouyang, HT. Nonlinear autoregressive neural networks with external inputs for forecasting of typhoon inundation level. Environ Monit Assess 189, 376 (2017). https://doi.org/10.1007/s10661-017-6100-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10661-017-6100-6