Deep Learning Approach for Runoff Prediction – Evaluating the Long-Short-Term Memory Neural Network Architectures for Capturing Extreme Discharge Events in the Ouergha Basin, Morocco

Karmouda, Nourelhouda; Bouramtane, Tarik; Tahiri, Mounia; Kacimi, Ilias; Leblanc, Marc; Kassou, Nadia

doi:10.12912/27197050/174146

Artykuł - szczegóły

Tytuł artykułu

Deep Learning Approach for Runoff Prediction – Evaluating the Long-Short-Term Memory Neural Network Architectures for Capturing Extreme Discharge Events in the Ouergha Basin, Morocco

Autorzy

Karmouda Nourelhouda , Bouramtane Tarik , Tahiri Mounia , Kacimi Ilias , Leblanc Marc , Kassou Nadia

Treść / Zawartość

Pełne teksty:

Pobierz

Identyfikatory

DOI

10.12912/27197050/174146

Warianty tytułu

Języki publikacji

Abstrakty

Rainfall-runoff modeling plays a crucial role in achieving efficient water resource management and flood forecasting, particularly in the context of increasing intensity and frequency of extreme meteorological events induced by climate change. Therefore, the aim of this research is to assess the accuracy of the Long-Short-Term Memory (LSTM) neural networks and the impact of its architecture in predicting runoff, with a particular focus on capturing extreme hydrological discharges in the Ouergha basin; a Moroccan Mediterranean basin with historical implications in many cases of flooding; using solely daily rainfall and runoff data for training. For this purpose, three LSTM models of different depths were constructed, namely LSTM 1 single-layer, LSTM 2 bi-layer, and LSTM 3 tri-layer, their window size and hyperparameters were first tuned, and on seven years of daily data they were trained, then validated and tested on two separate years to ensure the generalization on unseen data. The performance of the three models was compared using hydrogram-plots, Scatter-plots, Taylor diagrams, and several statistical metrics. The results indicate that the single-layer LSTM 1 outperforms the other models, it consistently achieves higher overall performance on the training, validation, and testing periods with a coefficient of determination R-squared of 0.92, 0.97, and 0.95 respectively; and with Nash-Sutcliffe efficiency metric of 0.91, 0.94 and 0.94 respectively, challenging the conventional beliefs about the direct link between complexity and effectiveness. Furthermore, all the models are capable of capturing the extreme discharges, although, with a moderate und erprediction trend for LSTM 1 and 2 as it does not exceed -25% during the test period. For LSTM 3, even if its underestimation is less pronounced, its increased error rate reduces the confidence in its performance. This study highlights the importance of aligning model complexity with data specifications and suggests the necessity of considering unaccounted factors like upstream dam releases to enhance the efficiency in capturing the peaks of extreme events.

Słowa kluczowe

Morocco hydrological modelling deep neural network runoff prediction Ouergha extreme event long-short-term memory LSTM

Wydawca

Lubelski Oddział Polskiego Towarzystwo Inżynierii Ekologicznej
Lublin University of Technology
WNGB Wydawnictwo Naukowe

Czasopismo

Ecological Engineering & Environmental Technology

Rocznik

2023

Tom

Vol. 24, iss. 9

Strony

271--290

Opis fizyczny

Bibliogr. 66 poz., rys., tab.

Twórcy

autor

Karmouda Nourelhouda

nourelhouda_karmouda@um5.ac.ma

Geosciences, Water and Environment Laboratory, Faculty of Sciences, Mohammed V University in Rabat, Avenue Ibn Batouta, Rabat, Morocco

https://orcid.org/0000-0003-0367-4898

autor

Bouramtane Tarik

Geosciences, Water and Environment Laboratory, Faculty of Sciences, Mohammed V University in Rabat, Avenue Ibn Batouta, Rabat, Morocco

https://orcid.org/0000-0003-3187-095X

autor

Tahiri Mounia

Geosciences, Water and Environment Laboratory, Faculty of Sciences, Mohammed V University in Rabat, Avenue Ibn Batouta, Rabat, Morocco

https://orcid.org/0000-0001-7523-1645

autor

Kacimi Ilias

Geosciences, Water and Environment Laboratory, Faculty of Sciences, Mohammed V University in Rabat, Avenue Ibn Batouta, Rabat, Morocco

https://orcid.org/0000-0001-9977-8880

autor

Leblanc Marc

Geosciences, Water and Environment Laboratory, Faculty of Sciences, Mohammed V University in Rabat, Avenue Ibn Batouta, Rabat, Morocco
Hydrogeology Laboratory, UMR EMMAH, University of Avignon, Avignon, France

https://orcid.org/0000-0003-3176-9253

autor

Kassou Nadia

Geosciences, Water and Environment Laboratory, Faculty of Sciences, Mohammed V University in Rabat, Avenue Ibn Batouta, Rabat, Morocco

https://orcid.org/0000-0002-1591-6674

Bibliografia

1. Alardhi, S., Al-Jadir, T., Hasan, A., Jaber, A., Al Saedi, L., 2023. Design of Artificial Neural Network for Prediction of Hydrogen Sulfide and Carbon Dioxide Concentrations in a Natural Gas Sweetening Plant. Ecol. Eng. Environ. Technol. 24, 55–66. https://doi.org/10.12912/27197050/157092
2. Alpaydin, E., 2010. Introduction to Machine Learning, fourth edition. MIT, USA.
3. Aqnouy, M., Messari, J.E.S.E., Bouadila, A., Morabbi, A., Benaabidate, L., Al-Djazouli, M.O., 2021. Modeling of Continuous and Extreme Hydrological Processes Using Spatially Distributed Models MERCEDES, VICAIR and VISHYR in a Mediterranean Watershed. Ecol. Eng. Environ. Technol., 22, 9–23. https://doi.org/10.12912/27197050/132098
4. Babu, S.R., Varma, K.P.V.K., Mohan, K.S.S., 2022. Artificial Neural Network Technique for Estimating the Thermo-Physical Properties of Water-Alumina Nanofluid. Ecol. Eng. Environ. Technol., 23, 97–106. https://doi.org/10.12912/27197050/145583
5. Bahremand, A., De Smedt, F., 2010. Predictive Analysis and Simulation Uncertainty of a Distributed Hydrological Model. Water Resour Manage, 24, 2869–2880. https://doi.org/10.1007/s11269-010-9584-1
6. Bahremand, A., De Smedt, F., 2008. Distributed Hydrological Modeling and Sensitivity Analysis in Torysa Watershed, Slovakia. Water Resour Manage, 22, 393–408. https://doi.org/10.1007/s11269-007-9168-x
7. Bashayreh, E., Manasrah, A., Alkhalil, S., Abdelhafez, E., 2021. Estimation of Water Disinfection by Using Data Mining. Ecol. Eng. Environ. Technol., 22, 109–116. https://doi.org/10.12912/27197050/132088
8. Bergstra, J., Bengio, Y., 2012. Random Search for Hyper-Parameter Optimization. Mach. Learn 281–305.
9. Berhich, A., Belouadha, F.-Z., Kassiri, A.E., 2020. Single and Multilayer LSTM Models for Positive COVID-19 Cases Prediction: Proceedings of the 2nd International Conference on Advanced Technologies for Humanity., 27–34. https://doi.org/10.5220/0010426900270034
10.Blöschl, G., et al., 2019. Changing climate both increases and decreases European river floods. Nature 573, 108–111. https://doi.org/10.1038/s41586-019-1495-6
11. Bouramtane, T., Leblanc, M., Kacimi, I., Ouatiki, H., Boudhar, A., 2023. The contribution of remote sensing and input feature selection for groundwater level prediction using LSTM neural networks in the Oum Er-Rbia Basin, Morocco. Frontiers in Water, 5. https://doi.org/10.3389/frwa.2023.1241451
12.Chen, F., Tiwari, S., Mohammed, K.S., Huo, W., Jamróz, P., 2023. Minerals resource rent responses to economic performance, greener energy, and environmental policy in China: Combination of ML and ANN outputs. Resources Policy, 81, 103–307. https://doi.org/10.1016/j.resourpol.2023.103307
13. Clarke, B., Otto, F., Stuart-Smith, R., Harrington, L., 2022. Extreme weather impacts of climate change: an attribution perspective. Environ. Res: Climate 1, https://doi.org/10.1088/2752-5295/ac6e7d
14. Combe, M., 1975. Le bassin Gharb-Maamora et les petits bassins septentrionaux des oueds Dradère et Souieire., in: Ressources En Eau Du Maroc, Notes et Mem. Serv. Géol. Maroc, pp. 93–145.
15. Damavandi, H.G., Shah, R., Stampoulis, D., Wei, Y., Boscovic, D., Sabo, J., 2019. Accurate prediction of streamflow using long short-term memory network: A case study in the Brazos river basin in Texas. International Journal of Environmental Science and Development, 10, 294–300. https://doi.org/10.18178/ijesd.2019.10.10.1190
16. Demirel, M.C., Venancio, A., Kahya, E., 2009. Flow forecast by SWAT model and ANN in Pracana basin, Portugal. Advances in Engineering Software, 40, 467–473. https://doi.org/10.1016/j.advengsoft.2008.08.002
17. Fang, K., Shen, C., Kifer, D., Yang, X., 2017. Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network. Geophysical Research Letters 44. https://doi.org/10.1002/2017GL075619
18. Fischer, T., Krauss, C., 2018. Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270, 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
19. Gao, S., Huang, Y., Zhang, S., Han, J., Wang, G., Zhang, M., Lin, Q., 2020. Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. Journal of Hydrology, 589, 125188. https://doi.org/10.1016/j.jhydrol.2020.125188
20. Gers, F.A., Schmidhuber, J., Cummins, F., 2000. Learning to forget: continual prediction with LSTM. Neural Comput 12, 2451–2471. https://doi.org/10.1162/089976600300015015
21. Goodfellow, I., Bengio, Y., Courville, A., 2016. Deep Learning; MIT Press, Cambridge, MA, USA.
22. Govindaraju, R.S., Rao, A.R. (Eds.), 2000. Artificial Neural Networks in Hydrology, Water Science and Technology Library. Springer Netherlands, Dordrecht. https://doi.org/10.1007/978-94-015-9341-0
23. Gupta, H.V., Sorooshian, S., Yapo, P.O., 1999. Status of Automatic Calibration for Hydrologic Models: Comparison with Multilevel Expert Calibration. Journal of Hydrologic Engineering 4, 135–143. https://doi.org/10.1061/(ASCE)1084-0699(1999)4:2(135)
24. Harrington, P., 2017. Multiple versus single set validation of multivariate models to avoid mistakes. Crit Rev Anal Chem 33–46.
25. Haykin, S., 1999. Neural Networks: A Comprehensive Foundation, 2nd edition. ed. Prentice-Hall, Englewood Cliffs, New Jersey, USA.
26. Hochreiter, S., 1991. Untersuchungen zu dynamischen neuronalen netzen.
27. Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J., 2001. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. IEEE Press, A Field Guide to Dynamical Recurrent Neural Networks. A Field Guide to Dynamical Recurrent Neural Networks.
28. Hochreiter, S., Schmidhuber, J., 1997. Long Short-Term Memory. Neural Computation 9, 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
29. Hsu, K., Gupta, H.V., Sorooshian, S., 1995. Artificial Neural Network Modeling of the Rainfall-Runoff Process. Water Resources Research, 31, 2517–2530. https://doi.org/10.1029/95WR01955
30. Hu, C., Wu, Q., Li, H., Jian, S., Li, N., Lou, Z., 2018. Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation. Water, 10, 1543. https://doi.org/10.3390/w10111543
31.Jimeno-Sáez, P., Senent-Aparicio, J., Pérez-Sánchez, J., Pulido-Velazquez, D., 2018. A Comparison of SWAT and ANN Models for Daily Runoff Simulation in Different Climatic Zones of Peninsular Spain. Water, 10, 192. https://doi.org/10.3390/w10020192
32.Juan, C., Genxu, W., Tianxu, M., Xiangyang, S., 2017. ANN Model-Based Simulation of the Runoff Variation in Response to Climate Change on the Qinghai-Tibet Plateau, China. Advances in Meteorology 2017, e9451802. https://doi.org/10.1155/2017/9451802
33. Karmouda, N., Naïma, E.A., Kacimi, I., Mahe, G., Bouramtane, T., Brirhet, H., Idrissi, A., Kassou, N., 2023. Hydrological Modelling of Extreme Events in Ouergha Mediterranean Basin, Northern Morocco, Using a Deterministic Model and Gridded Precipitations. Iraqi Geological Journal, 56, 1–20. https://doi.org/10.46717/igj.56.2B.1ms-2023-8-10
34. Kawakami, K., 2008. Supervised Sequence Labelling with Recurrent Neural Networks. (Ph.D. Thesis). Technical University of Munich, Munich, Germany.
35. Kingma, D.P., Ba, J., 2017. Adam: A Method for Stochastic Optimization San Diego.
36. Kouassi, A.M., Koffi, Y.B., Kouamé, K.F., Lasm, T., 2013. Application d’un modèle conceptuel et d’un modèle de réseaux de neurones artificiels à la simulation des débits annuels dans le bassin versant du N’zi-Bandama (Côte d’Ivoire) 09, 64–76.
37. Li, M., Wang, Z., 2022. LSTM-augmented deep networks for time-variant reliability assessment of dynamic systems. Reliability Engineering & System Safety, 217, 108014. https://doi.org/10.1016/j.ress.2021.108014
38. Liu, Y., Zhang, T., Kang, A., Li, J., Lei, X., 2021. Research on Runoff Simulations Using Deep-Learning Methods. Sustainability, 13, 1336. https://doi.org/10.3390/su13031336
39. Man, Y., Yang, Q., Shao, J., Wang, G., Bai, L., Xue, Y., 2022. Enhanced LSTM Model for Daily Runoff Prediction in the Upper Huai River Basin, China. Engineering, S2095809922002806. https://doi.org/10.1016/j.eng.2021.12.022
40. Mao, G., Wang, M., Liu, J., Wang, Z., Wang, K., Meng, Y., Zhong, R., Wang, H., Li, Y., 2021. Comprehensive comparison of artificial neural networks and long short-term memory networks for rainfall-runoff simulation. Physics and Chemistry of the Earth, Parts A/B/C, 123, 103026. https://doi.org/10.1016/j.pce.2021.103026
41. Mejia Cajica, F.A., García Henao, J.A., Barrios Hernández, C.J., Riveil, M., 2021. High Performance Computing: 7th Latin American Conference, CARLA 2020, Cuenca, Ecuador, September 2–4, 2020. https://doi.org/10.1007/978-3-030-68035-0
42. Moriasi, D.N., Arnold, J.G., Liew, M.W., Bingner, R.L., Harmel, R.D., Veith, T.L., 2007. Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations. Transactions of the ASABE, 50, 885–900. https://doi.org/10.13031/2013.23153
43. Moriasi, D.N., Gitau, M.W., Daggupati, P., 2015. Hydrologic and Water Quality Models: Performance Measures and Evaluation Criteria. Trans. ASABE, 58, 1763–1785. https://doi.org/10.13031/trans.58.10715
44. Msatef, K., Benaabidate, L., Bouignane, A., 2018. Hydrological and hydroclimatic regimes in the Ouergha watershed. E3S Web Conf., 37, 1–11. https://doi.org/10.1051/e3sconf/20183704001
45. Oni, O.M., Aremu, A.A., Oladapo, O.O., Agboluaje, B.A., Fajemiroye, J.A., 2022. Artificial neural network modeling of meteorological and geological influences on indoor radon concentration in selected tertiary institutions in Southwestern Nigeria. Journal of Environmental Radioactivity, 251–252, 106933. https://doi.org/10.1016/j.jenvrad.2022.106933
46. Rahimzad, M., Moghaddam Nia, A., Zolfonoon, H., Soltani, J., Danandeh Mehr, A., Kwon, H.-H., 2021. Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting. Water Resour Manage, 35, 4167–4187. https://doi.org/10.1007/s11269-021-02937-w
47. Rajaee, T., Ebrahimi, H., Nourani, V., 2019. A review of the artificial intelligence methods in groundwater level modeling. Journal of Hydrology, 572, 336–351. https://doi.org/10.1016/j.jhydrol.2018.12.037
48. Ripley, B.D., 1996. Pattern Recognition and Neural Networks Cambridge, MA, USA.
49. Sahraei, A., Chamorro, A., Kraft, P., Breuer, L., 2021. Application of Machine Learning Models to Predict Maximum Event Water Fractions in Streamflow. Frontiers in Water 3.
50. Salman, A.G., Heryadi, Y., Abdurahman, E., Suparta, W., 2018. Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting. Procedia Computer Science, 135, 89–98. https://doi.org/10.1016/j.procs.2018.08.153
51. Senoussi, S., Agoumi, A., Yacoubi, M., Fakhraddine, A., Sayouty, E.H., Mokssit, A., Chikri, N., 1999. Changements climatiques et ressources en eau Bassin versant de I’Ouergha (Maroc). Hydroécol. Appl. 11, 163–182. https://doi.org/10.1051/hydro:1999007
52. Servat, E., Dezetter, A., 1991. Selection of calibration objective fonctions in the context of rainfallronoff modelling in a Sudanese savannah area. Hydrological Sciences Journal, 36, 307–330. https://doi.org/10.1080/02626669109492517
53. Shanker, M., Hu, M.Y., Hung, M.S., 1996. Effect of data standardization on neural network training. Omega 24, 385–397. https://doi.org/10.1016/0305-0483(96)00010-2
54. Sharma, D.K., Chatterjee, M., Kaur, G., Vavilala, S., 2022. 3 - Deep learning applications for disease diagnosis, in: Gupta, D., Kose, U., Khanna, A., Balas, V.E. (Eds.), Deep Learning for Medical Applications with Unique Data. Academic Press, pp. 31–51. https://doi.org/10.1016/B978-0-12-824145-5.00005-8
55. Sherstinsky, A., 2020. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Physica D: Nonlinear Phenomena 404, 132306. https://doi.org/10.1016/j.physd.2019.132306
56. Singh, J., Knapp, H.V., Demissie, M., 2004. Hydrologic Modeling of the Iroquois River Watershed Using HSPF and SWAT. Illinois State Water Survey Contract, 08, 1–24.
57. Tingsanchali, T., 2000. Forecasting model of chao phraya river flood levels at bangkok., in: International Conference on Chao Phraya Delta. Citeseer, Bangkok, Thailand.
58. Westerhuis, J., Hoefsloot, H., Smit, S., Vis, D., Smilde, A., van Velzen, E., van Duijnhoven, J., van Dorsten, F., 2008. Assessment of PLSDA cross validation. Metabolomics, 81–9.
59. Wu, C.L., Chau, K.W., 2011. Rainfall–runoff modeling using artificial neural network coupled with singular spectrum analysis. Journal of Hydrology, 399, 394–409. https://doi.org/10.1016/j.jhydrol.2011.01.017
60. Xiang, Z., Yan, J., Demir, I., 2020. A Rainfall-Runoff Model With LSTM-Based Sequence-to-Sequence Learning. Water Resources Research, 56. https://doi.org/10.1029/2019WR025326
61. Xu, Y., Yao, L., Xu, P., Cui, W., Zhang, Z., Liu, F., Mao, B., Wen, Z., 2021. Load Forecasting Method for Building Energy Systems Based on Modified Two-Layer LSTM, in: 2021 3rd Asia Energy and Electrical Engineering Symposium. pp. 660–665.
62. Yin, H., Wang, F., Zhang, X., Zhang, Y., Chen, J., Xia, R., Jin, J., 2022. Rainfall-runoff modeling using long short-term memory-based step-sequence framework. Journal of Hydrology, 610, 127901. https://doi.org/10.1016/j.jhydrol.2022.127901
63. Young, Liu, 2015. Prediction and modelling of rainfall-runoff during typhoon events using a physically-based and artificial neural network hybrid model. Hydrol. Sci. ,J 60, 2102–2116.
64. Yu, Y., Si, X., Hu, C., Zhang, J., 2019. A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures. Neural Comput, 31, 1235–1270. https://doi.org/10.1162/neco_a_01199
65. Zema, D.A., Lucas-Borja, M.E., Fotia, L., Rosaci, D., Sarnè, G.M.L., Zimbone, S.M., 2020. Predicting the hydrological response of a forest after wildfire and soil treatments using an Artificial Neural Network. Computers and Electronics in Agriculture, 170, 105280. https://doi.org/10.1016/j.compag.2020.105280
66. Zia, T., Zahid, U., 2019. Long short-term memory recurrent neural network architectures for Urdu acoustic modeling. Int J Speech Technol, 22, 21–30. https://doi.org/10.1007/s10772-018-09573-7

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-febbe9ee-5525-4b9b-90fc-660721c43a37