Abstract
The insufficiency of hydrological time series prejudices the management of water resources in the Amazon, especially in small catchments. Thus, for the first time, through the Nonlinear Autoregressive Recurrent Neural Network with Exogenous Inputs (RNN-NARX), an attempt is made to simulate daily streamflow time series with a temporal resolution of 365 days, for five small Amazon catchments. A sensitivity analysis of the models was also performed to identify the lowest temporal resolution of the input to obtain satisfactory results. Since it is data-driven model, it is expected that these models have the ability to reproduce learning characteristics with less temporal variability, and make it possible to estimate daily streamflow time series with 365-day temporal resolution. For this objective, daily lagged rainfall and streamflow data were implemented with the support of the Cross-Correlation Function (CCF) and partial autocorrelation function (PACF) at the 5% significance level. Based on five statistical criteria, satisfactory results were obtained with supervised training based on 2 years of rainfall and streamflow data in four of the five analyzed basins (Igarapé of Prata, Piranhas River, Caeté River and Capivara River). According Garson’s algorithm, lagged rainfall is important for these simulations. In general, there are lower percentage errors in the dry periods, and overestimation of floods. In the practical context, the models developed and analyzed are applicable, mainly, for the simulation of average and minimum daily streamflows of small catchments in the Amazon, becoming a tool that should be used for sustainable evaluation purposes of the water availability of these catchments. However, in the case of simulating floods, it is necessary to apply hourly and lagged rainfall and streamflow data to the models.
Similar content being viewed by others
Data availability
Data will be made available on reasonable request.
References
Alvares CA, Stape JL, Sentelhas PC, Gonçalves JDM, Sparovek G (2013) Köppen’s climate classification map for Brazil. Meteorol Z 22(6):711–728. https://doi.org/10.1127/0941-2948/2013/0507
Banihabib ME, Bandari R, Peralta RC (2019) Auto-regressive neural-network models for long lead-time forecasting of daily flow. Water Resour Manag 33(1):159–172. https://doi.org/10.1007/s11269-018-2094-2
Bayer DM, Castro NMDR, Bayer FM (2012) Modelagem e previsão de vazões médias mensais do rio Potiribu utilizando modelos de séries temporais. Revista Brasileira de Recursos Hídricos 17(2):229–239. https://doi.org/10.21168/rbrh.v17n2.p229-239
Beale MH, Hagan MT, Demuth HB (2016) Neural network toolbox user’s guide. The MathWorks Inc, Natick, p 103
Behrangi A, Khakbaz B, Jaw TC, AghaKouchak A, Hsu K, Sorooshian S (2011) Hydrologic evaluation of satellite precipitation products over a mid-size basin. J Hydrol 397(3–4):225–237. https://doi.org/10.1016/j.jhydrol.2010.11.043
Beven KJ (2020) A history of the concept of time of concentration. Hydrol Earth Syst Sci 24(5):2655–2670. https://doi.org/10.5194/hess-24-2655-2020
Beven KJ, Wood EF, Sivapalan M (1988) On hydrological heterogeneity—catchment morphology and catchment response. J Hydrol 100(1–3):353–375. https://doi.org/10.1016/0022-1694(88)90192-8
Blanco CJC, Santos SSM, Quintas MC, Vinagre MVA, Mesquita ALA (2013) Contribution to hydrological modelling of small amazonian catchments: application of rainfall–runoff models to simulate flow duration curves. Hydrol Sci J 58(7):1423–1433. https://doi.org/10.1080/02626667.2013.830727
Chen S, Billings SA, Grant PM (1990) Non-linear system identification using neural networks. Int J Control 51(6):1191–1214. https://doi.org/10.1080/00207179008934126
Collischonn B, Collischonn W, Tucci CEM (2008) Daily hydrological modeling in the Amazon basin using TRMM rainfall estimates. J Hydrol 360(1–4):207–216. https://doi.org/10.1016/j.jhydrol.2008.07.032
Coulthard TJ, Lewin J, Macklin MG (2005) Modelling differential catchment response to environmental change. Geomorphology 69(1–4):222–241. https://doi.org/10.1016/j.geomorph.2005.01.008
Debastiani AB, Silva RDAD, Rafaeli Neto SL (2016) Eficácia da arquitetura MLP em modo closed-loop para simulação de um Sistema Hidrológico. Revista Brasileira de Recursos Hídricos 21:821–831. https://doi.org/10.1590/2318-0331.011615124
Dijkshoorn K, Huting J, Tempel P (2005) Update of the 1:5 million soil and terrain database for Latin America and the Caribbean (SOTERLAC; version 2.0). ISRIC—World Soil Information, Wageningen. https://www.isric.org/sites/default/files/isric_report_2005_01.pdf
Dudley RW, Hirsch RM, Archfield SA, Blum AG, Renard B (2020) Low streamflow trends at human-impacted and reference basins in the United States. J Hydrol 580:124254. https://doi.org/10.1016/j.jhydrol.2019.124254
Finnoff W, Hergert F, Zimmermann HG (1993) Improving model selection by nonconvergent methods. Neural Netw 6(6):771–783. https://doi.org/10.1016/S0893-6080(05)80122-4
Garson DG (1991) Interpreting neural network connection weights. Artif Intell Expert 6:47–51
Guzman SM, Paz JO, Tagert MLM (2017) The use of NARX neural networks to forecast daily groundwater levels. Water Resour Manag 31(5):1591–1603. https://doi.org/10.1007/s11269-017-1598-5
Guzman SM, Paz JO, Tagert MLM, Mercer AE (2019) Evaluation of seasonally classified inputs for the prediction of daily groundwater levels: NARX networks vs support vector machines. Environ Model Assess 24(2):223–234. https://doi.org/10.1007/s10666-018-9639-x
Haykin S (2002) Neural networks: a comprehensive foundation, 2nd edn. Pearson Education, Singapore
Hocking M, Kelly BF (2016) Groundwater recharge and time lag measurement through vertosols using impulse response functions. J Hydrol 535:22–35. https://doi.org/10.1016/j.jhydrol.2016.01.042
Hodgkins GA, Dudley RW, Nielsen MG, Renard B, Qi SL (2017) Groundwater-level trends in the US glacial aquifer system, 1964–2013. J Hydrol 553:289–303. https://doi.org/10.1016/j.jhydrol.2017.07.055
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366. https://doi.org/10.1016/0893-6080(89)90020-8
Karsoliya S (2012) Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. Int J Eng Trends Technol 3(6):714–717
Lee WK, Tuan Resdi TA (2016) Simultaneous hydrological prediction at multiple gauging stations using the NARX network for Kemaman catchment, Terengganu, Malaysia. Hydrol Sci J 61(16):2930–2945. https://doi.org/10.1080/02626667.2016.1174333
Legesse D, Vallet-Coulomb C, Gasse F (2003) Hydrological response of a catchment to climate and land use changes in Tropical Africa: case study South Central Ethiopia. J Hydrol 275(1–2):67–85. https://doi.org/10.1016/S0022-1694(03)00019-2
Leonard J, Andrieux P (1998) Infiltration characteristics of soils in Mediterranean vineyards in southern France. CATENA 32(3–4):209–223. https://doi.org/10.1016/S0341-8162(98)00049-6
Lin T, Horne BG, Giles CL (1998) How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies. Neural Netw 11(5):861–868. https://doi.org/10.1016/S0893-6080(98)00018-5
Liu YB, Gebremeskel S, De Smedt F, Hoffmann L, Pfister L (2003) A diffusive transport approach for flow routing in GIS-based flood modeling. J Hydrol 283(1–4):91–106. https://doi.org/10.1016/S0022-1694(03)00242-7
Maier HR, Dandy GC (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environ Model Softw 15(1):101–124. https://doi.org/10.1016/S1364-8152(99)00007-9
Maier HR, Jain A, Dandy GC, Sudheer KP (2010) Methods used for the development of neural networks for the prediction of water resource variables in river systems: current status and future directions. Environ Model Softw 25(8):891–909. https://doi.org/10.1016/j.envsoft.2010.02.003
Mendonça LM, Gomide IS, de Sousa JV, Blanco CJC (2021) Modelagem chuva-vazão via redes neurais artificiais para simulação de vazões de uma bacia hidrográfica da Amazônia. Revista de Gestão de Água da América Latina. https://doi.org/10.21168/rega.v18e2
Menezes Jr JMP, Barreto GA (2008) Long-term time series prediction with the NARX network: an empirical evaluation. Neurocomputing 71(16–18):3335–3343. https://doi.org/10.1016/j.neucom.2008.01.030
Mirus BB, Loague K (2013) How runoff begins (and ends): characterizing hydrologic response at the catchment scale. Water Resour Res 49(5):2987–3006. https://doi.org/10.1002/wrcr.20218
Moghaddamnia A, Remesan R, Kashani MH, Mohammadi M, Han D, Piri J (2009) Comparison of LLR, MLP, Elman, NNARX and ANFIS models—with a case study in solar radiation estimation. J Atmos Solar Terr Phys 71(8–9):975–982. https://doi.org/10.1016/j.jastp.2009.04.009
Moriasi DN, Arnold JG, Van Liew MW, Bingner RL, Harmel RD, Veith TL (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans ASABE 50(3):885–900. https://doi.org/10.13031/2013.23153
NASA JPL (2020) NASADEM merged DEM global 1 arc second V001. NASA EOSDIS land processes DAAC. https://doi.org/10.5067/MEaSUREs/NASADEM/NASADEM_HGT.001. Accessed 30 Dec 2020
Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I—a discussion of principles. J Hydrol 10(3):282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Paiva RCDD, Collischonn W, Bonnet MP, De Gonçalves LGG (2012) On the sources of hydrological prediction uncertainty in the Amazon. Hydrol Earth Syst Sci 16(9):3127–3137. https://doi.org/10.5194/hess-16-3127-2012
Panchal G, Ganatra A, Kosta YP, Panchal D (2011) Behavior analysis of multilayer perceptrons with multiple hidden neurons and hidden layers. Int J Comput Theory Eng 3(2):332–337. https://doi.org/10.7763/IJCTE.2011.V3.328
Peck R, Olsen C, Devore JL (2015) Introduction to statistics and data analysis. Cengage Learning, Boston
Peel MC, McMahon TA (2020) Historical development of rainfall-runoff modeling. Wiley Interdiscip Rev Water 7(5):e1471. https://doi.org/10.1002/wat2.1471
Ponce VM (1989) Engineering hydrology, principles and practices. Prentice-Hall, Englewood Cliffs
Prechelt L (1998) Automatic early stopping using cross validation: quantifying the criteria. Neural Netw 11(4):761–767. https://doi.org/10.1016/S0893-6080(98)00010-0
Quintas MC, Blanco CJ, Mesquita AL (2011) A non-linear rainfall-runoff model applied to Amazon small catchments with limited data to simulate the flow duration curves. Int J Hydrology Sci Technol 1(1–2):19–36. https://doi.org/10.1504/IJHST.2011.040738
Rezaeian Zadeh M, Amin S, Khalili D, Singh VP (2010) Daily outflow prediction by multilayer perceptron with logistic sigmoid and tangent sigmoid activation functions. Water Resour Manag 24(11):2673–2688. https://doi.org/10.1007/s11269-009-9573-4
Santana LR, Blanco CJC (2020) Contribution to the classification of small catchments according to the drainage area. Int J River Basin Manag 20(1):111–122. https://doi.org/10.1080/15715124.2020.1776301
Shen HY, Chang LC (2013) Online multistep-ahead inundation depth forecasts by recurrent NARX networks. Hydrol Earth Syst Sci 17(3):935–945. https://doi.org/10.5194/hess-17-935-2013
Sit M, Demiray BZ, Xiang Z, Ewing GJ, Sermet Y, Demir I (2020) A comprehensive review of deep learning applications in hydrology and water resources. Water Sci Technol 82(12):2635–2670. https://doi.org/10.48550/arXiv.2007.12269
Souza Jr CM, Shimbo JZ, Rosa MR, Parente LL, Alencar AA, Rudorff BF et al (2020) Reconstructing three decades of land use and land cover changes in Brazilian biomes with landsat archive and earth engine. Remote Sens 12(17):2735. https://doi.org/10.3390/rs12172735
Spaargaren OC, Deckers J (1998) The world reference base for soil resources. In: Schulte A, Ruhiyat D (eds) Soils of tropical forest ecosystems. Springer, Berlin. https://doi.org/10.1007/978-3-662-03649-5_2
Sudheer KP, Gosain AK, Ramasastri KS (2002) A data-driven algorithm for constructing artificial neural network rainfall‐runoff models. Hydrol Process 16(6):1325–1330. https://doi.org/10.1002/hyp.554
Tikhamarine Y, Souag-Gamane D, Ahmed AN, Sammen SS, Kisi O, Huang YF, El-Shafie A (2020) Rainfall-runoff modelling using improved machine learning methods: Harris hawks optimizer vs. particle swarm optimization. J Hydrol 589:125133. https://doi.org/10.1016/j.jhydrol.2020.125133
Towner J, Ficchí A, Cloke HL, Bazo J, Coughlan de Perez E, Stephens EM (2021) Influence of ENSO and tropical Atlantic climate variability on flood characteristics in the Amazon basin. Hydrol Earth Syst Sci 25(7):3875–3895. https://doi.org/10.5194/hess-25-3875-2021
Wang J, Chen Y (2022) Using NARX neural network to forecast droughts and floods over Yangtze River Basin. Nat Hazards 110(1):225–246. https://doi.org/10.1007/s11069-021-04944-x
Wilamowski BM, Chen Y, Malinowski A (1999) Efficient algorithm for training neural networks with one hidden layer. In: IJCNN’99. Proceedings of the international joint conference on neural networks, vol 3, pp 1725–1728. https://doi.org/10.1109/IJCNN.1999.832636
Wunsch A, Liesch T, Broda S (2018) Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX). J Hydrol 567:743–758. https://doi.org/10.1016/j.jhydrol.2018.01.045
Wunsch A, Liesch T, Broda S (2021) Groundwater level forecasting with artificial neural networks: a comparison of long short-term memory (LSTM), convolutional neural networks (CNNs), and non-linear autoregressive networks with exogenous input (NARX). Hydrol Earth Syst Sci 25(3):1671–1687. https://doi.org/10.5194/hess-25-1671-2021
Zhang J, Morris AJ (1998) A sequential learning approach for single hidden layer neural networks. Neural Netw 11(1):65–80. https://doi.org/10.1016/S0893-6080(97)00111-1
Acknowledgements
The authors thank ANA for providing the rainfall and streamflow data.
Funding
Coordination for the Improvement of Higher Education Personnel of Brasil (CAPES), Finance Code 001. CNPq for funding the research with productivity grant (Process 308147/2021-9).
Author information
Authors and Affiliations
Contributions
LMdM: data curation, formal analysis, investigation, methodology, software, supervision, validation, visualization, writing—original draft, writing—review and editing. CJCB: conceptualization, formal analysis, funding acquisition, methodology, project administration, resources, supervision, validation, visualization, writing—review and editing. FdOC: investigation, methodology, software, validation, visualization, writing—review and editing.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
de Mendonça, L.M., Blanco, C.J.C. & de Oliveira Carvalho, F. Recurrent neural networks for rainfall-runoff modeling of small Amazon catchments. Model. Earth Syst. Environ. 9, 2517–2531 (2023). https://doi.org/10.1007/s40808-022-01626-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-022-01626-w