[en] In this research, we demonstrate the effectiveness of a convolutional neural network (CNN) model, integrated with the ERA5-Land dataset, for accurately simulating daily streamflow in a mountainous watershed. Our methodology harnesses image-based inputs, incorporating spatial distribution maps of key environmental variables, including temperature, snowmelt, snow cover, snow depth, volumetric soil water content, total evaporation, total precipitation, and leaf area index. The proposed CNN architecture, while drawing inspiration from classical designs, is specifically tailored for the task of streamflow prediction. The model’s performance, assessed during both the training and testing phases, demonstrates high accuracy, reflected quantitatively in metrics such as RMSE, MAPE, R2, and NSE. Notably, the model exhibits enhanced accuracy in predicting lower flow rates, particularly in autumn and winter, as evidenced by an average RMSE of 2.02 m3/s for flows below 13.8 m3/s. In contrast, the model’s precision decreases in high flow rate scenarios, predominantly in spring and early summer. The implementation of forward feature selection (FFS) has further optimized the model, pinpointing total evaporation and volumetric soil water as key parameters, thus enabling a more efficient model with accuracy comparable to the initial, more complex version. This research underscores the practical utility of an image-based approach using CNN models for streamflow prediction. Moreover, the adoption of the freely available and universally accessible ERA5-Land dataset highlights its effectiveness as a valuable and cost-efficient tool for streamflow prediction. Graphical Abstract: (Figure presented.)
RAJABI, Mohammadmahdi ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE) ; Civil and Environmental Engineering Faculty, Tarbiat Modares University, Tehran, Iran
Oskouei, Ebrahim Asadi; Atmospheric Science and Meteorology Research Center, Tehran, Iran
Al-Maktoumi, Ali; Water Research Center, Sultan Qaboos University, Muscat, Oman ; College of Agriculture and Marine Sciences, Sultan Qaboos University, Muscat, Oman
External co-authors :
yes
Language :
English
Title :
Enhancing streamflow prediction in a mountainous watershed using a convolutional neural network with gridded data
J. Adamowski C. Karapataki Comparison of multivariate regression and artificial neural networks for peak urban water-demand forecasting: evaluation of different ANN learning algorithms J Hydrol Eng 2010 15 10 729 743 10.1061/(ASCE)HE.1943-5584.0000245
R.M. Adnan et al. Daily streamflow prediction using optimally pruned extreme learning machine J Hydrol 2019 577 123981 10.1016/j.jhydrol.2019.123981
Ahmed A, et al. (2022) New double decomposition deep learning methods for stream-flow water level forecasting using remote sensing modis satellite variables, climate indices and observations. Ravinesh C. and Ghahramani, Afshin and Feng, Qi and Raj, Nawin and Yin, Zhenliang and Yang, Linshan, New double decomposition deep learning methods for stream-flow water level forecasting using remote sensing modis satellite variables, Climate Indices and Observations
A. Altunkaynak Forecasting surface water level fluctuations of Lake Van by artificial neural networks Water Resour Manage 2007 21 399 408 10.1007/s11269-006-9022-6
S. Anderson V. Radić Evaluation and interpretation of convolutional long short-term memory networks for regional hydrological modelling Hydrol Earth Syst Sci 2022 26 3 795 825 10.5194/hess-26-795-2022
G. Asadollahfardi H. Zangooei S.H. Aria E. Danesh Application of artificial neural networks to predict total dissolved solids at the Karaj Dam Environ Qual Manage 2017 26 3 55 72 10.1002/tqem.21493
M.F. Azam S. Srivastava Mass balance and runoff modelling of partially debris-covered Dokriani Glacier in monsoon-dominated Himalaya using ERA5 data since 1979 J Hydrol 2020 590 125432 10.1016/j.jhydrol.2020.125432
S.-S. Baek J. Pyo J.A. Chun Prediction of water level and water quality using a CNN-LSTM combined deep learning approach Water 2020 12 12 3399 1:CAS:528:DC%2BB3MXoslSjsbo%3D 10.3390/w12123399
R. Barzegar M.T. Aalami J. Adamowski Coupling a hybrid CNN-LSTM deep learning model with a boundary corrected maximal overlap discrete wavelet transform for multiscale lake water level forecasting J Hydrol 2021 598 126196 10.1016/j.jhydrol.2021.126196
T. Bellini Forward search outlier detection in data envelopment analysis Eur J Oper Res 2012 216 1 200 207 10.1016/j.ejor.2011.07.023
K.J. Beven Rainfall-runoff modelling: the primer 2011 John Wiley & Sons
D.M. Carlisle J. Falcone D.M. Wolock M.R. Meador R.H. Norris Predicting the natural flow regime: models for assessing hydrological alteration in streams River Res Appl 2010 26 2 118 136 10.1002/rra.1247
A. Cerioli A. Farcomeni M. Riani Strong consistency and robustness of the forward search estimator of multivariate location and scatter J Multivar Anal 2014 126 167 183 10.1016/j.jmva.2013.12.010
Y. Chang Y. Qi Z. Wang Comprehensive evaluation of IMERG, ERA5-Land and their fusion products in the hydrological simulation of three karst catchments in Southwest China J Hydrol: Reg Stud 2024 52 101671
C. Chen et al. A short-term flood prediction based on spatial deep learning network: a case study for Xi County China J Hydrol 2022 607 127535 10.1016/j.jhydrol.2022.127535
M.-Y. Cheng M.-T. Cao Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines Appl Soft Comput 2014 22 178 188 10.1016/j.asoc.2014.05.015
M. Cheng F. Fang T. Kinouchi I. Navon C. Pain Long lead-time daily and monthly streamflow forecasting using machine learning methods J Hydrol 2020 590 125376 10.1016/j.jhydrol.2020.125376
S.R. Clark J. Lerat J.-M. Perraud P. Fitch Deep learning for monthly rainfall-runoff modelling: a comparison with classical rainfall-runoff modelling across Australia Hydrol Earth Syst Sci Discuss 2023 2023 1 34
Dozat T (2016) Incorporating nesterov momentum into adam
B. Du Q. Zhou J. Guo S. Guo L. Wang Deep learning with long short-term memory neural networks combining wavelet transform and principal component analysis for daily urban water demand forecasting Expert Syst Appl 2021 171 114571 10.1016/j.eswa.2021.114571
D.C. Edossa M.S. Babel Application of ANN-based streamflow forecasting model for agricultural water management in the Awash River Basin, Ethiopia Water Resour Manage 2011 25 1759 1773 10.1007/s11269-010-9773-y
H.I. Erdal O. Karakurt Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms J Hydrol 2013 477 119 128 10.1016/j.jhydrol.2012.11.015
X. Fan Y. Liu A generalized model for intersensor NDVI calibration and its comparison with regression approaches IEEE Trans Geosci Remote Sens 2016 55 3 1842 1852 10.1109/TGRS.2016.2635802
D. Feng K. Fang C. Shen Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales Water Resour Res 2020 56 9 e2019WR026793 10.1029/2019WR026793
Fill J (2021) Development of the bayesian recurrent neural network architectures for hydrological time series forecasting
A. Gharehbaghi R. Ghasemlounia Application of AI approaches to estimate discharge coefficient of novel kind of sharp-crested V-notch weirs J Irrig Drain Eng 2022 148 3 04022001 10.1061/(ASCE)IR.1943-4774.0001646
A. Ghasemi J. Amanollahi Integration of ANFIS model and forward selection method for air quality forecasting Air Qual Atmos Health 2019 12 59 72 1:CAS:528:DC%2BC1cXitVSltr3F 10.1007/s11869-018-0630-0
Ghose DK (2018) Measuring discharge using back-propagation neural network: a case study on Brahmani river basin, Intelligent Engineering Informatics: Proceedings of the 6th International Conference on FICTA. Springer, pp 591–598. https://doi.org/10.1007/978-981-10-7566-7_59
Gibelin AL, Calvet JC, Roujean JL, Jarlan L, Los SO (2006) Ability of the land surface model ISBA‐A‐gs to simulate leaf area index at the global scale: comparison with satellites products. J Geophys Res: Atmos 111(D18). https://doi.org/10.1029/2005JD006691
Y. Grusson et al. Assessing the capability of the SWAT model to simulate snow, snow melt and streamflow dynamics over an alpine watershed J Hydrol 2015 531 574 588 10.1016/j.jhydrol.2015.10.070
J. Guo J. Zhou H. Qin Q. Zou Q. Li Monthly streamflow forecasting based on improved support vector machine model Expert Syst Appl 2011 38 10 13073 13081 10.1016/j.eswa.2011.04.114
J.S. Hagen E. Leblois D. Lawrence D. Solomatine A. Sorteberg Identifying major drivers of daily streamflow from large-scale atmospheric circulation with machine learning J Hydrol 2021 596 126086 10.1016/j.jhydrol.2021.126086
S.H. Haji A.M. Abdulazeez Comparison of optimization techniques based on gradient descent algorithm: a review PalArch’s J Archaeol Egypt/egyptology 2021 18 4 2715 2743
H. Han R.R. Morrison Data-driven approaches for runoff prediction using distributed data Stoch Environ Res Risk Assess 2021 36 8 2153 2171 10.1007/s00477-021-01993-3
M. Heidarnejad S.H. Golmaee A. Mosaedi M.Z. Ahmadi Estimation of sediment volume in Karaj Dam Reservoir (Iran) by hydrometry method and a comparison with hydrography method Lake Reservoir Manage 2006 22 3 233 239 10.1080/07438140609353900
H.M.V.V. Herath J. Chadalawada V. Babovic Hydrologically informed machine learning for rainfall–runoff modelling: towards distributed modelling Hydrol Earth Syst Sci 2021 25 8 4373 4401 10.5194/hess-25-4373-2021
H. Hersbach ERA5 reanalysis is in production ECMWF Newsletter 2016 147 7 5
K.I. Hodges R.W. Lee L. Bengtsson A comparison of extratropical cyclones in recent reanalyses ERA-Interim, NASA MERRA, NCEP CFSR, and JRA-25 J Clim 2011 24 18 4888 4906 10.1175/2011JCLI4097.1
R.T. Hurkmans B. van den Hurk M. Schmeits F. Wetterhall I.G. Pechlivanidis Seasonal streamflow forecasting for fresh water reservoir management in the Netherlands: an assessment of multiple prediction systems J Hydrometeorol 2023 24 7 1275 1290 10.1175/JHM-D-22-0107.1
V.Y. Ivanov et al. Breaking down the computational barriers to real-time urban flood forecasting Geophys Res Lett 2021 48 20 e2021GL093585 10.1029/2021GL093585
D.J. Karran E. Morin J. Adamowski Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes J Hydroinf 2014 16 3 671 689 10.2166/hydro.2013.042
W.J. Khai et al. Daily forecasting of dam water levels using machine learning Int J Civ Eng Technol (IJCIET) 2019 10 314 323
Z.M. Khaing K.M.W. Soe M.M. Thu E. Norgbey Comparative study of semi-distributed and 2D-distributed hydrological models for streamflow prediction in a data scarce mountainous watershed Model Earth Syst Environ 2022 8 3 2933 2949 10.1007/s40808-021-01271-9
J.A. Khan S. Van Aelst R.H. Zamar Building a robust linear model with forward selection and stepwise procedures Comput Stat Data Anal 2007 52 1 239 248 10.1016/j.csda.2007.01.007
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1-2):273–324
Y. LeCun L. Bottou Y. Bengio P. Haffner Gradient-based learning applied to document recognition Proc IEEE 1998 86 11 2278 2324 10.1109/5.726791
E.H. Lee J.H. Kim Y.M. Choo D.J. Jo Application of flood nomograph for flood forecasting in urban areas Water 2018 10 1 53 10.3390/w10010053
Q. Li et al. Improved daily SMAP satellite soil moisture prediction over China using deep learning model with transfer learning J Hydrol 2021 600 126698 10.1016/j.jhydrol.2021.126698
P. Li J. Zhang P. Krebs Prediction of flow based on a CNN-LSTM combined deep learning approach Water 2022 14 6 993 10.3390/w14060993
Li Y, Yang J (2019) Hydrological time series prediction model based on attention-LSTM neural network, Proceedings of the 2019 2nd International Conference on Machine Learning and Machine Intelligence, pp 21–25
Y. Lin et al. Bias learning improves data driven models for streamflow prediction J Hydrol: Reg Stud 2023 50 101557
Y. Liu et al. Monthly streamflow forecasting based on hidden Markov model and Gaussian Mixture Regression J Hydrol 2018 561 146 159 10.1016/j.jhydrol.2018.03.057
S. Londhe P. Dixit Forecasting stream flow using model trees Int J Earth Sci Eng 2011 4 6 282 285
Meko DM, Woodhouse CA (2011) Application of streamflow reconstruction to water resources management. Dendroclimatology: Progress and prospects 231–261
H. Meyer C. Reudenbach T. Hengl M. Katurji T. Nauss Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation Environ Model Softw 2018 101 1 9 10.1016/j.envsoft.2017.12.001
Mhammedi Z, Hellicar A, Rahman A, Kasfi K, Smethurst P (2016) Recurrent neural networks for one day ahead prediction of stream flow, Proceedings of the Workshop on Time Series Analytics and Applications, pp 25–31
Molteni F, et al (2011) The new ECMWF seasonal forecast system (System 4), 49. European Centre for medium-range weather forecasts Reading
D.N. Moriasi M.W. Gitau N. Pai P. Daggupati Hydrologic and water quality models: performance measures and evaluation criteria Trans ASABE 2015 58 6 1763 1785 10.13031/trans.58.10715
Mosaffa H, Sadeghi M, Mallakpour I, Jahromi MN, Pourghasemi HR (2022) Application of machine learning algorithms in hydrology, Computers in earth and environmental sciences. Elsevier, pp 585–591
Muñoz Sabater J (2019) ERA5-Land hourly data from 1981 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS), 10(10.24381)
J. Muñoz-Sabater et al. ERA5-Land: a state-of-the-art global reanalysis dataset for land applications Earth Syst Sci Data 2021 13 9 4349 4383 10.5194/essd-13-4349-2021
A. Nazeer S. Maskey T. Skaugen M.E. McClain Simulating the hydrological regime of the snow fed and glaciarised Gilgit Basin in the Upper Indus using global precipitation products and a data parsimonious precipitation-runoff model Sci Total Environ 2022 802 149872 1:CAS:528:DC%2BB3MXhvFSru7nM 10.1016/j.scitotenv.2021.149872
H. Noor M. Vafakhah M. Taheriyoun M. Moghadasi Hydrology modelling in Taleghan mountainous watershed using SWAT J Water Land Dev 2014 20 1 11 18 10.2478/jwld-2014-0003
S. Nourinezhad M.M. Rajabi Simulation-based cost-risk analysis of phosphorus reduction alternatives: application to a mountainous watershed Model Earth Syst Environ 2023 9 1 847 863 10.1007/s40808-022-01532-1
G.A. Papacharalampous H. Tyralis Evaluation of random forests and prophet for daily streamflow forecasting Adv Geosci 2018 45 201 208 10.5194/adgeo-45-201-2018
L. Parviz K. Rasouli Development of precipitation forecast model based on artificial intelligence and subseasonal clustering J Hydrol Eng 2019 24 12 04019053 10.1061/(ASCE)HE.1943-5584.0001862
A. Pelosi F. Terribile G. D’Urso G.B. Chirico Comparison of ERA5-Land and UERRA MESCAN-SURFEX reanalysis data with spatially interpolated weather observations for the regional assessment of reference evapotranspiration Water 2020 12 6 1669 10.3390/w12061669
L.T. Pham L. Luo A. Finley Evaluation of random forests for short-term daily streamflow forecasting in rainfall-and snowmelt-driven watersheds Hydrol Earth Syst Sci 2021 25 6 2997 3015 1:CAS:528:DC%2BB3MXis1ymsbjI 10.5194/hess-25-2997-2021
R. Prasad R.C. Deo Y. Li T. Maraseni Input selection and performance optimization of ANN-based streamflow forecasts in the drought-prone Murray Darling Basin region using IIS and MODWT algorithm Atmos Res 2017 197 42 63 10.1016/j.atmosres.2017.06.014
M. Rahimzad et al. Performance comparison of an LSTM-based deep learning model versus conventional machine learning algorithms for streamflow forecasting Water Resour Manage 2021 35 12 4167 4187 10.1007/s11269-021-02937-w
Reis GB et al (2021) Effect of environmental covariable selection in the hydrological modeling using machine learning models to predict daily streamflow. J Environ Manag 290:112625
M. Sakizadeh Assessment the performance of classification methods in water quality studies, a case study in Karaj River Environ Monit Assess 2015 187 1 12 1:CAS:528:DC%2BC2MXhtlOhtbbP 10.1007/s10661-015-4761-6
Shayeghi M, et al (2015) Assessing the fauna of aquatic insects for possible use for malaria vector control in large river, central Iran. Acta Medica Iranica 523–532
Solomatine D, See LM, Abrahart R (2008) Data-driven modelling: concepts, approaches and experiences. Practical hydroinformatics: computational intelligence and technological developments in water applications pp. 17–30
C.M. Song Hydrological image building using curve number and prediction and evaluation of runoff through convolution neural network Water 2020 12 8 2292 1:CAS:528:DC%2BB3cXisFGmtrrL 10.3390/w12082292
C.M. Song Data construction methodology for convolution neural network based daily runoff prediction and assessment of its applicability J Hydrol 2022 605 127324 10.1016/j.jhydrol.2021.127324
A. Sood V. Smakhtin Global hydrological models: a review Hydrol Sci J 2015 60 4 549 565 1:CAS:528:DC%2BC2MXktlGksbc%3D 10.1080/02626667.2014.950580
K. Stefanidis G. Varlas A. Vourka A. Papadopoulos E. Dimitriou Delineating the relative contribution of climate related variables to chlorophyll-a and phytoplankton biomass in lakes using the ERA5-Land climate reanalysis data Water Res 2021 196 117053 1:CAS:528:DC%2BB3MXnt1yjtro%3D 10.1016/j.watres.2021.117053
M. Taghi Sattari M. Pal H. Apaydin F. Ozturk M5 model tree application in daily river flow forecasting in Sohu Stream, Turkey Water Resour 2013 40 233 242 1:CAS:528:DC%2BC3sXns1Kjtb0%3D 10.1134/S0097807813030123
M.L. Tan et al. Evaluation of NASA POWER and ERA5-Land for estimating tropical precipitation and temperature extremes J Hydrol 2023 624 129940 10.1016/j.jhydrol.2023.129940
P. Tencaliec A.C. Favre C. Prieur T. Mathevet Reconstruction of missing daily streamflow data using dynamic regression models Water Resour Res 2015 51 12 9447 9463 10.1002/2015WR017399
S.M. Vieira J.M. Sousa T.A. Runkler Two cooperative ant colonies for feature selection using fuzzy models Expert Syst Appl 2010 37 4 2714 2723 10.1016/j.eswa.2009.08.026
Z. Wan et al. Streamflow reconstruction and variation characteristic analysis of the Ganjiang River in China for the past 515 years Sustainability 2020 12 3 1168 10.3390/su12031168
Z. Wang et al. Flood hazard risk assessment model based on random forest J Hydrol 2015 527 1130 1141 10.1016/j.jhydrol.2015.06.008
X. Wu J. Su W. Ren H. Lü H F. Yuan Statistical comparison and hydrological utility evaluation of ERA5-Land and IMERG precipitation products on the Tibetan Plateau J Hydrol 2023 620 129384 10.1016/j.jhydrol.2023.129384
T. Xu A.J. Valocchi J. Choi E. Amir Use of machine learning methods to reduce predictive error of groundwater models Groundwater 2014 52 3 448 460 1:CAS:528:DC%2BC2cXnt1aqtLY%3D 10.1111/gwat.12061
R. Yan et al. Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering Expert Syst Appl 2021 169 114513 10.1016/j.eswa.2020.114513
Z.M. Yaseen et al. Non-tuned machine learning approach for hydrological time series forecasting Neural Comput Appl 2018 30 1479 1491 10.1007/s00521-016-2763-0
H. Yoon S.-C. Jun Y. Hyun G.-O. Bae K.-K. Lee A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer J Hydrol 2011 396 1–2 128 138 10.1016/j.jhydrol.2010.11.002
C.-C. Young W.-C. Liu M.-C. Wu A physically based and machine learning hybrid approach for accurate rainfall-runoff modeling during extreme typhoon events Appl Soft Comput 2017 53 205 216 10.1016/j.asoc.2016.12.052
D. Yun et al. Developing a deep learning model for the simulation of micro-pollutants in a watershed J Clean Prod 2021 300 126858 1:CAS:528:DC%2BB3MXovVagu7c%3D 10.1016/j.jclepro.2021.126858
H. Zakizadeh H. Ahmadi G. Zehtabian A. Moeini A. Moghaddamnia A novel study of SWAT and ANN models for runoff simulation with application on dataset of metrological stations Phys Chem Earth, Parts a/b/c 2020 120 102899 10.1016/j.pce.2020.102899
F. Zhang et al. Simulating low and high streamflow driven by snowmelt in an insufficiently gauged alpine basin Stoch Env Res Risk Assess 2016 30 59 75 10.1007/s00477-015-1028-2
B. Zhang H. Zhang G. Zhao J. Lian Constructing a PM2. 5 concentration prediction model by combining auto-encoder with Bi-LSTM neural networks Environ Model Softw 2020 124 104600 10.1016/j.envsoft.2019.104600
S. Zhu J. Wei H. Zhang Y. Xu H. Qin Spatiotemporal deep learning rainfall-runoff forecasting combined with remote sensing precipitation products in large scale basins J Hydrol 2023 616 128727 10.1016/j.jhydrol.2022.128727
