A novel hybrid framework to model the relationship of daily river discharge with meteorological variables

• Autorzy: Shabbir Maha , Chand Sohail , Iqbal Farhat

Identyfikatory

DOI

10.26491/mhwm/187899

• Języki publikacji: EN

Abstrakty

EN

River discharge is affected by many factors, such as water level, rainfall, and precipitation. This study proposes a new hybrid framework named LAES (LASSO-ANN-EMD-SVM) to model the relationship of daily river discharge with meteorological variables. This hybrid framework is a composite of the least absolute shrinkage and selection operator (LASSO), an artificial neural network (ANN), and an error correction method. In the first stage, LASSO identifies meteorological variables that have a significant influence on the generation of river discharge. Next, the ANN model is used to predict river discharge using meteorological variables selected by LASSO, and the error series is determined. The error series is decomposed into intrinsic mode functions and residuals using empirical mode decomposition (EMD). The EMD components are modeled using the support vector machine (SVM) model, and the error predictions are aggregated. In the last stage, the LASSO-ANN predictions and the predicted error series are aggregated as the final discharge prediction. The proposed hybrid framework is illustrated on the Kabul River of Pakistan. The performance of the proposed hybrid framework is compared with six models using various performance measures and the Diebold-Mariano test. These models include multiple linear regression (MLR), SVM, ANN, LASSO-MLR, LASSO-SVM, and LASSO-ANN models. The findings reveal that the proposed hybrid model outperforms all other models considered in the study. In the testing phase, the root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) of the proposed LAES hybrid model are 337.143 m3/s, 32.354%, and 218.353 m3/s which are smaller than all other models compared in the study. Our proposed hybrid system is an efficient model for river discharge prediction that will be helpful in water management and protection against floods. Long-term prediction can help to identify the major effects of climate change and to make evidence-based environmental policies.

Słowa kluczowe

EN

LASSO; river discharge; ANN; SVM; EMD

• Wydawca: Instytut Meteorologii i Gospodarki Wodnej - Państwowy Instytut Badawczy
• Czasopismo: Meteorology Hydrology and Water Management. Research and Operational Applications
• Rocznik: 2023
• Tom: Vol. 11, Iss. 2
• Strony: 70--94
• Opis fizyczny: Bibliogr. 42 poz., rys., tab.

Twórcy

autor

Shabbir Maha

• University of the Punjab, Pakistan

• https://orcid.org/0000-0002-1525-2505

autor

Chand Sohail

• University of the Punjab, Pakistan

• https://orcid.org/0000-0002-4564-143X

autor

Iqbal Farhat

• Imam Abulrahman Bin Faisal University, Saudi Arabia

• https://orcid.org/0000-0002-8579-0966

Bibliografia

• Adnan R.M., Mostafa R.R., Elbeltagi A., Yaseen Z.M., Shahid S., Kisi O., 2022, Development of new machine learning model for streamflow prediction: case studies in Pakistan, Stochastic Environmental Research and Risk Assessment, 36, 999-1033, DOI: 10.1007/s00477-021-02111-z.
• Ali S., Shahbaz M., 2020, Streamflow forecasting by modeling the rainfall-streamflow relationship using artificial neural networks, Modeling Earth Systems and Environment, 6, 1645-1656, DOI: 10.1007/s40808-020-00780-3.
• Baydaroğlu Ö., Koçak K., Duran K., 2018, River flow prediction using hybrid models of support vector regression with the wavelet transform, singular spectrum analysis and chaotic approach, Meteorology and Atmospheric Physics, 130, 349-359, DOI: 10.1007/s00703-017-0518-9.
• Bui A., Johnson F., Wasko C., 2019, The relationship of atmospheric air temperature and dew point temperature to extreme rainfall, Environmental Research Letters, 14 (7), DOI: 10.1088/1748-9326/ab2a26.
• Cheng K., Wei S., Fu Q., Li T., 2019, Adaptive management of water resources based on an advanced entropy method to quantify agent information, Journal of Hydroinformatics, 21 (3), 381-396, DOI: 10.2166/hydro.2019.007.
• Dariane A., Azimi S., 2018, Streamflow forecasting by combining neural networks and fuzzy models using advanced methods of input variable selection, Journal of Hydroinformatics, 20 (2), 520-532. DOI: 10.2166/hydro.2017.076.
• Duan J., Zuo H., Bai Y., Duan J., Chang M., Chen B., 2021, Short-term wind speed forecasting using recurrent neural networks with error correction, Energy, 217, DOI: 10.1016/j.energy.2020.119397.
• Elbeltagi A., Nunno F.D., Kushwaha N.L., Marinis G.D., Granata F., 2022, River flow rate prediction in the Des Moines watershed (Iowa, USA): a machine learning approach, Stochastic Environmental Research and Risk Assessment, 36, 3835-3855, DOI: 10.1007/s00477-022-02228-9.
• Emadi A., Sobhani R., Ahmadi H., Boroomandnia A., Zamanzad-Ghavidel S., Azamathulla H.M., 2022, Multivariate modeling of river water withdrawal using a hybrid evolutionary data-driven method, Water Supply, 22 (1), 957- 980, DOI: 10.2166/ws.2021.224.
• Gleason C.J., Smith L.C., Lee J., 2014, Retrieval of river discharge solely from satellite imagery and at-many-stations hydraulic geometry: Sensitivity to river form and optimization parameters, Water Resources Research, 50 (12), 9604-9619, DOI: 10.1002/2014WR016109.
• Hu J., Wu Y., Sun P., Zhao F., Sun K., Li T., Sivakumar B., Qiu L., Sun Y., Jin Z., 2022, Predicting long-term hydrological change caused by climate shifting in the 21st century in the headwater area of the Yellow River basin, Stochastic Environmental Research and Risk Assessment, 36, 1651-1668, DOI: 10.1007/s00477-021-02099-6.
• Huang N.E., Shen Z., Long S.R., Wu M.C., Shih H.H., Zheng Q., Yen N.C., Tung C.C., Liu H.H., 1998, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society A. London, 454 (1971), 903-995, DOI: 10.1098/rspa.1998.0193.
• Jungsheng C., Dejie Y., Yu Y., 2006, A fault diagnosis approach for roller bearings based on EMD method and AR model, Mechanical Systems Signal Processing, 20 (2), 350-362, DOI: 10.1016/j.ymssp.2004.11.002.
• Kachrimanis K., Kamaryan V., Malamataris S., 2003, Artificial neural networks (ANNs) and modeling of powder flow, International Journal of Pharmaceutics, 250 (1), 13-23, DOI: 10.1016/S0378-5173(02)00528-8.
• Kang Y., Cheng X., Chen P., Zhang S., Yang Q., 2023, Monthly runoff prediction by a multivariate hybrid model based on decomposition-normality and Lasso regression, Environmental Science and Pollution Research, 30, 27743-27762, DOI: 10.1007/s11356-022-23990-x.
• Kisi O., Alizamir M., Shiri J., 2021, Conjunction model design for intermittent streamflow forecasts: extreme learning machine with discrete wavelet transform, [in:] Intelligent Data Analytics for Decision-Support Systems in Hazard Mitigation, Springer, Singapore, 171-181, DOI: 10.1007/978-981-15-5772-9_9.
• Lei Y., He Z., Zi Y., 2003, Application of the EEMD method to rotor fault diagnosis of rotating machinery, Mechanical Systems and Signal Processing, 23 (4), 1327-1338, DOI: 10.1016/j.ymssp.2008.11.005.
• Luo X., Xiaohui Y., Zhu S., Xu Z., Meng L., Peng J., 2019, A hybrid support vector regression framework for streamflow forecast, Journal of Hydrology, 568, 184-193, DOI: 10.1016/j.jhydrol.2018.10.064.
• Malik A., Tikhamarine Y., Souag-Gamane D., Kisi O., Pham Q.B., 2020, Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction, Stochastic Environmental Research and Risk Assessment, 34, 1755-1773, DOI: 10.1007/s00477-020-01874-1.
• Mangukiya N.K., Mehta D.J., Jariwala R., 2022, Flood frequency analysis and inundation mapping for lower Narmada basin, India, Water Practice and Technology, 17(2), 612-622, DOI: 10.2166/wpt.2022.009.
• Mehmood A., Jia S., Lv A., Zhu W., Mehmood R., Saifullah M., Adnan M.R., 2021, Detection of spatial shift in flood regime of the Kabul river basin in Pakistan, causes, challenges, and opportunities, Water, 13 (9), 1296-1301, DOI: 10.3390/w13091276.
• Mehr A.D., Gandomi A.H., 2021, MSGP-LASSO: An improved multi-stage genetic programming model for streamflow prediction, Information Sciences, 561, 181-195, DOI: 10.1016/j.ins.2021.02.011.
• Mehta D.J., Eslamian S., Prajapati K., 2022, Flood modelling for a data-scare semi-arid region using 1-D hydrodynamic model: a case study of Navsari Region, Modeling Earth Systems and Environment, 8 (2), 2675-2685, DOI: 10.1007/s40808-021-01259-5.
• Meng E., Huang S., Huang Q., Fang W., Wang H., Leng G., Wang L., Liang H., 2021, A hybrid VMD-SVM model for practical streamflow prediction using an innovative input selection framework, Water Resources Management, 35, 1321-1337, DOI: 10.1007/s11269-021-02786-7.
• Poul A.K., Shourian M., Ebrahimi H., 2019, A comparative study of MLR, KNN, ANN and ANFIS models with wavelet transform in monthly stream flow prediction, Water Resources Management, 33, 2907-2923, DOI: 10.1007/s11269-019-02273-0.
• R Core Team, 2022, R: A language and environment for statistical computing, R Foundation for Statistical Computing, Vienna, Austria, https://www.R-project.org/.
• Rasouli H., 2022, Climate change impacts on water resource and air pollution in Kabul sub-basins, Afghanistan, Advances in Geological and Geotechnical Engineering Research, 4 (1), 11-27, DOI: 10.30564/agger.v4i1.4312.
• Rasouli K., Hsieh W.W., Cannon A.J., 2012, Daily streamflow forecasting by machine learning methods with weather and climate inputs, Journal of Hydrology, 414-415, 284-293, DOI: 10.1016/j.jhydrol.2011.10.039.
• Ravindran S.M., Bhaskaran S.K., Ambat S.K., 2021, A deep neural network architecture to model reference evapotranspiration using a single input meteorological parameter, Environmental Processes, 8, 1567-1599, DOI: 10.1007/s40710-021-00543-x.
• Saidi H., Dresti C., Manca D., Ciampittiello M., 2018, Quantifying impacts of climate variability and human activities on the streamflow of an Alpine river, Environmental Earth Sciences, 77, DOI: 10.1007/s12665-018-7870-z.
• Shabbir M., Chand S., Iqbal F., 2022, A Novel Hybrid Method for River Discharge Prediction. Water Resources Management, 36, 253-272. DOI: https://doi.org/10.1007/s11269-021-03026-8.
• Shabbir M., Chand S., Iqbal F., 2023, Prediction of river inflow of the major tributaries of Indus river basin using hybrids of EEMD and LMD methods, Arabian Journal of Geosciences, 16, 257, DOI: 10.1007/s12517-023- 11351-y.
• Shabbir M., Chand S., Iqbal F., 2024, Novel hybrid and weighted ensemble models to predict river discharge series with outliers, Kuwait Journal of Science, 51 (2), DOI: 10.1016/j.kjs.2024.100188.
• Silva R.G., Ribeiro M.H., Moreno S.R., Mariani V.C., Coelho L.D., 2021, A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting, Energy, 216, DOI: 10.1016/j.energy.2020.119174.
• Tibshirani R., 1996, Regression Shrinkage and Selection via the Lasso, Journal of Royal Statistical Society: Series B (Methodological), 58 (1), 267-288, DOI: 10.1111/j.2517-6161.1996.tb02080.x.
• Vapnik V., 1995, The nature of statistical learning theory, Springer, New York, 188 pp., DOI: 10.1007/978-1-4757-2440-0.
• Wang J., Li Y., 2018, Multi-step ahead wind speed prediction based on optimal feature extraction, long short term memory neural network and error correction strategy, Applied Energy, 230, 429-443, DOI: 10.1016/j.apenergy.2018.08.114.
• Yan S., Wang X., Zhang Y., Liu D., Yi Y., Li C., Liu Q., Yang Z., 2020, A hybrid PCA-GAM model for investigating the spatiotemporal impacts of water level fluctuations on the diversity of benthic macroinvertebrates in Baiyangdian Lake, North China, Ecological Indicators, 116, DOI: 10.1016/j.ecolind.2020.106459.
• Yousuf I., Ghumman A.R., Hashmi H.N., 2017, Optimally sizing small hydropower project under future projected flows, KSCE Journal of Civil Engineering, 21, 1964-1978, DOI: 10.1007/s12205-016-1043-y.
• Zeinali M., Azari A., Heidari M., 2020, Multiobjective optimization for water resource management in low-flow areas based on a coupled surface water–groundwater model, Journal of Water Resources Planning and Management, 146 (5), DOI: 10.1061/(ASCE)WR.1943-5452.0001189.
• Zhang X., Liu P., Zhao Y., Deng C., Li Z., Xiong M., 2018a, Error correction-based forecasting of reservoir water levels: Improving accuracy over multiple lead times, Environmental Modelling and Software, 104, 27-39, DOI: 10.1016/j.envsoft.2018.02.017.
• Zhang Z., Zhang Q., Singh V.P., 2018b, Univariate streamflow forecasting using commonly used data-driven models: Literature review and case study, Hydrological Sciences Journal, 63 (7), 1091-1111, DOI: 10.1080/02626667.2018.1469756.