COMPARATIVE ANALYSIS OF GRADIENT BOOSTING MACHINES AND LONG SHORT-TERM MEMORY NETWORKS FOR STREAM FLOW FORECASTING

A.F. SHAIKH, S.B. MORE, Y.L. BHIRUD, V.V. SHELAR, K.M. BAGWAN

Abstract


Stream flow forecasting is essential for effective water resource management and flood prediction, but it poses significant challenges due to the complex nature of hydrological systems. Traditional methods often struggle to capture temporal dependencies and nonlinear relationships within the data, leading to inaccuracies in predictions. The specific objectives of this study are to (1) evaluate the effectiveness of long short-term memory (LSTM) networks and gradient boosting machine (GBM) in predicting stream flow in the Garudeshwar watershed of the Narmada River basin in central India, and (2) compare their performance using several evaluation metrics. This study utilizes datasets spanning training, validation, and testing phases to thoroughly examine and compare the models' performances. The evaluation metrics include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-squared (R²), and Root Mean Square Percent Error (RMSPE). The findings demonstrate that GBM consistently outperforms LSTM across all datasets. For instance, on the training dataset, GBM achieved an MAE of 0.123, an RMSE of 0.456, and an R² of 0.96, whereas LSTM had an MAE of 0.234, an RMSE of 0.567, and an R² of 0.87. Similar trends were observed on the validation and testing datasets, with GBM maintaining superior performance metrics. By showcasing the superior performance of GBM, this research aims to enhance stream flow forecasting methods and support well-informed decision-making in water resource management and flood prediction efforts.


Keywords


Stream flow forecasting, Long Short-Term Memory networks, Water resource management, Gradient Boosting Machines

Full Text:

PDF

References


ABD RAHMAN A.N. OTHMAN F., WAN JAAFAR W.J., AHMED ELSHAFIE A.H.K. (2023). An assessment of floods' characteristics and patterns in Pahang, Malaysia, Larhyss Journal, No 55, pp. 89-105.

AJEAGAH G., BISSAYA R. (2017). Availability of water resources in cameroon: ecoenvironmental potentialities and sustainable management by the population, Larhyss Journal, No 32, pp. 7-22. (In French)

AKBARIAN M., SAGHAFIAN B., GOLIAN S. (2023). Monthly streamflow forecasting by machine learning methods using dynamic weather prediction model outputs over Iran, Journal of Hydrology, Vol. 620, Paper ID 129480. https://doi.org/10.1016/j.jhydrol.2023.129480

BAUDHANWALA D., MEHTA D., KUMAR V. (2024). Machine learning approaches for improving precipitation forecasting in the Ambica River basin of Navsari District, Gujarat, Water Practice and Technology. Vol. 19, Issue 4, pp. 1315-1329. https://doi.org/10.2166/wpt.2024.079

BENKACI T., MEZENNER N., DECHEMI N. (2020). Exploration of maximum likelihood method in extreme rainfall forecasting using four probability distributions - the case of northern Algeria, Larhyss Journal, No 43, pp. 57-72.

BRUNNER M.I., SLATER L., TALLAKSEN L.M., CLARK M. (2021). Challenges in modeling and predicting floods and droughts: A review, WIREs Water, Vol. 8, Issue 3. https://doi.org/10.1002/wat2.1520

CHENG M., FANG F., KINOUCHI T., NAVON I.M., PAIN C.C. (2020). Long lead-time daily and monthly streamflow forecasting using machine learning methods, Journal of Hydrology, Vol. 590, Paper ID 125376.

https://doi.org/10.1016/j.jhydrol.2020.125376

CHERKI K. (2019). Daily and instantaneous flood forecasting using artificial neural networks in a north-west Algerian watershed, Larhyss Journal, No 40, pp. 27-43.

DJEDDOU M., ACHOUR B. (2015). The use of a neural network technique for the prediction of sludge volume index in municipal wastewater treatment plant, Larhyss Journal, No 24, pp. 351-370.

DWARAKISH G.S., GANASRI B.P. (2015). Impact of land use change on hydrological systems: A review of current modeling approaches, Cogent Geoscience, Vol. 1, Issue 1, Paper ID 1115691. https://doi.org/10.1080/23312041.2015.1115691

GRANATA F., DI NUNNO F., DE MARINIS G. (2022). Stacked machine learning algorithms and bidirectional long short-term memory networks for multi-step ahead streamflow forecasting: A comparative study, Journal of Hydrology, Vol. 613, Paper ID 128431. https://doi.org/10.1016/j.jhydrol.2022.128431

FELLOUS S., BENDJAMA A., BENZAOUI Y. (2023). Use of machine learning algorithms and in situ data for estimating particulate organic carbon from the Mediterranean sea, Larhyss Journal, No 56, pp. 179-192.

FERNANDO H.M.S., GUNAWARDENA M.P., NAJIM M.M.M. (2021). Modelling of stream flows of a forested catchment in the tropics using HEC-HMS, Larhyss Journal, No 48, pp. 73-89.

HELLAL A., DJEDDOU M., LOUKAM I., HAMEED A.I., AL DALLAL J., SHAWAQFAH M. (2023). Predictive modeling of ozone dosing in drinking water treatment plant using deep learning comparative study between deep neural networks and convolutional neural networks, Larhyss Journal, No 55, pp. 145-159.

HACHEMI A., BENKHALED A. (2016). Flood- Duration-Frequency modeling application to Wadi Abiodh, Biskra (Algeria). (2016), Larhyss Journal, No 27, pp. 277-297.

HAFNAOUI M.A., BOULTIF M., DABANLI I. (2023). Floods in Algeria: analyzes and statistics, Larhyss Journal, No 56, pp. 351-369.

JODHANI, K.H., PATEL, D., MADHAVAN, N., SINGH, S.K. (2023a). Soil Erosion Assessment by RUSLE, Google Earth Engine, and Geospatial Techniques over Rel River Watershed, Gujarat, India, Water Conservation Science and Engineering, Vol. 8, Issue 1, Paper ID 49. https://doi.org/10.1007/s41101-023-00223-x

JODHANI, K.H., PATEL, D., MADHAVAN, N. (2023b). A review on analysis of flood modelling using different numerical models, Materials Today: Proceedings, Vol. 80, pp. 3867–3876. https://doi.org/10.1016/j.matpr.2021.07.405

JODHANI, K.H., JODHANI, K.H., PATEL, D., MADHAVAN, N. (2023c). Land Use Land Cover Classification for REL River Using Machine Learning Techniques, In 2023 International Conference on IoT, Communication and Automation Technology (ICICAT) IEEE, pp.1–3. https://doi.org/10.1109/ICICAT57735.2023.10263663

KANTHARIA V., MEHTA D., KUMAR V., SHAIKH M.P., JHA S. (2024). Rainfall–runoff modeling using an Adaptive Neuro-Fuzzy Inference System considering soil moisture for the Damanganga basin, Journal of Water and Climate Change, Vol. 15, Issue 5, pp. 2518-2531. https://doi.org/10.2166/wcc.2024.143

KEDAM N., TIWARI D.K., KUMAR V., KHEDHER K.M., SALEM M.A. (2024). River stream flow prediction through advanced machine learning models for enhanced accuracy, Results in Engineering, Vol. 22, Paper ID 102215. https://doi.org/10.1016/j.rineng.2024.102215

KHALIQ M.N., OUARDA T.B.M.J., GACHON P., SUSHAMA L., ST-HILAIRE A. (2009). Identification of hydrological trends in the presence of serial and cross correlations: A review of selected methods and their application to annual flow regimes of Canadian rivers, Journal of Hydrology, Vol. 368, Issue 1–4, pp. 117–130. https://doi.org/10.1016/j.jhydrol.2009.01.035

KUMAR V., AZAMATHULLA H.MD., SHARMA K.V., MEHTA D.J., MAHARAJ K.T. (2023). The State of the Art in Deep Learning Applications, Challenges, and Future Prospects: A Comprehensive Review of Flood Forecasting and Management, Sustainability, Vol. 15, Issue 13, Paper ID 10543.

https://doi.org/10.3390/su151310543

KUMAR V., KEDAM N., SHARMA K.V., MEHTA D.J., CALOIERO T. (2023). Advanced Machine Learning Techniques to Improve Hydrological Prediction: A Comparative Analysis of Streamflow Prediction Models, Water, Vol. 15, Issue 14, Paper ID 2572. https://doi.org/10.3390/w15142572

LE X.-H., NGUYEN D.-H., JUNG S., YEON M., LEE G. (2021). Comparison of Deep Learning Techniques for River Streamflow Forecasting, IEEE Access, Vol. 9, pp. 71805–71820. https://doi.org/10.1109/ACCESS.2021.3077703

LIU D., JIANG W., MU L., WANG S. (2020a). Streamflow Prediction Using Deep Learning Neural Network: Case Study of Yangtze River, IEEE Access, Vol. 8, pp. 90069–90086. https://doi.org/10.1109/ACCESS.2020.2993874

LIU D., JIANG W., MU L., WANG S. (2020b). Streamflow Prediction Using Deep Learning Neural Network: Case Study of Yangtze River, IEEE Access, Vol. 8, pp. 90069–90086. https://doi.org/10.1109/ACCESS.2020.2993874.

LIU J., YANG H., GOSLING S.N., KUMMU M., FLÖRKE M., PFISTER S., HANASAKI, N., WADA, Y., ZHANG, X., ZHENG, C., ALCAMO, J., OKI, T. (2017). Water scarcity assessments in the past, present, and future, Earth’s Future, Vol. 5, Issue 6, pp. 545–559. https://doi.org/10.1002/2016EF000518

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, Vol. 8, Issue 2, pp. 2675–2685. https://doi.org/10.1016/j.rineng.2023.101571

MUTTIL N., CHAU K.W. (2007). Machine-learning paradigms for selecting ecologically significant input variables, Engineering Applications of Artificial Intelligence, Vol. 20, Issue 6, pp. 735–744.

https://doi.org/10.1016/j.engappai.2006.11.016

RAHIMZAD M., MOGHADDAM N.A., ZOLFONOON H., SOLTANI J., DANANDEH M.A., KWON H.H. (2021). Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting, Water Resources Management, Vol. 35, Issue 12, pp. 4167–4187. https://doi.org/10.1007/s11269-021-02937-w

RASOULI K., HSIEH W.W., CANNON A.J. (2012). Daily streamflow forecasting by machine learning methods with weather and climate inputs, Journal of Hydrology, Vols. 414–415, pp. 284–293. https://doi.org/10.1016/j.jhydrol.2011.10.039

REZAIE-BALF M., NAGANNA S.R., KISI O., EL-SHAFIE A. (2019). Enhancing streamflow forecasting using the augmenting ensemble procedure coupled machine learning models: case study of Aswan High Dam, Hydrological Sciences Journal, Vol. 64, Issue 13, pp. 1629–1646. https://doi.org/10.1080/02626667.2019.1661417

ROUISSAT B., SMAIL N. (2022). Contribution of water resource systems analysis for the dynamics of territorial rebalancing, case of Tafna system, Algeria, Larhyss Journal, No 50, pp. 69-94.

SARAIVA S.V., CARVALHO F. DE O., SANTOS C.A.G., BARRETO L.C., FREIRE P.K., DE M.M. (2021). Daily streamflow forecasting in Sobradinho Reservoir using machine learning models coupled with wavelet transform and bootstrapping, Applied Soft Computing, Vol. 102, Paper ID 107081.

https://doi.org/10.1016/j.asoc.2021.107081

WEGAYEHU E.B., MULUNEH F.B. (2022). Short-Term Daily Univariate Streamflow Forecasting Using Deep Learning Models, Advances in Meteorology, Wiley online Library, Hindawi, Issue 1, Article ID 1860460, pp. 1–21.

https://doi.org/10.1155/2022/1860460

WU C.L., CHAU K.W. (2010). Data-driven models for monthly streamflow time series prediction, Engineering Applications of Artificial Intelligence, Vol. 23, Issue 8, pp. 1350–1367. https://doi.org/10.1016/j.engappai.2010.04.003

YASEEN Z.M., EL-SHAFIE A., JAAFAR O., AFAN H.A., SAYL K.N. (2015). Artificial intelligence-based models for stream-flow forecasting: 2000–2015, Journal of Hydrology, Vol. 530, pp. 829–844. https://doi.org/10.1016/j.jhydrol.2015.10.038


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.