Machine learning-based method for forecasting water levels in irrigation and drainage systems

Abstract This study presents possible applications of machine learning (ML) methods for estimating water levels without a throughout understanding of hydrological processes and complex databases of irrigation systems. The Bac-Hung-Hai catchment, the biggest irrigation and drainage area in Vietnam, is selected as a case study due to the large database on this case consisting of 3348 samples drawn over a 21-year monitoring period. The state-of-the-art Gradient tree boosting (GTB)-based model was developed and is compared with eight other common ML methods. The proposed GTB-based model consistently showed the best performance, with the lowest value of mean-squares-error and the greatest values for R 2 and adjusted R 2 in all case studies. Moreover, over 91% of the total samples had an error rate of below 10% between the predicted and the observed values. The results suggested that the GTB model can predict water level with high accuracy, thus helping researchers and policy-makers devise proactive strategies for hydraulic regulation and sustainable water management.

[1]  Viet-Hung Truong,et al.  A robust method for safety evaluation of steel trusses using Gradient Tree Boosting algorithm , 2020, Adv. Eng. Softw..

[2]  Armas Andrei,et al.  Numerical Limitations of 1D Hydraulic Models Using MIKE11 or HEC-RAS software - Case study of Baraolt River, Romania , 2017 .

[3]  Josette Garnier,et al.  Hydrological regime and water budget of the Red River Delta (Northern Vietnam) , 2010 .

[4]  Muhammad Mukhlisin,et al.  Accuracy Enhancement for Forecasting Water Levels of Reservoirs and River Streams Using a Multiple-Input-Pattern Fuzzification Approach , 2014, TheScientificWorldJournal.

[5]  Megan Mehaffey,et al.  Development of a spatially complete floodplain map of the conterminous United States using random forest , 2018, The Science of the total environment.

[6]  Yousry Mahmoud Ghazaw,et al.  Design and analysis of a canal section for minimum water loss , 2011 .

[7]  Jong Wan Hu,et al.  Real-time prediction of water level change using adaptive neuro-fuzzy inference system , 2017 .

[8]  Gang Zhao,et al.  A hybrid machine learning framework for real-time water level prediction in high sediment load reaches , 2020, Journal of Hydrology.

[9]  A. Abuzaid,et al.  Implications of irrigation water quality on shallow groundwater in the Nile Delta of Egypt: A human health risk prospective , 2021 .

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  Quang Viet Ly,et al.  Characteristics and influencing factors of organic fouling in forward osmosis operation for wastewater applications: A comprehensive review. , 2019, Environment international.

[12]  Organic carbon source-dependent properties of soluble microbial products in sequencing batch reactors and its effects on membrane fouling. , 2019, Journal of environmental management.

[13]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[14]  Zhao Fan,et al.  Health risks of occupational exposure to toxic chemicals in coal mine workplaces based on risk assessment mathematical model based on deep learning , 2021 .

[15]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[16]  H. Pourghasemi,et al.  Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. , 2018, The Science of the total environment.

[17]  R. Elliott,et al.  Hydropower generation, flood control and dam cascades: A national assessment for Vietnam , 2018 .

[18]  Vijay P. Singh,et al.  Flood Hydrograph Prediction Using Machine Learning Methods , 2018, Water.

[19]  Bo Du,et al.  Scene Classification via a Gradient Boosting Random Convolutional Network Framework , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Ramalakshmi Ramar,et al.  An efficient approach for rice prediction from authenticated Block chain node using machine learning technique , 2020 .

[21]  Mariusz Ptak,et al.  Forecasting of water level in multiple temperate lakes using machine learning models , 2020 .

[22]  L. Bui,et al.  Modelling bank erosion dependence on natural and anthropogenic factors — case study of Ganh Hao estuary, Bac Lieu - Ca Mau, Vietnam , 2020 .

[23]  Zaher Mundher Yaseen,et al.  Incorporating synoptic-scale climate signals for streamflow modelling over the Mediterranean region using machine learning models , 2019, Hydrological Sciences Journal.

[24]  Takahiro Hosono,et al.  Multiscale groundwater level forecasting: Coupling new machine learning approaches with wavelet transforms , 2020 .

[25]  P. D. Porey,et al.  HEC-RAS BASED HYDRODYNAMIC MODEL IN PREDICTION OF STAGES OF LOWER TAPI RIVER , 2011 .

[26]  Özgür Kisi,et al.  Forecasting daily lake levels using artificial intelligence approaches , 2012, Comput. Geosci..

[27]  Chang Hong Wang.  Application of HEC-RAS Model in Simulation of Water Surface Profile of River , 2014 .

[28]  Zongxue Xu,et al.  Mapping flood susceptibility in mountainous areas on a national scale in China. , 2018, The Science of the total environment.

[29]  Xixi Lu,et al.  Sediment budget as affected by construction of a sequence of dams in the lower Red River, Viet Nam , 2015 .

[30]  Omid Bozorg-Haddad,et al.  Simulating thermal stratification and modeling outlet water temperature in reservoirs with a data-mining method , 2018, Journal of Water Supply: Research and Technology-Aqua.

[31]  Klemen Kenda,et al.  Usage of statistical modeling techniques in surface and groundwater level prediction , 2020 .

[32]  Jungwook Kim,et al.  Development of Water Level Prediction Models Using Machine Learning in Wetlands: A Case Study of Upo Wetland in South Korea , 2019 .

[33]  Sivaram Rajeyyagari,et al.  Accuracy enhancement in mobile phone recycling process using machine learning technique and MEPH process , 2020 .

[34]  Halla Marinósdóttir.  Applications of different machine learning methods for water level predictions , 2019 .

[35]  M. Ye,et al.  Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas , 2018, Journal of Hydrology.

[36]  P. Willems,et al.  Comparative analysis of 1-D river flow models applied in a quasi 2-D approach for floodplain inundation prediction , 2013 .

[37]  Ismail Abustan,et al.  Comparison between capabilities of HEC-RAS and MIKE11 hydraulic models in river flood risk modelling (a case study of Sungai Kayu Ara River basin, Malaysia) , 2012 .

[38]  Larry W. Mays,et al.  Water distribution systems handbook , 2012 .

[39]  Rosmina A. Bustami,et al.  Artificial neural network for precipitation and water level predictions of Bedup River , 2007 .

[40]  Ching-Hsue Cheng,et al.  A Time-Series Water Level Forecasting Model Based on Imputation and Variable Selection Method , 2017, Comput. Intell. Neurosci..

[41]  Subira E. Munishi,et al.  Simiyu River catchment parameterization using SWAT model , 2007 .

[42]  Minxing Si,et al.  Development of a predictive emissions model using a gradient boosting machine learning method , 2020 .

[43]  Aftab Ahmed Khan,et al.  Machine learning techniques for monthly river flow forecasting of Hunza River, Pakistan , 2020, Earth Science Informatics.