Water Level Prediction of Taocha Based on CCS-GBDT Model

The aim is to forecast water level accurately and to provide scientific basis for decision-making of water regulation of South-to-North Water Transfer Project. Firstly, the cuckoo algorithm is improved. Secondly, the improved chaotic cuckoo algorithm is used to optimize the gradient boosted decision tree. Taking the water level at the head of Taocha canal as an example, the model is used to predict the water level. The analysis shows that the relative error between the improved gradient boosted decision tree and the measured water level is reduced by 2.70%. Compared with BP neural network, RBF network and SVR show better, accuracy.

[1]  Weiguo Zhao,et al.  RVM based on PSO for Groundwater Level Forecasting , 2012, J. Comput..

[2]  Edson Wendland,et al.  Stochastic simulation of time-series models combined with geostatistics to predict water-table scenarios in a Guarani Aquifer System outcrop area, Brazil , 2012, Hydrogeology Journal.

[3]  Chuan Ding,et al.  Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method , 2017, IEEE Transactions on Intelligent Transportation Systems.

[4]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[5]  Mihai Oltean,et al.  Multiobjective optimization using adaptive Pareto archived evolution strategy , 2005, 5th International Conference on Intelligent Systems Design and Applications (ISDA'05).

[6]  Chao Wang,et al.  River water level forecast based on spatio-temporal series model and RBF neural network , 2010, The 2nd International Conference on Information Science and Engineering.

[7]  Manfred F. Buchroithner,et al.  Combining Partial Least Squares and the Gradient-Boosting Method for Soil Property Retrieval Using Visible Near-Infrared Shortwave Infrared Spectra , 2017, Remote. Sens..

[8]  B Ming.  Cascade reservoir operation optimization based-on improved Cuckoo Search , 2015 .

[9]  Yufei Xia,et al.  A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring , 2017, Expert Syst. Appl..

[10]  Xin-She Yang,et al.  Cuckoo Search via Lévy flights , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[11]  L. L. Hamm,et al.  Data fusion modeling for groundwater systems , 2000 .