A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series

By Wenchao Wang, Kwok-Wing Chau, Chun-tian Cheng, Lin Qiu. 2009

811 citations recorded by the source corpus.

Summary Developing a hydrological forecasting model based on past records is crucial to effective hydropower reservoir management and scheduling. Traditionally, time series analysis and modeling is used for building mathematical models to generate hydrologic records in hydrology and water resources. Artificial intelligence (AI), as a branch of computer science, is capable of analyzing long-series and large-scale hydrological data. In recent years, it is one of front issues to apply AI technology to the hydrological forecasting modeling. In this paper, autoregressive moving-average (ARMA) models, artificial neural networks (ANNs) approaches, adaptive neural-based fuzzy inference system (ANFIS) techniques, genetic programming (GP) models and support vector machine (SVM) method are examined using the long-term observations of monthly river flow discharges. The four quantitative standard statistical performance evaluation measures, the coefficient of correlation ( R ), Nash–Sutcliffe efficiency coefficient ( E ), root mean squared error (RMSE), mean absolute percentage error (MAPE), are employed to evaluate the performances of various models developed. Two case study river sites are also provided to illustrate their respective performances. The results indicate that the best performance can be obtained by ANFIS, GP and SVM, in terms of different evaluation criteria during the training and validation phases.

Subfields: Environmental Engineering, Ocean Engineering, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/98f9db6743bc1f781b10bf2a8fa72fafdaa85067

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Environmental Engineering

In Ocean Engineering

In Water Science and Technology

Citations in the corpus

The Annual Maximum Flood Peak Discharge Forecasting Using Hermite Projection Pursuit Regression with SSO and LS Method (2016, methodology): “…nor do they require extensive data pre-processing (Dawson et al. 2002), have been increasingly used in hydrologic forecasting, such as rainfall-runoff modeling (Dawson and Wilby 1998), stream flow forecasting (Chen and Chau 2016; Wang et al. 2009, 2014, 2015), flood forecasting (Chau et al. 2005).”
Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada (2012, methodology): “SVMs have also been successfully used to forecast hourly streamﬂow by Asefa et al. [2006], and were shown to perform better than ANN [ Wang et al. , 2009] and ARIMA [ Maity et al. , 2010] models for monthly streamﬂow prediction.”
Tree‐based iterative input variable selection for hydrological modeling (2013, background): “…The second class of problems comprises a larger variety of application fields ranging from rainfall predictions [e.g., Sharma et al., 2000] to streamflow modeling [e.g., Wang et al., 2009], evaporation estimation [Moghaddamnia et al., 2009], and water quality modeling [e.g., Huang and Foo, 2002].”
Probabilistic Prediction for Monthly Streamflow through Coupling Stepwise Cluster Analysis and Quantile Regression Methods (2016, background): “2013), artificial intelligence (Cigizoglu 2005; Turan and Yurdusev 2009; Wang et al. 2009; Yang et al. 2015) and machine learning methods (Okkan and Serbes 2012; Sadri and Burn 2012; Sujay Raghavendra and Deka 2014).”
A stepwise-cluster forecasting approach for monthly streamflows based on climate teleconnections (2015, result): “Wang et al. (2009) compared the performance of several AI methods for forecasting monthly discharge time series.”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, background): “The concise outline here cannot possibly do justice, and readers are referred to multiple review papers for more details (e.g., Dawson & Wilby, 2001; Fallah-Mehdipour et al., 2013; Jha & Sahoo, 2015; Raghavendra & Deka, 2014; Tsai et al., 2017; W.-C. Wang et al., 2009; Yaseen et al., 2015).”
Combing Random Forest and Least Square Support Vector Regression for Improving Extreme Rainfall Downscaling (2019, methodology): “In addition, SVM performed better than NN and empirical models in modeling daily reference evapotranspiration [38], neuro fuzzy inference system (ANFIS) in river flow forecasting [29] and daily forecasting of dam water levels [39], and genetic programming (GP) in forecasting monthly discharge time s”
Wavelet Genetic Algorithm-Support Vector Regression (Wavelet GA-SVR) for Monthly Flow Forecasting (2015, methodology): “Wang et al. (2009) used the shuffled complex evolution algorithm to determine SVM model parameters in forecasting monthly discharge time series.”
Flood Prediction Using Machine Learning Models: Literature Review (2018, methodology): “This paper suggests that the drawbacks to major ML methods in terms of accuracy, uncertainty, performance, and robustness were improved through the hybridization of ML methods, as well as using an ensemble variation of the ML method.”
Comparative study of monthly inflow prediction methods for the Three Gorges Reservoir (2014, background): “3.1 Data normalization Data normalization is an essential step because it can not only avoid attributes in greater numeric ranges dominating those in smaller numeric ranges, but also avoid numerical difficulties during calculation (Wang et al. 2009a).”