MSGP-LASSO: An improved multi-stage genetic programming model for streamflow prediction

Mehr, Ali Danandeh; Gandomi, Amir H.

doi:10.1016/j.ins.2021.02.011

Cited by 37 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is seen that the SARIMA suffers from low-variance forecasts unable to capture peak flows. This result agrees with that of Danandeh Mehr and Gandomi (2021) in which SARIMA was applied to model the Sedre River flow in Turkey. Such drawback at the estimation of high discharge values might be due to the existence of strong deviation during the snow melting months so that the linear SARIMA cannot capture it.…”

Section: Results Of the Proposed Gp-sarima Model For Long-term Streamflow Forecastingsupporting

confidence: 91%

“…Figure 5c exhibits the highest strength of the serial correlations at lag 12. Following Danandeh Mehr and Gandomi (2021), multiple combinations of seasonal (p, d, q) and non-seasonal parameters (P, D, Q) were tested in this study to select the best SARIMA model. The model which shows the smallest corrected Akaike information criterion (AIC c ) in the training period and RMSE in the testing period was selected as the best solution.…”

Section: Results Of Standalone Gp and Sarima Modelsmentioning

confidence: 99%

See 1 more Smart Citation

A new evolutionary time series model for streamflow forecasting in boreal lake-river systems

Mehr

Ghadimi

Marttila

et al. 2022

Theor Appl Climatol

View full text Add to dashboard Cite

Genetic programming (GP) is an evolutionary regression method that has received considerable interest to model hydro-environmental phenomena recently. Considering the sparseness of hydro-meteorological stations on northern areas, this study investigates the benefits and downfalls of univariate streamflow modeling at high latitudes using GP and seasonal autoregressive integrated moving average (SARIMA). Furthermore, a new evolutionary time series model, called GP-SARIMA, is introduced to enhance streamflow forecasting accuracy at long-term horizons in a lake-river system. The paper includes testing the new model for one-step-ahead forecasts of daily mean, weekly mean, and monthly mean streamflow in the headwaters of the Oulujoki River, Finland. The results showed that a combination of correlogram and average mutual information (AMI) analysis might yield in the selection of the optimum lags that are needed to be used as the predictors of streamflow models. With Nash-Sutcliffe efficiency values of more than 99%, both GP and SARIMA models exhibited good performance for daily streamflow prediction. However, they were not able to precisely model the intramonthly snow water equivalent in the long-term forecast. The proposed ensemble model, which integrates the best GP and SARIMA models with the most efficient predictor, may eliminate one-fourth of root mean squared errors of standalone models. The GP-SARIMA also showed up to three times improvement in the accuracy of the standalone models based on the Nash-Sutcliff efficiency measure.

show abstract

Section: Results Of the Proposed Gp-sarima Model For Long-term Streamflow Forecastingsupporting

confidence: 91%

Section: Results Of Standalone Gp and Sarima Modelsmentioning

confidence: 99%

A new evolutionary time series model for streamflow forecasting in boreal lake-river systems

Mehr

Ghadimi

Marttila

et al. 2022

Theor Appl Climatol

View full text Add to dashboard Cite

show abstract

“…e study applied linear correlation statistics to measure the strength of dependency between different input variables [25]. Even though Mehr and Gandomi [26] stated that linear correlation might mislead or provide abundant inputs, our study does no't have a huge feature size that requires intensive feature selection criteria. Hence, we adopted a linear correlation coefficient.…”

Section: Data Source and Preprocessingmentioning

confidence: 99%

Multivariate Streamflow Simulation Using Hybrid Deep Learning Models

Wegayehu

Muluneh

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Reliable and accurate streamflow simulation has a vital role in water resource development, mainly in agriculture, environment, domestic water supply, hydropower generation, flood control, and early warning systems. In this context, these days, deep learning algorithms have got enormous attention due to their high-performance simulation capacity. In this study, we compared multilayer perceptron (MLP), long short-term memory (LSTM), and gated recurrent unit (GRU) with the proposed new hybrid models, including CNN-LSTM and CNN-GRU. Hence, we can simulate one-step daily streamflow in different agroclimatic conditions, rolling time windows, and a range of variable input combinations. The analysis used daily multivariate and multisite time series data collected from Awash River Basin (Borkena watershed: Ethiopia) and Tiber River Basin (Upper Tiber River Basin: Italy) stations. The datasets were subjected to rigorous quality control processes. Consequently, it rolled to a different time lag to remove noise in the time series and further split into training and testing datasets using a ratio of 80 : 20, respectively. Finally, the results showed that integrating the GRU layer with the convolutional layer and using monthly rolled average daily input time series could substantially improve the simulation of streamflow time series.

show abstract

“…However, there is no agreement on which of them are more reliable for model assessment. Therefore, some researchers [33][34][35][36] indicated that model performance indicators should be selected in a multi-objective sense. According to Ritter and Munoz-Carpena [36], the performance assessment of a model should include at least one absolute value error indicator, one dimensionless indicator for quantifying the goodness of fit, and a graphical representation of the relationship between the model predictions and measurements.…”

Section: Performance Evaluationmentioning

confidence: 99%

Sea Level Prediction Using Machine Learning

Tür

Tas

Haghighi

et al. 2021

Water

Self Cite

View full text Add to dashboard Cite

Sea level prediction is essential for the design of coastal structures and harbor operations. This study presents a methodology to predict sea level changes using sea level height and meteorological factor observations at a tide gauge in Antalya Harbor, Turkey. To this end, two different scenarios were established to explore the most feasible input combinations for sea level prediction. These scenarios use lagged sea level observations (SC1), and both lagged sea level and meteorological factor observations (SC2) as the input for predictive modeling. Cross-correlation analysis was conducted to determine the optimum input combination for each scenario. Then, several predictive models were developed using linear regressions (MLR) and adaptive neuro-fuzzy inference system (ANFIS) techniques. The performance of the developed models was evaluated in terms of root mean squared error (RMSE), mean absolute error (MAE), scatter index (SI), and Nash Sutcliffe Efficiency (NSE) indices. The results showed that adding meteorological factors as input parameters increases the performance accuracy of the MLR models up to 33% for short-term sea level predictions. Moreover, the results contributed a more precise understanding that ANFIS is superior to MLR for sea level prediction using SC1- and SC2-based input combinations.

show abstract

MSGP-LASSO: An improved multi-stage genetic programming model for streamflow prediction

Cited by 37 publications

References 31 publications

A new evolutionary time series model for streamflow forecasting in boreal lake-river systems

A new evolutionary time series model for streamflow forecasting in boreal lake-river systems

Multivariate Streamflow Simulation Using Hybrid Deep Learning Models

Sea Level Prediction Using Machine Learning

Contact Info

Product

Resources

About