Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation

Mohammadi, Babak; Guan, Yiqing; Moazenzadeh, Roozbeh; Safari, Mir Jafar Sadegh

doi:10.1016/j.catena.2020.105024

Cited by 96 publications

(28 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach allows the models reach to their maximum capabilities, and then the new hybrid model can have advantages of both the ANFIS and optimization algorithms for estimation [48]. Previous studies have proven that such coupled optimized techniques can provide better results in hydrological modeling [50][51][52]. Table 3 provides the optimal parameters related to the machine learning models used.…”

Section: Hybrid Models (Anfis-sfla and Anfis-iwo)mentioning

confidence: 99%

Development of Boosted Machine Learning Models for Estimating Daily Reference Evapotranspiration and Comparison with Empirical Approaches

Mehdizadeh

Mohammadi

Pham

et al. 2021

Water

Self Cite

View full text Add to dashboard Cite

Proper irrigation scheduling and agricultural water management require a precise estimation of crop water requirement. In practice, reference evapotranspiration (ETo) is firstly estimated, and used further to calculate the evapotranspiration of each crop. In this study, two new coupled models were developed for estimating daily ETo. Two optimization algorithms, the shuffled frog-leaping algorithm (SFLA) and invasive weed optimization (IWO), were coupled on an adaptive neuro-fuzzy inference system (ANFIS) to develop and implement the two novel hybrid models (ANFIS-SFLA and ANFIS-IWO). Additionally, four empirical models with varying complexities, including Hargreaves–Samani, Romanenko, Priestley–Taylor, and Valiantzas, were used and compared with the developed hybrid models. The performance of all investigated models was evaluated using the ETo estimates with the FAO-56 recommended method as a benchmark, as well as multiple statistical indicators including root-mean-square error (RMSE), relative RMSE (RRMSE), mean absolute error (MAE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). All models were tested in Tabriz and Shiraz, Iran as the two studied sites. Evaluation results showed that the developed coupled models yielded better results than the classic ANFIS, with the ANFIS-SFLA outperforming the ANFIS-IWO. Among empirical models, generally the Valiantzas model in its original and calibrated versions presented the best performance. In terms of model complexity (the number of predictors), the model performance was obviously enhanced by an increasing number of predictors. The most accurate estimates of the daily ETo for the study sites were achieved via the hybrid ANFIS-SFLA models using full predictors, with RMSE within 0.15 mm day−1, RRMSE within 4%, MAE within 0.11 mm day−1, and both a high R2 and NSE of 0.99 in the test phase at the two studied sites.

show abstract

Section: Hybrid Models (Anfis-sfla and Anfis-iwo)mentioning

confidence: 99%

Development of Boosted Machine Learning Models for Estimating Daily Reference Evapotranspiration and Comparison with Empirical Approaches

Mehdizadeh

Mohammadi

Pham

et al. 2021

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, some researchers suggested radial basic functions (RBF) as a powerful tool for considering as a kernel function in soil and water studies (Moazenzadeh et al 2018;Mohammadi et al 2021), and the RBF kernel function parameters were optimized through the trial and error method. Figure 3 shows a schematic structure of the SVM model.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

New hybrid nature-based algorithm to integration support vector machine for prediction of soil cation exchange capacity

Emamgholizadeh

Mohammadi

2021

Soft Comput

Self Cite

View full text Add to dashboard Cite

Soil cation exchange capacity (CEC) strongly influences the chemical, physical, and biological properties of soil. As the direct measurement of the CEC is difficult, costly, and time-consuming, the indirect estimation of CEC from chemical and physical parameters has been considered as an alternative method by researchers. Accordingly, in this study, a new hybrid model using a support vector machine (SVM), coupling with particle swarm optimization (PSO), and integrated invasive weed optimization (IWO) algorithm is developed for estimating the soil CEC. The physical and chemical data (i.e., clay, organic matter (OM), and pH) from two field sites of Taybad and Semnan in Iran were used for validating the new proposed approach. The ability of the proposed model (SVM-PSOIWO) was compared with the individual model (SVM) and the hybrid model (SVM-PSO). The results of the SVM-PSOIWO model were also compared with those of existing studies. Different performance evaluation criteria such as RMSE, R2, MAE, RRMSE, and MAPE, Box plots, and scatter diagrams were used to test the ability of the proposed models for estimation of the CEC values. The results showed that the SVM-PSOIWO model with the RMSE (R2) of 0.229 Cmol + kg−1 (0.924) was better than those of the SVM and SVM-PSO models with the RMSE (R2) of 0.335 Cmol + kg−1 (0.843) and 0.279 Cmol + kg−1 (0.888), respectively. Furthermore, the ability of the SVM-PSOIWO model compared with existing studies, which used the genetic expression programming, artificial neural network, and multivariate adaptive regression splines models. The results indicated that the SVM-PSOIWO model estimates the CEC more accurately than existing studies.

show abstract

“…Mohammadi et al [22] recommended a novel hybrid approach for SSL estimation in which multilayer perceptron (MLP) was hybridized with PSO and then integrated with a differential evolution algorithm (DE); the model was called MLP-PSODE. The developed MLP-PSODE model was found to be a parsimonious model that incorporates a lower number of input parameters in its structure for SSL estimation.…”

Section: Introductionmentioning

confidence: 99%

Daily Streamflow Forecasting Based on the Hybrid Particle Swarm Optimization and Long Short-Term Memory Model in the Orontes Basin

Kilinç¹

2022

Water

View full text Add to dashboard Cite

Water, a renewable but limited resource, is vital for all living creatures. Increasing demand makes the sustainability of water resources crucial. River flow management, one of the key drivers of sustainability, will be vital to protect communities from the worst impacts on the environment. Modelling and estimating river flow in the hydrological process is crucial in terms of effective planning, management, and sustainable use of water resources. Therefore, in this study, a hybrid approach integrating long short-term memory networks (LSTM) and particle swarm algorithm (PSO) was proposed. For this purpose, three hydrological stations were utilized in the study along the Orontes River basin, Karasu, Demirköprü, and Samandağ, respectively. The timespan of Demirköprü and Karasu stations in the study was between 2010 and 2019. Samandağ station data were from 2009–2018. The datasets consisted of daily flow values. In order to validate the performance of the model, the first 80% of the data were used for training, and the remaining 20% were used for the testing of the three FMSs. Statistical methods such as linear regression and the more classical model autoregressive integrated moving average (ARIMA) were used during the comparison process to assess the proposed method’s performance and demonstrate its superior predictive ability. The estimation results of the models were evaluated with RMSE, MAE, MAPE, SD, and R2 statistical metrics. The comparison of daily streamflow predictions results revealed that the PSO-LSTM model provided promising accuracy results and presented higher performance compared with the benchmark and linear regression models.

show abstract

Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation

Cited by 96 publications

References 63 publications

Development of Boosted Machine Learning Models for Estimating Daily Reference Evapotranspiration and Comparison with Empirical Approaches

Development of Boosted Machine Learning Models for Estimating Daily Reference Evapotranspiration and Comparison with Empirical Approaches

New hybrid nature-based algorithm to integration support vector machine for prediction of soil cation exchange capacity

Daily Streamflow Forecasting Based on the Hybrid Particle Swarm Optimization and Long Short-Term Memory Model in the Orontes Basin

Contact Info

Product

Resources

About