Flood discharge prediction using improved ANFIS model combined with hybrid particle swarm optimisation and slime mould algorithm

Samantaray, Sandeep; Sahoo, Prasana; Sahoo, Abinash; Satapathy, Deba Prakash

doi:10.1007/s11356-023-27844-y

Cited by 23 publications

(5 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4.2.9. Others Moreover, researchers have hybridized an SMA with a sine cosine algorithm [83], marine predators algorithm [85], particle swarm optimization [97], evolutionary algorithm [98], firefly algorithm [99], gray wolf optimization algorithm [100], gradient-based optimizer [101], quadratic approximation [102], tournament selection [103], artificial neural network [104], moth-flame optimization algorithm [105], pattern search algorithm [106], and support vector regression [107]. These hybrid SMA variants indicated their benefits, such as the good balance between exploration and exploitation capabilities, good convergence speed, ability to avoid premature convergence, and reduced computation time.…”

Section: Hybridization With the Artificial Bee Colony (Abc)mentioning

confidence: 99%

“…The experimental results indicated that the proposed JASMA-SVM was a promising tool when used for RSA predictions. Samantaray S et al [97] proposed an ANFIS-PSOSMA model to predict river flood discharge (QFD) results considering the data obtained from four gauging stations in the River Brahmani, Odisha India. From the evaluation, it was observed that the proposed model had the highest accuracy.…”

Section: Prediction Modelmentioning

confidence: 99%

See 1 more Smart Citation

Advances in Slime Mould Algorithm: A Comprehensive Survey

Wei,

Othman,

Daud

et al. 2024

Biomimetics

View full text Add to dashboard Cite

The slime mould algorithm (SMA) is a new swarm intelligence algorithm inspired by the oscillatory behavior of slime moulds during foraging. Numerous researchers have widely applied the SMA and its variants in various domains in the field and proved its value by conducting various literatures. In this paper, a comprehensive review of the SMA is introduced, which is based on 130 articles obtained from Google Scholar between 2022 and 2023. In this study, firstly, the SMA theory is described. Secondly, the improved SMA variants are provided and categorized according to the approach used to apply them. Finally, we also discuss the main applications domains of the SMA, such as engineering optimization, energy optimization, machine learning, network, scheduling optimization, and image segmentation. This review presents some research suggestions for researchers interested in this algorithm, such as conducting additional research on multi-objective and discrete SMAs and extending this to neural networks and extreme learning machining.

show abstract

Section: Hybridization With the Artificial Bee Colony (Abc)mentioning

confidence: 99%

Section: Prediction Modelmentioning

confidence: 99%

Advances in Slime Mould Algorithm: A Comprehensive Survey

Wei,

Othman,

Daud

et al. 2024

Biomimetics

View full text Add to dashboard Cite

show abstract

“…The four metrics used in this study to evaluate the performance of deep learning networks are relative mean absolute percentage error (RMSE), Nash-Sutcliffe efficiency coefficient (NSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). This research chose these metrics because they are widely used in previous literatures [36][37][38][39]. Smaller values of MAE, RMSE, and MAPE indicate better performance of the network in terms of the difference between measured and estimated data.…”

Section: Evaluation Metricsmentioning

confidence: 99%

Computing River Discharge Using Water Surface Elevation Based on Deep Learning Networks

Liu,

Zou,

Jiang

et al. 2023

Water

View full text Add to dashboard Cite

Accurately computing river discharge is crucial, but traditional computing methods are complex and need the assistance of many other hydraulic parameters. Therefore, it is of practical value to develop a convenient and effective auto-computation technique for river discharge. Water surface elevation is relatively easy to obtain and there is a strong relationship between river discharge and water surface elevation, which can be used to compute river discharge. Unlike previous usage of deep learning to predict short-term river discharge that need multiple parameters besides water level, this paper proved that deep learning has the potential to accurately compute long-term river discharge purely based on water level. It showed that the majority of relative errors on the test dataset were within ±5%, particularly it could operate continuously for almost one year with high precision without retraining. Then, we used BiGRU to compute river flow with different hyperparameters, and its best RMSE, NSE, MAE, and MAPE values were 256 m3/s, 0.9973, 207 m3/s, and 0.0336, respectively. With this data-driven based technology, it will be more convenient to obtain river discharge time series directly from local water surface elevation time series accurately in natural rivers, which is of practical value to water resources management and flood protection.

show abstract

“…Deng et al [40] divided the SMA into two populations dynamically, adjusting population sizes to balance the algorithm's exploitation and exploration capabilities, and successfully applying it to real-world engineering problems. Samantaray et al [41] amalgamated SMA with particle swarm optimization (PSO), successfully applying this hybrid approach to predict flood flow rates. Tan et al [42] combined the whale optimization algorithm (WOA) with the equilibrium optimizer, validating its performance on benchmark test sets.…”

Section: Introductionmentioning

confidence: 99%

IRIME: A Novel Approach to Mitigating Exploitation-Exploration Imbalance in Rime Optimization Algorithm for Feature Selection

Huang,

Chen,

Heidari

et al. 2024

Preprint

View full text Add to dashboard Cite

Rime optimization algorithm (RIME) is an emerging metaheuristic algorithm. However, RIME encounters issues such as an imbalance between exploitation and exploration, susceptibility to local optima, and low convergence accuracy when handling problems. To address these drawbacks, this paper introduces a variant of RIME called IRIME. IRIME integrates the soft besiege (SB) and composite mutation strategy and restart strategy (CMS-RS), aiming to balance exploitation and exploration in RIME, enhance population diversity, improve convergence accuracy, and endow RIME with the capability to escape local optima. To comprehensively validate IRIME's performance, IEEE CEC 2017 benchmark tests were conducted, comparing it against 13 conventional algorithms and 11 advanced algorithms, including excellent algorithms in the CEC competition such as JADE. The results indicate that the performance of IRIME is the best. To validate IRIME's practical applicability, the paper proposes a binary version, bIRIME, applied to feature selection problems. bIRIMR performs well on 12 low-dimensional datasets and 24 high-dimensional datasets. It outperforms other advanced algorithms in terms of the number of feature subsets and classification accuracy. In conclusion, bIRIME performs notably well in feature selection, particularly in high-dimensional datasets.

show abstract

Flood discharge prediction using improved ANFIS model combined with hybrid particle swarm optimisation and slime mould algorithm

Cited by 23 publications

References 78 publications

Advances in Slime Mould Algorithm: A Comprehensive Survey

Advances in Slime Mould Algorithm: A Comprehensive Survey

Computing River Discharge Using Water Surface Elevation Based on Deep Learning Networks

IRIME: A Novel Approach to Mitigating Exploitation-Exploration Imbalance in Rime Optimization Algorithm for Feature Selection

Contact Info

Product

Resources

About