Suspended sediment load prediction using sparrow search algorithm-based support vector machine model

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 5, 2024

Abstract Prediction of suspended sediment load (SSL) in streams is significant hydrological modeling and water resources engineering. Development a consistent accurate prediction model highly necessary due to its difficulty complexity practice because transportation vastly non-linear governed by several variables like rainfall, strength flow, supply. Artificial intelligence (AI) approaches have become prevalent resource engineering solve multifaceted problems modelling. The present work proposes robust incorporating support vector machine with novel sparrow search algorithm (SVM-SSA) compute SSL Tilga, Jenapur, Jaraikela Gomlai stations Brahmani river basin, Odisha State, India. Five different scenarios are considered for development. Performance assessment developed analyzed on basis mean absolute error (MAE), root squared (RMSE), determination coefficient (R 2 ), Nash–Sutcliffe efficiency (E NS ). outcomes SVM-SSA compared three hybrid models, namely SVM-BOA (Butterfly optimization algorithm), SVM-GOA (Grasshopper SVM-BA (Bat benchmark SVM model. findings revealed that successfully estimates high accuracy scenario V (3-month lag) discharge (current time-step 3-month as input than other alternatives RMSE = 15.5287, MAE 15.3926, E 0.96481. conventional performed the worst prediction. Findings this investigation tend claim suitability employed approach rivers precisely reliably. guarantees precision forecasted while significantly decreasing computing time expenditure, satisfies demands realistic applications.

Language: Английский

---

Daily flow discharge prediction using integrated methodology based on LSTM models: Case study in Brahmani-Baitarani basin

HydroResearch, Journal Year: 2024, Volume and Issue: 7, P. 272 - 284

Published: Jan. 1, 2024

For flood control, hydropower operation, and agricultural planning, among other applications, flow discharge prediction is a critical first step toward the strong dependable planning management of water resources. Floods are destructive natural calamities that destroy human lives infrastructure across world. Development effective forecasting models for minimising deaths mitigating damages. This study employs hybrid deep learning Long Short Term Memory (LSTM) algorithms like LSTM, Convolution LSTM (Conv-LSTM) Convolutional Neural Network (CNN-LSTM) to predict likelihood events using daily precipitation, temperature relative humidity from two flood-forecasting stations i.e., Champua (Baitarani River, Odisha) Jarikela (Brahmani over 20-year period. The results show CNN-LSTM performed best followed by Conv-LSTM in terms R2 = 0.98055, 0.96564, 0.93244, RMSE 19.137, 35.635, 49.347, MAE 18.372, 33.766, 47.058, NSE 0.971, 0.9517 0.9257 respectively. findings support claim machine algorithms, particular model, can be applied with high accuracy, thereby enhancing hazard management.

Language: Английский

---

Evaluation of sustainable energy use in sugarcane production: A holistic model from planting to harvest and life cycle assessment

Environmental and Sustainability Indicators, Journal Year: 2025, Volume and Issue: unknown, P. 100617 - 100617

Published: Jan. 1, 2025

Language: Английский

---

Multi-Strategy Improved Particle Swarm Optimization Algorithm and Gazelle Optimization Algorithm and Application

Electronics, Journal Year: 2024, Volume and Issue: 13(8), P. 1580 - 1580

Published: April 20, 2024

In addressing the challenges associated with low convergence accuracy and unstable optimization results in original gazelle algorithm (GOA), this paper proposes a novel approach incorporating chaos mapping termed multi-strategy particle swarm (MPSOGOA). population initialization stage, segmented is integrated to generate uniformly distributed high-quality which enhances diversity, global perturbation of added improve speed early iteration late iteration. By combining (PSO) GOA, leverages individual experiences gazelles, improves stability. Tested on 35 benchmark functions, MPSOGOA demonstrates superior performance stability through Friedman tests Wilcoxon signed-rank tests, surpassing other metaheuristic algorithms. Applied engineering problems, including constrained implementations, exhibits excellent performance.

Language: Английский

---

IRIME: Mitigating exploitation-exploration imbalance in RIME optimization for feature selection

iScience, Journal Year: 2024, Volume and Issue: 27(8), P. 110561 - 110561

Published: July 22, 2024

Rime optimization algorithm (RIME) encounters issues such as an imbalance between exploitation and exploration, susceptibility to local optima, low convergence accuracy when handling problems. This paper introduces a variant of RIME called IRIME address these drawbacks. integrates the soft besiege (SB) composite mutation strategy (CMS) restart (RS). To comprehensively validate IRIME's performance, IEEE CEC 2017 benchmark tests were conducted, comparing it against many advanced algorithms. The results indicate that performance is best. In addition, applying in four engineering problems reflects solving practical Finally, proposes binary version, bIRIME, can be applied feature selection bIRIMR performs well on 12 low-dimensional datasets 24 high-dimensional datasets. It outperforms other algorithms terms number subsets classification accuracy. conclusion, bIRIME has great potential selection.

Language: Английский

---

Adaptive Neuro Fuzzy Inference System (ANFIS)-Based Control for Solving the Misalignment Problem inVehicle-to-Vehicle Dynamic Wireless Charging Systems

Electronics, Journal Year: 2025, Volume and Issue: 14(3), P. 507 - 507

Published: Jan. 26, 2025

Vehicle-to-vehicle dynamic wireless charging (V2V-DWC) represents a modern advancement in electrified transportation, where specialized vehicle delivers power to another on the move. The rising popularity of this technology can be attributed gradual advancements energy storage technologies and scarcity plug-in infrastructure. V2V transfer provides solution for electric vehicles (EVs) recharge their batteries while transit. existing literature confirms empirical validation concept through analytical experimental studies, yet challenge misalignment remains insufficiently explored. Achieving optimal systems necessitates precise alignment inductive coils. Lateral (LTM) occurs due deviation coils from proper alignment, leading significant losses. Additionally, development effective controllers address problem inadequate. This study proposes neural network-based adaptive fuzzy logic controller (ANFIS) alleviate issues V2V-DWC systems. A comparative analysis is conducted between proposed ANFIS conventional (FLC) evaluate performance across various degrees LTM. evaluated simulations MATLAB/Simulink, supplemented by testing. results indicate that surpasses FLC both simulation contexts addressing challenge.

Language: Английский

---

Joint identification of groundwater contaminant sources: an improved optimization algorithm

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(5)

Published: April 5, 2025

Language: Английский

---

Exploring ANFIS hybrid optimization for improved rainfall-runoff predictions: insights from Banjar River Catchment, India

Environment Development and Sustainability, Journal Year: 2025, Volume and Issue: unknown

Published: May 15, 2025

Language: Английский

---

Matrix scenario-based urban flooding damage prediction via convolutional neural network

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 349, P. 119470 - 119470

Published: Oct. 27, 2023

Language: Английский

---

Comparative study of rainfall prediction based on different decomposition methods of VMD

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Nov. 17, 2023

Rainfall forecasting is an important means for macro-control of water resources and prevention future disasters. In order to achieve a more accurate prediction effect, this paper analyzes the applicability "full decomposition" "stepwise VMD (Variational mode decomposition) algorithm actual service; The MAVOA (Modified African Vultures Optimization Algorithm) improved by Tent chaotic mapping selected; DNC (Differentiable Neural Computer), which combines advantages recurrent neural networks computational processing, applied forecasting. different decompositions MAVOA-DNC combination together with other comparative models are example predictions at four sites in Huaihe River Basin. results show that SMFSD (Single-model Fully stepwise most effective, average Root Mean Square Error (RMSE) forecasts SMFSD-MAVOA-DNC 9.02, Absolute (MAE) 7.13, Nash-Sutcliffe Efficiency (NSE) 0.94. Compared traditional full decomposition, RMSE reduced 7.42, MAE 4.83, NSE increased 0.05; best obtained compared coupled models.

Language: Английский

---