Advances in Sparrow Search Algorithm: A Comprehensive Survey

Archives of Computational Methods in Engineering, Год журнала: 2022, Номер 30(1), С. 427 - 455

Опубликована: Авг. 22, 2022

Язык: Английский

---

Predicting lake water quality index with sensitivity-uncertainty analysis using deep learning algorithms

Journal of Cleaner Production, Год журнала: 2023, Номер 406, С. 136885 - 136885

Опубликована: Апрель 3, 2023

Язык: Английский

---

An improved adaptive neuro fuzzy inference system model using conjoined metaheuristic algorithms for electrical conductivity prediction

Scientific Reports, Год журнала: 2022, Номер 12(1)

Опубликована: Март 23, 2022

Precise prediction of water quality parameters plays a significant role in making an early alert pollution and better decisions for the management resources. As one influential indicative parameters, electrical conductivity (EC) has crucial calculating proportion mineralization. In this study, integration adaptive hybrid differential evolution particle swarm optimization (A-DEPSO) with neuro fuzzy inference system (ANFIS) model is adopted EC prediction. The A-DEPSO method uses unique mutation crossover processes to correspondingly boost global local search mechanisms. It also refreshing operator prevent solution from being caught inside optimal solutions. This study optimizer ANFIS training phase eliminate defects predict accurately parameter every month at Maroon River southwest Iran. Accordingly, recorded dataset originated Tange-Takab station 1980 2016 was operated develop ANFIS-A-DEPSO model. Besides, wavelet analysis jointed proposed algorithm which original time series disintegrated into sub-time through two mother wavelets certainty. following, comparison between statistical metrics standalone ANFIS, least-square support vector machine (LSSVM), multivariate regression spline (MARS), generalized neural network (GRNN), wavelet-LSSVM (WLSSVM), wavelet-MARS (W-MARS), wavelet-ANFIS (W-ANFIS) wavelet-GRNN (W-GRNN) models implemented. result, it apparent that not only W-ANFIS-A-DEPSO able rise remarkably certainty, but (R = 0.988, RMSE 53.841, PI 0.485) had edge over other Dmey terms Moreover, can improve compared ANFIS-DEPSO model, accounting 80%. Hence, create closer approximation value likely act as promising procedure simulate data.

Язык: Английский

---

A hybrid decomposition and Machine learning model for forecasting Chlorophyll-a and total nitrogen concentration in coastal waters

Journal of Hydrology, Год журнала: 2023, Номер 619, С. 129207 - 129207

Опубликована: Фев. 4, 2023

Язык: Английский

---

A data-driven model for water quality prediction in Tai Lake, China, using secondary modal decomposition with multidimensional external features

Journal of Hydrology Regional Studies, Год журнала: 2023, Номер 47, С. 101435 - 101435

Опубликована: Май 30, 2023

Tai Lake, the third largest freshwater lake in China, with a history of serious ecological pollution incidents. Lake water quality prediction techniques are essential to ensure an early emergency response capability for sustainable management. Herein, effective data-driven ensemble model was developed predicting dissolved oxygen (DO) based on meteorological factors, indicators and spatial information. First, variation mode decomposition (VMD) used decompose data into multiple modal components classify them feature terms self terms. The were combined relevant external features multivariate by convolutional neural network (CNN) bi-directional long short-term memory (BiLSTM) attention mechanism (AT), as well using whale optimization algorithm (WOA) optimize hyperparameters. form secondary model. Finally, groupings linearly summed obtain outcome. proposed has highest accuracy best effect 0.5 days period. This research also establishes stepwise temperature regulation mechanism, where output target DO content value is achieved changing magnitude combining it this model, thereby strengthening protection resources management fishery production.

Язык: Английский

---

An ensemble model for accurate prediction of key water quality parameters in river based on deep learning methods

Journal of Environmental Management, Год журнала: 2024, Номер 366, С. 121932 - 121932

Опубликована: Июль 22, 2024

Язык: Английский

---

Water Quality Prediction in Urban Waterways Based on Wavelet Packet Denoising and LSTM

Water Resources Management, Год журнала: 2024, Номер 38(7), С. 2399 - 2420

Опубликована: Фев. 19, 2024

Язык: Английский

---

Monthly sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR

Expert Systems with Applications, Год журнала: 2023, Номер 237, С. 121512 - 121512

Опубликована: Сен. 13, 2023

Язык: Английский

---

Water Quality Assessment with Artificial Neural Network Models: Performance Comparison Between SMN, MLP and PS-ANN Methodologies

Arabian Journal for Science and Engineering, Год журнала: 2024, Номер unknown

Опубликована: Июнь 18, 2024

Abstract Identifying and measuring potential sources of pollution is essential for water management control. Using a range artificial intelligence models to analyze quality (WQ) one the most effective techniques estimating index (WQI). In this context, machine learning–based are introduced predict WQ factors Southeastern Black Sea Basin. The data comprising monthly samples different were collected 12 months at eight locations Türkiye region in Sea. traditional evaluation with WQI surface was calculated as average (i.e. good WQ). Single multiplicative neuron (SMN) model, multilayer perceptron (MLP) pi-sigma neural networks (PS-ANNs) used WQI, accuracy proposed algorithms compared. SMN model PS-ANNs prediction modeling first time literature. According results obtained from ANN models, it found provide highly reliable approach that allows capturing nonlinear structure complex series thus generate more accurate predictions. analyses demonstrate applicability instead using other computational methods both particular resources general.

Язык: Английский

---

Prediction of Total Nitrogen and Phosphorus in Surface Water by Deep Learning Methods Based on Multi-Scale Feature Extraction

Water, Год журнала: 2022, Номер 14(10), С. 1643 - 1643

Опубликована: Май 20, 2022

To improve the precision of water quality forecasting, variational mode decomposition (VMD) method was used to denoise total nitrogen (TN) and phosphorus (TP) time series obtained several high- low-frequency components at four online surface monitoring stations in Poyang Lake. For each aforementioned high-frequency components, a long short-term memory (LSTM) network introduced achieve excellent prediction results. Meanwhile, novel metaheuristic optimization algorithm, called chaos sparrow search algorithm (CSSA), implemented compute optimal hyperparameters for LSTM model. component with periodic changes, multiple linear regression model (MLR) adopted rapid effective prediction. Finally, combined based on VMD-CSSA-LSTM-MLR (VCLM) proposed compared nine models. Results indicated that (1), three standalone models, performed best terms mean absolute error (MAE), percentage (MAPE), root square (RMSE), as well Nash–Sutcliffe efficiency coefficient (NSE) Kling–Gupta (KGE). (2) Compared model, TN TP into relatively stable sub-sequences can evidently performance (3) CEEMDAN, VMD extract multiscale period nonlinear information better. The experimental results proved averages MAE, MAPE, RMSE, NSE, KGE predicted by VCLM are 0.1272, 8.09%, 0.1541, 0.9194, 0.8862, respectively; those 0.0048, 10.83%, 0.0062, 0.9238, 0.8914, respectively. comprehensive shows hybrid be recommended promising environment management lake systems.

Язык: Английский

---