“…It’s worth noting that the data analyzed in this study has been used in previous research conducted by the same authors 26 , 54 – 57 . Figure 1 Location of the study area.…”
Section: Methodsmentioning
confidence: 99%
“… Figure 1 Location of the study area. The EMAs points indicate the automatic monitoring stations where the data under analysis in this work are collected 54 . Figure 2 Daily data, total: 5844, between 2003 and 2018 (15 years).…”
Section: Methodsmentioning
confidence: 99%
“…The application of these hybrid approaches for predicting hydrological variables is a relatively new technique that has shown significant improvement in forecasting 16 – 24 . Recent studies along these lines have been conducted for predicting river flows 25 – 31 .…”
Accurate streamflow prediction is essential for efficient water resources management. Machine learning (ML) models are the tools to meet this need. This paper presents a comparative research study focusing on hybridizing ML models with bioinspired optimization algorithms (BOA) for short-term multistep streamflow forecasting. Specifically, we focus on applying XGB, MARS, ELM, EN, and SVR models and various BOA, including PSO, GA, and DE, for selecting model parameters. The performances of the resulting hybrid models are compared using performance statistics, graphical analysis, and hypothesis testing. The results show that the hybridization of BOA with ML models demonstrates significant potential as a data-driven approach for short-term multistep streamflow forecasting. The PSO algorithm proved superior to the DE and GA algorithms in determining the optimal hyperparameters of ML models for each step of the considered time horizon. When applied with all BOA, the XGB model outperformed the others (SVR, MARS, ELM, and EN), best predicting the different steps ahead. XGB integrated with PSO emerged as the superior model, according to the considered performance measures and the results of the statistical tests. The proposed XGB hybrid model is a superior alternative to the current daily flow forecast, crucial for water resources planning and management.
“…It’s worth noting that the data analyzed in this study has been used in previous research conducted by the same authors 26 , 54 – 57 . Figure 1 Location of the study area.…”
Section: Methodsmentioning
confidence: 99%
“… Figure 1 Location of the study area. The EMAs points indicate the automatic monitoring stations where the data under analysis in this work are collected 54 . Figure 2 Daily data, total: 5844, between 2003 and 2018 (15 years).…”
Section: Methodsmentioning
confidence: 99%
“…The application of these hybrid approaches for predicting hydrological variables is a relatively new technique that has shown significant improvement in forecasting 16 – 24 . Recent studies along these lines have been conducted for predicting river flows 25 – 31 .…”
Accurate streamflow prediction is essential for efficient water resources management. Machine learning (ML) models are the tools to meet this need. This paper presents a comparative research study focusing on hybridizing ML models with bioinspired optimization algorithms (BOA) for short-term multistep streamflow forecasting. Specifically, we focus on applying XGB, MARS, ELM, EN, and SVR models and various BOA, including PSO, GA, and DE, for selecting model parameters. The performances of the resulting hybrid models are compared using performance statistics, graphical analysis, and hypothesis testing. The results show that the hybridization of BOA with ML models demonstrates significant potential as a data-driven approach for short-term multistep streamflow forecasting. The PSO algorithm proved superior to the DE and GA algorithms in determining the optimal hyperparameters of ML models for each step of the considered time horizon. When applied with all BOA, the XGB model outperformed the others (SVR, MARS, ELM, and EN), best predicting the different steps ahead. XGB integrated with PSO emerged as the superior model, according to the considered performance measures and the results of the statistical tests. The proposed XGB hybrid model is a superior alternative to the current daily flow forecast, crucial for water resources planning and management.
“…Moreover, the arbitrary assignment of initial values to the input weights and bias of the hidden node parameters in the ELM lead to two notable problems 59 . The performance of EML slows down when an innovative trial sample is provided because: 1) ELM requires additional hidden neurons than conventional gradient-based algorithm; 2) ELM results in an output matrix for the hidden layer that is improperly conditioned and has poor generalization capabilities 57 . Several evolutionary and swarm intelligence-based systems have been investigated and implemented.…”
In software development and testing, detecting and mitigating faults are paramount to prevent potential issues from escalating
and disrupting the development and testing processes. The proposed method can also improve the prediction of various is
sues, such as increased model complexity, longer execution times, higher error rates, and enhanced fault detection capabilities.
Addressing this concern, the paper introduced a three-stage model encompassing data pre-processing, feature dimensionality
reduction, and fault prediction, which are essential steps in effective software testing. Our research leverages the publicly
available NASA dataset and employs Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) to re
duce feature vector dimensions, a common practice in software testing. We propose an improved version of the Grey Wolf
Optimization (IMGWO) algorithm, complemented by Extreme Learning Machines (ELM), to discern the presence of defects
within software modules. This approach is highly relevant in software testing, as it aids in identifying problematic areas early
in the development cycle. Utilizing the PCA-LDA+IMGWO-ELM approach, our model achieves an average accuracy rate of
0.9811 when applied to the KC2 dataset, a significant milestone in software testing. These results are substantiated through
experimental validation, reinforcing the credibility of our approach in predicting potential software defects during the software testing phase.
“…For instance, data assimilation methods may be applied to merge physically based models with ML methods to increase prediction accuracy or incorporate actual streamflow data into ML models. To enhance model performance, [59] created hybrid particle swarm optimization (PSO) and the group method of data handling for short-term prediction of daily streamflow, [60] developed ML-based grey wolf optimization for the short-term prediction of streamflows, [61] used hybrid LSTM-PSO for the streamflow forecast, [62] combined different ML methods for daily streamflow simulation, and [63] used an LSTM-based DL model for streamflow forecasting using Kalman filtering.…”
Section: Machine Learning Approaches For River Inflow Predictionmentioning
The management of water resources depends heavily on hydrological prediction, and advances in machine learning (ML) present prospects for improving predictive modelling capabilities. This study investigates the use of a variety of widely used machine learning algorithms, such as CatBoost, ElasticNet, k-Nearest Neighbors (KNN), Lasso, Light Gradient Boosting Machine Regressor (LGBM), Linear Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Ridge, Stochastic Gradient Descent (SGD), and the Extreme Gradient Boosting Regression Model (XGBoost), to predict the river inflow of the Garudeshwar watershed, a key element in planning for flood control and water supply. The substantial engineering feature used in the study, which incorporates temporal lag and contextual data based on Indian seasons, leads it distinctiveness. The study concludes that the CatBoost method demonstrated remarkable performance across various metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values, for both training and testing datasets. This was accomplished by an in-depth investigation and model comparison. In contrast to CatBoost, XGBoost and LGBM demonstrated a higher percentage of data points with prediction errors exceeding 35% for moderate inflow numbers above 10,000. CatBoost established itself as a reliable method for hydrological time-series modelling, easily managing both categorical and continuous variables, and thereby greatly enhancing prediction accuracy. The results of this study highlight the value and promise of widely used machine learning algorithms in hydrology and offer valuable insights for academics and industry professionals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
