Explore the vast range of titles available.

Fine particulate matter (PM 2.5 ) is a significant air pollutant that drives the most chronic health problems and premature mortality in big metropolitans such as Delhi. In such a context, accurate prediction of PM 2.5 concentration is critical for raising public awareness, allowing sensitive populations to plan ahead, and providing governments with information for public health alerts. This study applies a novel hybridization of extreme learning machine (ELM) with a snake optimization algorithm called the ELM-SO model to forecast PM 2.5 concentrations. The model has been developed on air quality inputs and meteorological parameters. Furthermore, the ELM-SO hybrid model is compared with individual machine learning models, such as Support Vector Regression (SVR), Random Forest (RF), Extreme Learning Machines (ELM), Gradient Boosting Regressor (GBR), XGBoost, and a deep learning model known as Long Short-Term Memory networks (LSTM), in forecasting PM 2.5 concentrations. The study results suggested that ELM-SO exhibited the highest level of predictive performance among the five models, with a testing value of squared correlation coefficient ( R 2 ) of 0.928, and root mean square error of 30.325 µg/m 3 . The study's findings suggest that the ELM-SO technique is a valuable tool for accurately forecasting PM 2.5 concentrations and could help advance the field of air quality forecasting. By developing state-of-the-art air pollution prediction models that incorporate ELM-SO, it may be possible to understand better and anticipate the effects of air pollution on human health and the environment.

Atmospheric air temperature is the most crucial metrological parameter. Despite its influence on multiple fields such as hydrology, the environment, irrigation, and agriculture, this parameter describes climate change and global warming quite well. Thus, accurate and timely air temperature forecasting is essential because it provides more important information that can be relied on for future planning. In this study, four Data-Driven Approaches, Support Vector Regression (SVR), Regression Tree (RT), Quantile Regression Tree (QRT), ARIMA, Random Forest (RF), and Gradient Boosting Regression (GBR), have been applied to forecast short-, and mid-term air temperature (daily, and weekly) over North America under continental climatic conditions. The time-series data is relatively long (2000 to 2021), 70% of the data are used for model calibration (2000 to 2015), and the rest are used for validation. The autocorrelation and partial autocorrelation functions have been used to select the best input combination for the forecasting models. The quality of predicting models is evaluated using several statistical measures and graphical comparisons. For daily scale, the SVR has generated more accurate estimates than other models, Root Mean Square Error (RMSE = 3.592°C), Correlation Coefficient (R = 0.964), Mean Absolute Error (MAE = 2.745°C), and Thiels’ U-statistics (U = 0.127). Besides, the study found that both RT and SVR performed very well in predicting weekly temperature. This study discovered that the duration of the employed data and its dispersion and volatility from month to month substantially influence the predictive models’ efficacy. Furthermore, the second scenario is conducted using the randomization method to divide the data into training and testing phases. The study found the performance of the models in the second scenario to be much better than the first one, indicating that climate change affects the temperature pattern of the studied station. The findings offered technical support for generating high-resolution daily and weekly temperature forecasts using Data-Driven Methodologies.

The design and sustainability of reinforced concrete deep beam are still the main issues in the sector of structural engineering despite the existence of modern advancements in this area. Proper understanding of shear stress characteristics can assist in providing safer design and prevent failure in deep beams which consequently lead to saving lives and properties. In this investigation, a new intelligent model depending on the hybridization of support vector regression with bio-inspired optimization approach called genetic algorithm (SVR-GA) is employed to predict the shear strength of reinforced concrete (RC) deep beams based on dimensional, mechanical and material parameters properties. The adopted SVR-GA modelling approach is validated against three different well established artificial intelligent (AI) models, including classical SVR, artificial neural network (ANN) and gradient boosted decision trees (GBDTs). The comparison assessments provide a clear impression of the superior capability of the proposed SVR-GA model in the prediction of shear strength capability of simply supported deep beams. The simulated results gained by SVR-GA model are very close to the experimental ones. In quantitative results, the coefficient of determination (R2) during the testing phase (R2 = 0.95), whereas the other comparable models generated relatively lower values of R2 ranging from 0.884 to 0.941. All in all, the proposed SVR-GA model showed an applicable and robust computer aid technology for modelling RC deep beam shear strength that contributes to the base knowledge of material and structural engineering perspective.

Accurate monthly runoff forecasting is vital for water management, flood control, hydropower, and irrigation. In glacierized catchments affected by climate change, runoff is influenced by complex hydrological processes, making precise forecasting even more challenging. To address this, the study focuses on the Lotschental catchment in Switzerland, conducting a comprehensive comparison between deep learning and ensemble-based models. Given the significant autocorrelation in runoff time series data, which may hinder the evaluation of prediction models, a novel statistical method is employed to assess the effectiveness of forecasting models in detecting turning points in the runoff data. The performance of Extreme Gradient Boosting (XGBoost) was compared with long short-term memory (LSTM) and random forest (RF) models for one-month-ahead runoff forecasting. The study used 20 years of runoff data (2002–2021), with 70% (2002–2015) dedicated for training and calibration, and the remaining data (2016–2021) for testing. The findings for the testing phase results show that the XGBoost model achieves the best accuracy, with R² of 0.904, RMSE of 1.554 m³/sec, an NSE of 0.797, and Willmott index ( d ) of 0.972, outperforming both the LSTM and RF models. The study also found that the XGBoost model estimated turning points more accurately, obtaining forecasting improvements of up to 22% to 34% compared to LSTM and RF models. Overall, the study’s findings are essential for global water resource management, providing insights that can inform sustainable practices to support societies impacted by climate change.

The Great Lakes are critical freshwater sources, supporting millions of people, agriculture, and ecosystems. However, climate change has worsened droughts, leading to significant economic and social consequences. Accurate multi-month drought forecasting is, therefore, essential for effective water management and mitigating these impacts. This study introduces the Multivariate Standardized Lake Water Level Index (MSWI), a modified drought index that utilizes water level data collected from 1920 to 2020. Four hybrid models are developed: Support Vector Regression with Beluga whale optimization (SVR-BWO), Random Forest with Beluga whale optimization (RF-BWO), Extreme Learning Machine with Beluga whale optimization (ELM-BWO), and Regularized ELM with Beluga whale optimization (RELM-BWO). The models forecast droughts up to six months ahead for Lake Superior and Lake Michigan-Huron. The best-performing model is then selected to forecast droughts for the remaining three lakes, which have not experienced severe droughts in the past 50 years. The results show that incorporating the BWO improves the accuracy of all classical models, particularly in forecasting drought turning and critical points. Among the hybrid models, the RELM-BWO model achieves the highest level of accuracy, surpassing both classical and hybrid models by a significant margin (7.21 to 76.74%). Furthermore, Monte-Carlo simulation is employed to analyze uncertainties and ensure the reliability of the forecasts. Accordingly, the RELM-BWO model reliably forecasts droughts for all lakes, with a lead time ranging from 2 to 6 months. The study’s findings offer valuable insights for policymakers, water managers, and other stakeholders to better prepare drought mitigation strategies.

Accurate determination of the discharge coefficient ( Cd ) is essential for calculating discharge over side weirs. The current study aims to enhance the prediction accuracy of Cd for rectangular sharp-crested side weirs by addressing the limitation of the output layer of the Extreme learning machine (ELM). The output layer of ELM depends mainly on the linear system which limits its generalization capabilities. Therefore, this study uses Locally Weighted Linear Regression (LWLR) with radial basis kernel function instead of the linear system to effectively capture nonlinear relationships and enhance local data pattern recognition. The proposed model (ELM-LWLR) has been validated against classic multiple linear regression (MLR), ELM, LWLR, and Extreme Gradient Boosting (XGBoost). The quantitative results showed that the ELM-LWLR model has a superior performance, achieving higher prediction accuracy with a correlation coefficient of 0.968, and percentage bias ( PBIAS ) of -0.130%. Moreover, the accuracy of Cd prediction using the ELM-LWLR model improved by 37.21% compared to LWLR, 28.95% compared to XGBoost, 48.08% compared to ELM, and 64.94% compared to MLR. Additionally, sensitivity analysis identified the ratio of weir height to length and dimensionless length as critical factors affecting Cd estimation. Overall, the findings demonstrate that the ELM-LWLR model is a practical and robust tool for Cd modeling, offering significant advantages in cost reduction and enhanced hydraulic modeling for complex engineering applications.

In the construction and cement manufacturing sectors, the development of artificial intelligence models has received remarkable progress and attention. This paper investigates the capacity of hybrid models conducted for predicting the compressive strength (CS) of concrete where the cement was partially replaced with ground granulated blast-furnace slag (FS) and fly ash (FA) materials. Accurate estimation of CS can reduce the cost and laboratory tests. Since the traditional method of calculation CS is complicated and requires lots of effort, this article presents new predictive models called SVR−PSO and SVR−GA, that are a hybridization of support vector regression (SVR) with improved particle swarm algorithm (PSO) and genetic algorithm (GA). Furthermore, the hybrid models (i.e., SVR−PSO and SVR−GA) were used for the first time to predict CS of concrete where the cement component is partially replaced. The improved PSO and GA are given essential roles in tuning the hyperparameters of the SVR model, which have a significant influence on model accuracy. The suggested models are evaluated against extreme learning machine (ELM) via quantitative and visual evaluations. The models are evaluated using eight statistical parameters, and then the SVR-PSO has provided the highest accuracy than comparative models. For instance, the SVR−PSO during the testing phase provided fewer root mean square error RMSE with 1.386 MPa, a higher Nash–Sutcliffe model efficiency coefficient (NE) of 0.972, and lower uncertainty at 95% (U95) with 28.776%. On the other hand, the SVR−GA and ELM models provide lower accuracy with RMSE of 2.826 MPa and 2.180, NE with 0.883 and 0.930, and U95 with 518.686 183.182, respectively. Sensitivity analysis is carried out to select the influential parameters that significantly affect CS. Overall, the proposed model showed a good prediction of CS of concrete where cement is partially replaced and outperformed 14 models developed in the previous studies.

Liquefaction is a devastating consequence of earthquakes that occurs in loose, saturated soil deposits, resulting in catastrophic ground failure. Accurate prediction of such geotechnical parameter is crucial for mitigating hazards, assessing risks, and advancing geotechnical engineering. This study introduces a novel predictive model that combines Extreme Learning Machine (ELM) with Dingo Optimization Algorithm (DOA) to estimate strain energy-based liquefaction resistance. The hybrid model (ELM-DOA) is compared with the classical ELM, Adaptive Neuro-Fuzzy Inference System with Fuzzy C-Means (ANFIS-FCM model), and Sub-clustering (ANFIS-Sub model). Also, two data pre-processing scenarios are employed, namely traditional linear and non-linear normalization. The results demonstrate that non-linear normalization significantly enhances the prediction performance of all models by approximately 25% compared to linear normalization. Furthermore, the ELM-DOA model achieves the most accurate predictions, exhibiting the lowest root mean square error (484.286 J/m 3 ), mean absolute percentage error (24.900%), mean absolute error (404.416 J/m 3 ), and the highest correlation of determination (0.935). Additionally, a Graphical User Interface (GUI) has been developed, specifically tailored for the ELM-DOA model, to assist engineers and researchers in maximizing the utilization of this predictive model. The GUI provides a user-friendly platform for easy input of data and accessing the model's predictions, enhancing its practical applicability. Overall, the results strongly support the proposed hybrid model with GUI serving as an effective tool for assessing soil liquefaction resistance in geotechnical engineering, aiding in predicting and mitigating liquefaction hazards.

Chemical pollutants, such as methyl orange (MO), constitute the main ingredients in the textile industry wastewater, and specifically, the dyeing process. The use of such chemicals leads to huge quantities of unfixed dyes to make their way to the water effluent and consequently escalates the water pollution problem. This work investigates the incorporation of hydrophobic carbon nanospheres (CNS) prepared from the pyrolysis of acetylene using the chemical vapor deposition technique with poly(vinylidene fluoride-co-hexafluoropropylene) (PVDF-HFP) in order to enhance its hydrophobicity. Moreover, a deep eutectic solvent (DES) was used to enhance the membrane’s porosity. The former was based on the quaternary ammonium salt (N,N-diethyl-ethanol-ammonium chloride) as a chemical addition throughout the membrane synthesis. Direct contact membrane distillation (DCMD) was employed to assess the performance of the modified membrane for treatment of MO contaminated water. The phase inversion method was used to embed various contents of CNS (i.e., 1.0, 3.0, and 5.0 wt.%) with 22:78 wt.% of PVDF-co-HFP/N-Methyl-2-pyrrolidone solution to prepare flat-sheet membranes. The membrane embedded with 5 wt.% CNS resulted in an increase in membrane hydrophobicity and presented considerable enhancement in DCMD permeation from 12 to 35 L/h.m2 with salt rejection >99.9%. Moreover, the composite membrane showed excellent anti-biofouling and mechanical characteristics as compared to the pristine counterpart. Using this membrane, a complete rejection of MO was achieved due to the synergistic contribution of the dye negative charge and the size exclusion effect.

Modeling sediment load is a significant factor in water resources engineering as it affects directly the design and management of water resources. In this study, artificial neural networks (ANNs) are employed to estimate the daily sediment load. Two different ANN algorithms, the feed forward neural network (FFNN) and radial basis function (RBF) have been used for this purpose. The neural networks are trained and tested using daily sediment and flow data from Rantau Panjang station on Johor River. The results show that combining flow data with sediment load data gives an accurate model to predict sediment load. The comparison of the results indicate that the FFNN model has superior performance than the RB model in estimating daily sediment load.