The significant rise in the air pollution index due to black carbon (BC) can be ascribed to heavy energy dependency of developing nations on coal as their primary energy resource. For countries like India, Coal is the principal contributor to energy demand required for electricity generation and expansion of industry. Bokaro, Jharia and Raniganj are the three important coal fields located in India. The BC concentration data from these coal fields is analysed and forecasted with a suitable developed conjunction mathematical model to look for solutions to the alarming pollution levels both nationally and globally. The model so developed helps to lower the error metrices significantly while forecasting the pollution data as compared to individual soft computing model.

Particle Swarm Optimization (PSO) is widely recognized in the literature as a leading swarm-based algorithm. Since its inception in the mid-1990s, PSO has undergone significant advancements, including various enhancements, extensions, and modifications, particularly in the years following the turn of the century. As a result, research in this area has reached a remarkable level of sophistication. This paper presents a comprehensive and systematic review that organizes and synthesizes current knowledge on PSO. It offers an in-depth examination of the core concepts of the algorithm, neighborhood topologies, and historical and recent variants of the PSO. In addition, it highlights the significant engineering applications of PSO and discusses ongoing challenges in the field. By systematically arranging and summarizing the latest research, this review serves as a valuable resource for both researchers and practitioners interested in the development and application of PSO.

The incessant degradation of the environment is a major global challenge in today’s world, which is posing huge threat to the human health and environmental equilibrium. The escalating accumulation of hazardous pollutants in the air and water, and the subsequent threats to human health, are driven by complex interconnected mechanisms involving climate variability, geographical characteristics, and anthropogenic activities. Since these processes exhibit strong non-linear and dynamic behavior, it becomes very arduous to depict accurate forecasts using conventional statistical methods. Artificial Neural Networks (ANNs) have captured notable attention to overcome these challenges because of their ability to model intricate non-linear relationships in diverse environmental systems. This study demonstrates an extensive review of ANN applications across environmental and non-environmental domains. It looks forward to primarily focusing on the environmental systems, which would comprise of air quality modeling, management of water resources and predictions related to health. A critical analysis of more than 135 peer-reviewed articles from high-impact journals has been conducted to bring out the efficaciousness, shortcomings, and advancements of ANN-based modeling frameworks. The findings indicate that while individual ANN models are competent to represent the non-linear relationships, their performance is often constrained by issues such as local minima convergence, overfitting, and reduced generalizations under noisy and non-stationary conditions. The review further illustrates that when ANN models are seamlessly connected with methods such as wavelet decomposition, ARIMA, and evolutionary optimization techniques, the hybrid frameworks steadily reflect the immense strength, stability, and precision of forecasting compared to the standalone ANN models. The comparative evidence emphatically suggest that hybrid models provide a stronger benchmark for complex real world datasets, especially in the highly variable environmental systems. The study draws the conclusion that focuses on the escalating significance of hybrid intelligent systems and highlights the areas of subsequent research on model interpretability, uncertainty handling, and adaptive learning. This paper is organized into five main sections: an introduction to ANNs, their historical development, applications of ANN models in environmental studies, a detailed review of these practical implementations, and a discussion of results. By consolidating this knowledge, we can foster collaborative efforts towards developing more effective strategies for mitigating environmental pollution and safeguarding the planet for future generations.

Environmental pollution is a critical challenge that requires our attention due to its potential for irreversible damage to our planet. As urbanization and technological advancements continue, addressing the degradation of vital environmental components, including air, water, and soil, caused by hazardous waste released from industrial activities is essential. Pollutants disrupt the ecological balance and pose serious health risks to humans, animals, and birds. To combat this issue, effective tools and methodologies are necessary. For example, wavelet hybrid modelling significantly enhances our ability to predict concentrations of air and water pollutants, which can lead to informed decision-making and future improvements. Accurate predictions can be achieved effectively with wavelet hybrid models. A review of approximately 150 research papers highlights the advancements in forecasting environmental pollutants, climate variations, and groundwater levels using various wavelet hybrid models. These studies demonstrate the versatility of different wavelet hybrid models compared to traditional single models in forecasting time series data. Researchers use a range of statistical indices, including Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Nash-Sutcliffe Efficiency (NSE), and R-squared (R²), to evaluate their effectiveness. The findings indicate that wavelet hybrid models offer a promising approach, showing greater accuracy in forecasting time series data than single models. This paper is structured into five comprehensive sections: an introduction to wavelets, their historical context, the applications of wavelet-coupled models in environmental studies, a review of these practical applications and discussions of results. By sharing this knowledge, we can collaborate on more effective strategies for mitigating environmental pollution and protecting our planet for future generations.

The presence of aerosol concentrations in mining regions substantially affects air quality and human health. Aerosol Optical Depth (AOD) is directly related to the amount and type of aerosols present in the atmosphere. Higher aerosol concentrations generally lead to higher AOD values. The main aim of this study is to utilize the Support Vector Machine (SVM) algorithm to forecast AOD near coal mines located in Assam. The SVM was developed for application on specific datasets between 2003 and 2019. The AOD data is acquired from Moderate Resolution Imaging Spectroradiometer (MODIS-Terra) in the proximity of coal mines over four distinct coalfields at Assam. Using a comprehensive dataset, the SVM model is trained and validated with great attention to detail. The hyperparameters are optimized, and measures are taken to mitigate overfitting. The optimized model is developed to predict monthly AOD550 values based on historical AOD550 observations. The analysis of seasonal patterns reveals that Dilli-Jeypore, Mikir, and Sheelveta exhibit the most elevated values of AOD during the Winter season, with respective values of 0.58 ± 0.16, 0.63 ± 0.14, and 0.49 ± 0.13. The Singrimari sample site reaches its maximum AOD during the Pre-Monsoon season. In contrast, the Dilli-Jeypore, Mikir, and Sheelveta regions show the lowest values during the Post-Monsoon season respectively. However, Singrimari is an exception, with higher AOD during the Monsoon season (0.50 ± 0.20). It is observed that the Sheelveta coalmine fields exhibit the lowest Root Mean Square Error (RMSE) values in both the training and testing phases, with values of 0.0469 and 0.0744, respectively. The results show that this method establishes better ecosystems and sustainable mining methods.

Accurate streamflow prediction remains challenging due to the nonlinear and dynamic nature of rainfall-runoff processes. Conceptual hydrological models provide physically interpretable representations, yet their predictive performance is often limited, while data-driven models may suffer from overfitting and a lack of interpretability. To address these limitations, this study proposes a physics-informed hybrid modeling framework that integrates the GR4J conceptual model with the XGBoost machine learning algorithm. Unlike conventional hybrid approaches, the proposed method incorporates GR4J-derived state and flux variables (including simulated discharge, storage state, effective rainfall, evapotranspiration, percolation, and exchange fluxes) as input features, enabling a process-based representation of catchment dynamics within the machine learning framework. The proposed framework was evaluated using a catchment selected from the CAMELS-DE (Catchment Attributes and Meteorology for Large-sample Studies-Germany) dataset. Model performance was assessed using multiple lag configurations (7, 14, and 30 days) across training, validation, and independent test datasets. The results demonstrate that the hybrid GR4J-XGBoost model generally outperforms the standalone GR4J and XGBoost models, particularly in terms of generalization capability and predictive stability. While the standalone XGBoost model benefits from longer lag structures, the hybrid model achieves comparable or superior predictive performance with shorter lag inputs, indicating reduced dependence on extended temporal memory while providing physically meaningful conceptual information for model interpretation. SHAP analysis reveals that physically meaningful variables, especially GR4J-derived state and flux components, play a dominant role in governing model predictions. Furthermore, residual-based uncertainty assessment shows that the hybrid model produces lower prediction bias, reduced residual dispersion, and narrower residual uncertainty bounds than the standalone approaches, indicating improved prediction reliability. Overall, the proposed framework provides a physics-informed, process-based, and interpretable approach for rainfall-runoff modeling while offering an additional assessment of prediction reliability through residual-based uncertainty evaluation.

Accurate rainfall-runoff modeling is crucial for effective watershed management, hydraulic infrastructure safety, and flood mitigation. However, predicting rainfall-runoff remains challenging due to the nonlinear interplay between hydro-meteorological and topographical variables. This study introduces a hybrid Gaussian process regression (GPR) model integrated with K-means clustering (GPR-K-means) for short-term rainfall-runoff forecasting. The Orgeval watershed in France serves as the study area, providing hourly precipitation and streamflow data spanning 1970–2012. The performance of the GPR-K-means model is compared with standalone GPR and principal component regression (PCR) models across four forecasting horizons: 1-hour, 6-hour, 12-hour, and 24-hour ahead. The results reveal that the GPR-K-means model significantly improves forecasting accuracy across all lead times, with a Nash-Sutcliffe Efficiency (NSE) of approximately 0.999, 0.942, 0.891, and 0.859 for 1-hour, 6-hour, 12-hour, and 24-hour forecasts, respectively. These results outperform other ML models, such as Long Short-Term Memory, Support Vector Machines, and Random Forest, reported in the literature. The GPR-K-means model demonstrates enhanced reliability and robustness in hourly streamflow forecasting, emphasizing its potential for broader application in hydrological modeling. Furthermore, this study provides a novel methodology for combining clustering and Bayesian regression techniques in surface hydrology, contributing to more accurate and timely flood prediction.

The analysis and prediction of stock market prices are crucial areas of research due to their complex, chaotic, and nonlinear features. As a result, making significant gains in stock market investments is a crucial task. However, expert and intelligent modeling techniques can help in achieving positive stock market returns. In this study, we use the Monte Carlo (MC) simulation method to generate multiple future values of the time series of closing prices of a particular stock of BSE using a combination of wavelet denoising and the autoregressive integrated moving average (ARIMA) model. The multiple future realizations of stock prices produced by the Monte Carlo (MC) simulation can help minimize risk and uncertainty in stock market investments. Firstly, we use wavelet analysis to detect significant noise levels in the time series at each scale in discrete wavelet decomposition, which is then eliminated by an appropriate wavelet denoising method. Next, the time series of denoised stock prices is fitted with a suitable ARIMA model, and the future values are obtained using this model. The future values of the denoised time series are simulated using MC simulation. The results of the study show that simulated forecasts obtained by MC simulation using the integrated wavelet-denoising-ARIMA model become more accurate with increasing simulation count than by applying a single ARIMA model to noisy stock price series. It has also been observed that MC simulation reduces the standard error of estimates to one half when the number of simulations is quadrupled.

This study enhances the prediction of biochemical oxygen demand (BOD5), a vital water quality parameter, by developing hybrid artificial neural network models integrated with advanced optimization algorithms. Data from two monitoring stations in South Korea were used to create five models, including the innovative ANN-Enhanced Runge Kutta (ANN-ERUN) model. ANN-ERUN achieved the highest accuracy, significantly outperforming other models. At Gong station, it reduced prediction error (root mean square error: 1.24mg/L; mean absolute error: 0.83mg/L) and achieved a determination coefficient of 0.857. Models using eight water quality parameters, including dissolved oxygen and chemical oxygen demand, exhibited superior performance. These findings confirm the effectiveness of ANN-ERUN in precise BOD5 prediction, offering a robust tool for environmental monitoring and sustainable water quality management.

Precise and robust streamflow estimation is crucial for effective water resource management, particularly in mitigating extreme climatic events such as droughts and floods. This study introduces an innovative integration of the Random Vector Functional Link (RVFL) network with an Enhanced Remora Optimization Algorithm (EROA), specifically designed for monthly streamflow prediction. The RVFL-EROA is compared against standalone RVFL and RVFL models optimized using the Gorilla Troops Optimizer (GTO), Whale Optimization Algorithm (WOA), and the original Remora Optimization Algorithm (ROA). Performance is evaluated using statistical indices, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2), and Nash-Sutcliffe Efficiency (NSE). The methodology is tested on streamflow time series data from the Kunhar River Basin in Pakistan, with input variables derived from antecedent streamflow, air temperature, and rainfall. Results indicate that temperature and streamflow-based inputs yielded higher accuracy compared to rainfall inputs. The RVFL-EROA outperformed other models, achieving improvements in mean RMSE, MAE, R2, and NSE by 8.63-1.77%, 12.08-1.58%, 16.88-3.33%, and 19.03-3.05%, respectively. Moreover, the RVFLEROA demonstrated superior performance in estimating peak streamflow values, which is critical for flood management. These findings highlight the potential of temperature-based inputs and RVFL-EROA models for streamflow prediction in data-scarce regions, particularly in developing countries. The proposed approach offers a reliable solution for enhancing hydrological forecasting and supports efficient water resource planning.

The preset paper discusses the COVID-19 pandemic in India and the development of a data-driven model to predict COVID-19 confirmed cases, casualties, and recoveries in the country. The Coronavirus Disease 2019 (COVID-19) was first identified in December 2019 in the Hubei Province of the People's Republic of China. It quickly spread to 220 countries worldwide and had a significant impact. In India, the second wave of COVID-19 hit in April 2021, resulting in over 40 million reported cases and three lakh casualties. India ranked second in COVID-19 infections globally, after the United States of America. To better understand the dynamics of the COVID-19 pandemic in India, a data-driven WANFIS (Wavelet Adaptive Neuro-Fuzzy Inference System) model was developed. This model uses discrete wavelet decomposition to extract information from input data and predict the escalation of confirmed cases, casualties, and recoveries in India. The WANFIS model's effectiveness was compared to other models like the artificial neural network (ANN) model and individual ANFIS model, and it proved to be more robust in predicting COVID-19 transmission. The proposed WANFIS model has the potential to effectively forecast the transmission of infectious diseases, enabling government and health officials to anticipate and prepare for emergencies more effectively.

This study investigates monthly streamflow modeling at Kale and Durucasu stations in the Black Sea Region of Turkey using remote sensing data. The analysis incorporates key meteorological variables, including air temperature, relative humidity, soil wetness, wind speed, and precipitation. The study also investigates the accuracy of multivariate adaptive regression (MARS) with Kmeans clustering (MARS-Kmeans) by comparing it with single MARS, M5 model tree (M5Tree), random forest regression (RF), multilayer perceptron neural network (MLP). In the first modeling stage, principal component regression is applied to diverse input combinations, both with and without lagged streamflow (Q), resulting in twenty-three and twenty input combinations, respectively. Results demonstrate the critical role of including lagged Q for improved model accuracy, as models without lagged Q exhibit significant performance degradation. The second stage involves a comparative analysis of the MARS-Kmeans model with other machine-learning models, utilizing the best-input combination. MARS-Kmeans, incorporating three clusters, consistently outperforms other models, showcasing superior accuracy in predicting monthly streamflow.

Air pollution has emerged as a significant environmental challenge at the global level, and India is majorly affected by it. Numerous emission sources, such as automobiles, industries, fuel-burning for household and commercial activities, and dust due to construction activities, are responsible for air pollution. The lockdown in India which was clamped for controlling the spread of virulent disease also brought down the level of pollutants in air significantly. The proposed approach deals with the application of the hybrid model of Daubechies discrete wavelet decomposition (Db-DWD) and the autoregressive integrated moving average (ARIMA) model for modeling and forecasting the chaotic data of air quality index (PM 2.5 ) from the three most polluted cities (Agra, New Delhi, and Varanasi) in India for pre and within lockdown periods. The estimated outputs of the component series are then reconstructed to obtain the final forecast of the AQI data. The statistical evaluation compares the performance of the simple ARIMA model and the joint Db-DWD-ARIMA model. Also, the coupled model has been applied for forecasting efficacy with Daubechies mother wavelet of orders 5, 8, 10, and 12. The hybrid model reduced forecasting errors and improved accuracy significantly. Secondly, the forecasting efficiencies in this hybrid model have enhanced with the increase in wavelet order. This study will help to assess and take appropriate steps to control air pollution levels and to monitor the growing air pollutants, which will be significant for our existence.

Precise estimation of water temperature plays a key role in environmental impact assessment, aquatic ecosystems’ management and water resources planning and management. In the current study, convolutional neural networks (CNN) and long short-term memory (LSTM) network-based deep learning models were examined to estimate daily water temperatures of the Bailong River in China. Two novel optimization algorithms, namely the reptile search algorithm (RSA) and weighted mean of vectors optimizer (INFO), were integrated with both deep learning models to enhance their prediction performance. To evaluate the prediction accuracy of the implemented models, four statistical indicators, i.e., the root mean square errors (RMSE), mean absolute errors, determination coefficient and Nash–Sutcliffe efficiency were utilized on the basis of different input combinations involving air temperature, streamflow, precipitation, sediment flows and day of the year (DOY) parameters. It was found that the LSTM-INFO model with DOY input outperformed the other competing models by considerably reducing the errors of RMSE and MAE in predicting daily water temperature.

The study examines the applicability of six metaheuristic regression techniques-M5 model tree (M5RT), multivariate adaptive regression spline (MARS), principal component regression (PCR), random forest (RF), partial least square regression (PLSR) and Gaussian process regression (GPR)-for predicting short-term significant wave heights from one hour to one day ahead. Hourly data from two stations, Townsville and Brisbane Buoys, Queensland, Australia, and historical values were used as model inputs for the predictions. The methods were assessed based on root mean square error, mean absolute error, determination coefficient and new graphical inspection methods (e.g., Taylor and violin charts). On the basis of root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R-2) statistics, it was observed that GPR provided the best accuracy in predicting short-term single-time-step and multi-time-step significant wave heights. On the basis of mean RMSE, GPR improved the accuracy of M5RT, MARS, PCR, RF and PLSR by 16.63, 8.03, 10.34, 3.25 and 7.78% (first station) and by 14.04, 8.35, 13.34, 3.87 and 8.30% (second station) for the test stage.

Though globalization, industrialization, and urbanization have escalated the economic growth of nations, these activities have played foul on the environment. Better understanding of ill effects of these activities on environment and human health and taking appropriate control measures in advance are the need of the hour. Time series analysis can be a great tool in this direction. ARIMA model is the most popular accepted time series model. It has numerous applications in various domains due its high mathematical precision, flexible nature, and greater reliable results. ARIMA and environment are highly correlated. Though there are many research papers on application of ARIMA in various fields including environment, there is no substantial work that reviews the building stages of ARIMA. In this regard, the present work attempts to present three different stages through which ARIMA was evolved. More than 100 papers are reviewed in this study to discuss the application part based on pure ARIMA and its hybrid modeling with special focus in the field of environment/health/air quality. Forecasting in this field can be a great contributor to governments and public at large in taking all the required precautionary steps in advance. After such a massive review of ARIMA and hybrid modeling involving ARIMA in the fields including or excluding environment/health/atmosphere, it can be concluded that the combined models are more robust and have higher ability to capture all the patterns of the series uniformly. Thus, combining several models or using hybrid model has emerged as a routinized custom.

Most of the stock market data are high-frequency data showing nonlinearity, asymmetry, and chaotic behavior due to sharp variations in prices over time. Volatility explains these sudden variations in prices over time and is related to conditional variances that reveal some important facts about stock market returns. So, volatility modeling is required to investigate these significant facts of stock market returns. Autoregressive conditional heteroskedastic (ARCH) models are powerful tools for modeling and estimating conditional variances and volatility in stock market prices. The present study deals with volatility prediction of stock market returns using different variants of Generalized Autoregressive Conditional Heteroskedastic (GARCH) models such as Exponential Autoregressive conditional heteroskedastic (EGARCH) and Glosten-Jagannathan-Runkle (GJR) models with Gaussian distribution and Student's t-distribution. The input data for the study consist of stock market data of the daily and weekly returns of the BSE 100 S&P stock index series from 2009 to 2019. After modeling the daily and weekly returns with GARCH, EGARCH, and GJR models, the volatility of price returns is forecasted for the out-of-sample period. The performance of the proposed models has been evaluated by error statistics that compare the values of original volatility with the predicted values. The results reveal that the out-of-sample volatility forecast with the EGARCH model tends to generate more accurate results with Student's t-distribution when compared to GARCH and GJR models.

Fresh air is imminent for life and to thrive on this planet. However, this vital component of life is ill-effected by fast-paced industrialization, urbanization, automobiles, factories, and coal-based thermal power generation as over the years these have jeopardized the air quality index. Due to hazardous impact of black carbon on the environment as well as human health, researchers have turned their attention towards its study. The artificial neural network and econometric ARIMA model are used to predict black carbon emissions from three major coal mines located at Bokaro, Jharia, and Raniganj in India. A comparative analysis of these two techniques over three different forecasting horizons is carried out for investigating short-term or long-term efficiencies of both the models. The three coal mines have large emissions of particulate matter ( $$P{M}_{2.5}$$ ) that contribute significantly to pollution levels. A multilayer perceptron feedforward artificial neural network with Bayesian regularization-backpropagation neural network (BR-BPNN) algorithm is employed. The efficiency of neural network models is evaluated by mean absolute deviation (MAD), root mean square error (RMSE), and coefficient of determination (R2) values. For all the forecasting horizons and in all the accuracy measures, the BR-BPNN outperformed the traditional econometric ARIMA model in predicting the black carbon concentration values with a considerable reduction in errors ranging from 60 to 70% for all the sites. In addition, the performance of an ARIMA model is found to be dependent on the length of the forecasting horizon. However, no such evidence is found for ANN model in forecasting black carbon concentration data.

The potential of four different neuro-fuzzy embedded meta-heuristic algorithms, particle swarm optimization, genetic algorithm, harmony search, and teaching–learning-based optimization algorithm, was investigated in this study in estimating the water quality of the Yamuna River in Delhi, India. A cross-validation approach was employed by splitting data into three equal parts, where the models were evaluated using each part. The main aim of this study was to find an accurate prediction model for estimating the water quality of the Yamuna River. It is worth noting that the hybrid neuro-fuzzy and LSSVM methods have not been previously compared for this issue. Monthly water quality parameters, total kjeldahl nitrogen, free ammonia, total coliform, water temperature, potential of hydrogen, and fecal coliform were considered as inputs to model chemical oxygen demand (COD). The performance of hybrid neuro-fuzzy models in predicting COD was compared with classical neuro-fuzzy and least square support vector machine (LSSVM) methods. The results showed higher accuracy in COD prediction when free ammonia, total kjeldahl nitrogen, and water temperature were used as inputs. Hybrid neuro-fuzzy models improved the root mean square error of the classical neuro-fuzzy model and LSSVM by 12% and 4%, respectively. The neuro-fuzzy models optimized with harmony search provided the best accuracy with the lowest root mean square error (13.659) and mean absolute error (11.272), while the particle swarm optimization and teaching–learning-based optimization showed the highest computational speed (21 and 24 min) compared to the other models.

In the present investigation, we study the reflection of plane waves, that is, Longitudinal displacement wave(P-Wave), Thermal wave(T-Wave) and Mass Diffusive wave(MD-Wave) in thermodiffusion elastic-half medium which is subjected to impedence boundary condition in context of one relaxatioon time theory given by Lord and Shulman theory (L-S) and the Coupled theory (C-T) of thermoelasticity. The expressions of amplitude ratios are obtained numerically and their variation with angle of incidence is presented graphically for a particular model to emphasize on the impact of impedence parameter, relaxation time and diffusion. Some special cases are also deduced.