Search

Predicting the nearshore sediment transport and shifts in coastlines in view of climate change is important for planning and management of coastal infrastructure and requires an accurate prediction of the regional wave climate as well as an in-depth understanding of the complex morphology surrounding the area of interest. Recently, hybrid shoreline evolution models are being used to inform coastal management. These models typically apply the one-line theory to estimate changes in shoreline morphology based on littoral drift gradients calculated from a 2DH coupled wave, flow, and sediment transport model. As per the one-line theory, the calculated littoral drift is uniformly distributed over the active coastal profile. A key challenge facing the application of hybrid models is that they fail to consider complex morphologies when updating the shorelines for several scenarios. This is mainly due to the scarcity of field datasets on beach behavior and nearshore morphological change that extends up to the local depth of closure, leading to assumptions in this value in overall shoreline shift predictions. In this study, we propose an improved hybrid model for shoreline shift predictions in an open sandy beach system impacted by human interventions and changes in wave climate. Three main conclusions are derived from this study. First, the optimal boundary conditions for modeling shoreline evolution need to vary according to local coastal geomorphology and processes. Second, specifying boundary conditions within physically realistic ranges does not guarantee reliable shoreline evolution predictions. Third, hybrid 2D/one-line models have limited applicability in simple planform morphologies where the active beach profile is subject to direct impacts due to wave action and/or human interventions, plausibly due to the one-line theory assumption of a constant time-averaged coastal profile. These findings provide insightful information into the drivers of shoreline evolution around sandy beaches, which have practical implications for advancing the shoreline evolution models. [ABSTRACT FROM AUTHOR]

To develop agricultural risk management strategies, the early identification of water deficits during the growing cycle is critical. This research proposes a deep learning hybrid approach for multi-step soil moisture forecasting in the Bundaberg region in Queensland, Australia, with predictions made for 1-day, 14-day, and 30-day, intervals. The model integrates Geospatial Interactive Online Visualization and Analysis Infrastructure (Giovanni) satellite data with ground observations. Due to the periodicity, transience, and trends in soil moisture of the top layer, time series datasets were complex. Hence, the Maximum Overlap Discrete Wavelet Transform (moDWT) method was adopted for data decomposition to identify the best correlated wavelet and scaling coefficients of the predictor variables with the target top layer moisture. The proposed 3-phase hybrid moDWT-Lasso-LSTM model used the Least Absolute Shrinkage and Selection Operator (Lasso) method for feature selection. Optimal hyperparameters were identified using the Hyperopt algorithm with deep learning LSTM method. This proposed model's performances were compared with benchmarked machine learning (ML) models. In total, nine models were developed, including three standalone models (e.g., LSTM), three integrated feature selection models (e.g., Lasso-LSTM), and three hybrid models incorporating wavelet decomposition and feature selection (e.g., moDWT-Lasso-LSTM). Compared to alternative models, the hybrid deep moDWT-Lasso-LSTM produced the superior predictive model across statistical performance metrics. For example, at 1-day forecast, The moDWT-Lasso-LSTM model exhibits the highest accuracy with the highest R 2 ≈ 0.92469 and the lowest RMSE ≈ 0.97808 , MAE ≈ 0.76623 , and SMAPE ≈ 4.39700 %, outperforming other models. The moDWT-Lasso-DNN model follows closely, while the Lasso-ANN and Lasso-DNN models show lower accuracy with higher RMSE and MAE values. The ANN and DNN models have the lowest performance, with higher error metrics and lower R2 values compared to the deep learning models incorporating moDWT and Lasso techniques. This research emphasizes the utility of the advanced complementary ML model, such as the developed moDWT-Lasso-LSTM 3-phase hybrid model, as a robust data-driven tool for early forecasting of soil moisture. [ABSTRACT FROM AUTHOR]

In the domain of smart health devices, the accurate detection of physical indicators levels plays a crucial role in enhancing safety and well-being. This paper introduces a cross device federated learning framework using hybrid deep learning model. Specifically, the paper presents a comprehensive comparison of different combination of long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), random forest (RF), and extreme gradient boosting (XGBoost), in order to forecast stress levels by utilizing time series information derived from wearable smart gadgets. The LSTM-RF model demonstrated the highest level of accuracy, achieving 93.53% for user 1, 99.40% for user 2, and 97.88% for user 3. Similarly, the LSTM-XGBoost model yielded favorable outcomes, with accuracy rates of 85.88%, 98.55%, and 92.02% for users 1, 2, and 3, respectively, out of 23 users studied. These findings highlight the efficacy of federated learning and the utilization of hybrid models in stress detection. Unlike traditional centralized learning paradigms, the presented federated approach ensures privacy preservation and reduces data transmission requirements by processing data locally on Edge devices. [ABSTRACT FROM AUTHOR]

This study introduces an advanced mathematical methodology for predicting energy generation and consumption based on temperature variations in regions with diverse climatic conditions and increasing energy demands. Using a comprehensive dataset of monthly energy production, consumption, and temperature readings spanning ten years (2010–2020), we applied polynomial, sinusoidal, and hybrid modeling techniques to capture the non-linear and cyclical relationships between temperature and energy metrics. The hybrid model, which combines sinusoidal and polynomial functions, achieved an accuracy of 79.15% in estimating energy consumption using temperature as a predictor variable. This model effectively captures the seasonal and non-linear consumption patterns, demonstrating a significant improvement over conventional models. In contrast, the polynomial model for energy production, while yielding partial accuracy (R² = 0.65), highlights the need for more advanced techniques to fully capture the temperature-dependent nature of energy production. The results indicate that temperature variations significantly affect energy consumption, with higher temperatures driving increased energy demand for cooling, while lower temperatures affect production efficiency, particularly in systems like hydropower. These findings underscore the necessity for integrating sophisticated models into energy planning to ensure resilience in energy systems amidst climate variability. The study offers critical insights for policymakers to optimize energy generation and distribution in response to changing climatic conditions. [ABSTRACT FROM AUTHOR]

Introduction: Early diagnosis of cervical cancer at the precancerous stage is critical for effective treatment and improved patient outcomes. Objective: This study aims to explore the use of SWIN Transformer and Convolutional Neural Network (CNN) hybrid models combined with transfer learning to classify precancerous colposcopy images. Methods: Out of 913 images from 200 cases obtained from the Colposcopy Image Bank of the International Agency for Research on Cancer, 898 met quality standards and were classified as normal, precancerous, or cancerous based on colposcopy and histopathological findings. The cases corresponding to the 360 precancerous images, along with an equal number of normal cases, were divided into a 70/30 train–test split. The SWIN Transformer and CNN hybrid model combines the advantages of local feature extraction by CNNs with the global context modeling by SWIN Transformers, resulting in superior classification performance and a more automated process. The hybrid model approach involves enhancing image quality through preprocessing, extracting local features with CNNs, capturing the global context with the SWIN Transformer, integrating these features for classification, and refining the training process by tuning hyperparameters. Results: The trained model achieved the following classification performances on fivefold cross-validation data: a 94% Area Under the Curve (AUC), an 88% F1 score, and 87% accuracy. On two completely independent test sets, which were never seen by the model during training, the model achieved an 80% AUC, a 75% F1 score, and 75% accuracy on the first test set (precancerous vs. normal) and an 82% AUC, a 78% F1 score, and 75% accuracy on the second test set (cancer vs. normal). Conclusions: These high-performance metrics demonstrate the models' effectiveness in distinguishing precancerous from normal colposcopy images, even with modest datasets, limited data augmentation, and the smaller effect size of precancerous images compared to malignant lesions. The findings suggest that these techniques can significantly aid in the early detection of cervical cancer at the precancerous stage. [ABSTRACT FROM AUTHOR]

To ensure the constant availability of electrical energy, power companies must consistently maintain a balance between supply and demand. However, electrical load is influenced by a variety of factors, necessitating the development of robust forecasting models. This study seeks to enhance electricity load forecasting by proposing a hybrid model that combines Sorted Coefficient Wavelet Decomposition with Long Short-Term Memory (LSTM) networks. This approach offers significant advantages in reducing algorithmic complexity and effectively processing patterns within the same class of data. Various models, including Stacked LSTM, Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM), and Convolutional Long Short-Term Memory (ConvLSTM), were compared and optimized using grid search with cross-validation on consumption data from Lome, a city in Togo. The results indicate that the ConvLSTM model outperforms its counterparts based on Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and correlation coefficient (R2) metrics. The ConvLSTM model was further refined using wavelet decomposition with coefficient sorting, resulting in the WT+ConvLSTM model. This proposed approach significantly narrows the gap between actual and predicted loads, reducing discrepancies from 10–50 MW to 0.5–3 MW. In comparison, the WT+ConvLSTM model surpasses Autoregressive Integrated Moving Average (ARIMA) models and Multilayer Perceptron (MLP) type artificial neural networks, achieving a MAPE of 0.485%, an RMSE of 0.61 MW, and an R2 of 0.99. This approach demonstrates substantial robustness in electricity load forecasting, aiding stakeholders in the energy sector to make more informed decisions. [ABSTRACT FROM AUTHOR]

The compressive strength of concrete is a crucial parameter in structural design, yet its determination in a laboratory setting is both time-consuming and expensive. The prediction of compressive strength in fly ash-based concrete can be accelerated through the use of machine learning algorithms with artificial intelligence, which can effectively address the problems associated with this process. This paper presents the most innovative model algorithms established based on artificial intelligence technology. These include three single models—a fully connected neural network model (FCNN), a convolutional neural network model (CNN), and a transformer model (TF)—and three hybrid models—FCNN + CNN, TF + FCNN, and TF + CNN. A total of 471 datasets were employed in the experiments, comprising 7 input features: cement (C), fly ash (FA), water (W), superplasticizer (SP), coarse aggregate (CA), fine aggregate (S), and age (D). Six models were subsequently applied to predict the compressive strength (CS) of fly ash-based concrete. Furthermore, the loss function curves, assessment indexes, linear correlation coefficient, and the related literature indexes of each model were employed for comparison. This analysis revealed that the FCNN + CNN model exhibited the highest prediction accuracy, with the following metrics: R2 = 0.95, MSE = 14.18, MAE = 2.32, SMAPE = 0.1, and R = 0.973. Additionally, SHAP was utilized to elucidate the significance of the model parameter features. The findings revealed that C and D exerted the most substantial influence on the model prediction outcomes, followed by W and FA. Nevertheless, CA, S, and SP demonstrated comparatively minimal influence. Finally, a GUI interface for predicting compressive strength was developed based on six models and nonlinear functional relationships, and a criterion for minimum strength was derived by comparison and used to optimize a reasonable mixing ratio, thus achieving a fast data-driven interaction that was concise and reliable. [ABSTRACT FROM AUTHOR]

This study explores the application of deep learning in forecasting electricity consumption. Initially, we assess the performance of standard neural networks, such as convolutional neural networks (CNN) and long short‐term memory (LSTM), along with basic methods like ARIMA and random forest, on a univariate electricity consumption data set. Subsequently, we develop hybrid models for a comprehensive multivariate data set created by merging weather and electricity data. These hybrid models demonstrate superior performance compared to individual models on the univariate data set. Our main contribution is the introduction of a novel hybrid data fusion model. This model integrates a single‐model approach for univariate data, a hybrid model for multivariate data, and a linear regression model that processes the outputs from both. Our hybrid fusion model achieved an RMSE value of 0.0871 on the Chicago data set, outperforming other models such as Random Forest (0.2351), ARIMA (0.2184), CNN (0.1802), LSTM + LSTM (0.1496), and CNN + LSTM (0.1587). Additionally, our model surpassed the performance of our base transformer model. Furthermore, combining the best‐performing transformer model, with a Gaussian Process model resulted in further improvement in performance. The Transformer + Gaussian model achieved an RMSE of 0.0768, compared with 0.0781 for the single transformer model. Similar trends were observed in the Pittsburgh and IHEC data sets. [ABSTRACT FROM AUTHOR]

In late 2023, the United Nations conference on climate change (COP28), which was held in Dubai, encouraged a quick move from fossil fuels to renewable energy. Solar energy is one of the most promising forms of energy that is both sustainable and renewable. Generally, photovoltaic systems transform solar irradiance into electricity. Unfortunately, instability and intermittency in solar radiation can lead to interruptions in electricity production. The accurate forecasting of solar irradiance guarantees sustainable power production even when solar irradiance is not present. Batteries can store solar energy to be used during periods of solar absence. Additionally, deterministic models take into account the specification of technical PV systems and may be not accurate for low solar irradiance. This paper presents a comparative study for the most common Deep Learning (DL) and Machine Learning (ML) algorithms employed for short-term solar irradiance forecasting. The dataset was gathered in Islamabad during a five-year period, from 2015 to 2019, at hourly intervals with accurate meteorological sensors. Furthermore, the Grid Search Cross Validation (GSCV) with five folds is introduced to ML and DL models for optimizing the hyperparameters of these models. Several performance metrics are used to assess the algorithms, such as the Adjusted R2 score, Normalized Root Mean Square Error (NRMSE), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE) and Mean Square Error (MSE). The statistical analysis shows that CNN-LSTM outperforms its counterparts of nine well-known DL models with Adjusted R2 score value of 0.984. For ML algorithms, gradient boosting regression is an effective forecasting method with Adjusted R2 score value of 0.962, beating its rivals of six ML models. Furthermore, SHAP and LIME are examples of explainable Artificial Intelligence (XAI) utilized for understanding the reasons behind the obtained results. [ABSTRACT FROM AUTHOR]

Forecasting the electricity market, even in the short term, is a difficult task, due to the nature of this commodity, the lack of storage capacity, and the multiplicity and volatility of factors that influence its price. The sensitivity of the market results in the appearance of anomalies in the market, during which forecasting models often break down. The aim of this paper is to present the possibility of using hybrid machine learning models to forecast the price of electricity, especially when such events occur. It includes the automatic detection of anomalies using three different switch types and two independent forecasting models, one for use during periods of stable markets and the other during periods of anomalies. The results of empirical tests conducted on data from the Polish energy market showed that the proposed solution improves the overall quality of prediction compared to using each model separately and significantly improves the quality of prediction during anomaly periods. [ABSTRACT FROM AUTHOR]

The estimation of a certain threshold beyond which an extreme value distribution can be fitted to the tail of a data distribution remains one of the main issues in the theory of statistics of extremes. While standard Peak over Threshold (PoT) approaches determine this threshold graphically, we introduce in this paper a general framework which makes it possible for one to determine this threshold algorithmically by estimating it as a free parameter within a composite distribution. To see how this threshold point arises, we propose a general framework for generating three-component hybrid distributions which meets the need of data sets with right heavy-tail. The approach involves the combination of a distribution which can efficiently model the bulk of the data around the mean, with an heavy-tailed distribution meant to model the data observations in the tail while using another distribution as a link to connect the two. Some special examples of distributions resulting from the general framework are generated and studied. An estimation algorithm based on the maximum likelihood method is proposed for the estimation of the free parameters of the hybrid distributions. Application of the hybrid distributions to the S &P 500 index financial data set is also carried out. [ABSTRACT FROM AUTHOR]

Abstract This study introduces an advanced mathematical methodology for predicting energy generation and consumption based on temperature variations in regions with diverse climatic conditions and increasing energy demands. Using a comprehensive dataset of monthly energy production, consumption, and temperature readings spanning ten years (2010–2020), we applied polynomial, sinusoidal, and hybrid modeling techniques to capture the non-linear and cyclical relationships between temperature and energy metrics. The hybrid model, which combines sinusoidal and polynomial functions, achieved an accuracy of 79.15% in estimating energy consumption using temperature as a predictor variable. This model effectively captures the seasonal and non-linear consumption patterns, demonstrating a significant improvement over conventional models. In contrast, the polynomial model for energy production, while yielding partial accuracy (R² = 0.65), highlights the need for more advanced techniques to fully capture the temperature-dependent nature of energy production. The results indicate that temperature variations significantly affect energy consumption, with higher temperatures driving increased energy demand for cooling, while lower temperatures affect production efficiency, particularly in systems like hydropower. These findings underscore the necessity for integrating sophisticated models into energy planning to ensure resilience in energy systems amidst climate variability. The study offers critical insights for policymakers to optimize energy generation and distribution in response to changing climatic conditions.

Abstract The estimation of a certain threshold beyond which an extreme value distribution can be fitted to the tail of a data distribution remains one of the main issues in the theory of statistics of extremes. While standard Peak over Threshold (PoT) approaches determine this threshold graphically, we introduce in this paper a general framework which makes it possible for one to determine this threshold algorithmically by estimating it as a free parameter within a composite distribution. To see how this threshold point arises, we propose a general framework for generating three-component hybrid distributions which meets the need of data sets with right heavy-tail. The approach involves the combination of a distribution which can efficiently model the bulk of the data around the mean, with an heavy-tailed distribution meant to model the data observations in the tail while using another distribution as a link to connect the two. Some special examples of distributions resulting from the general framework are generated and studied. An estimation algorithm based on the maximum likelihood method is proposed for the estimation of the free parameters of the hybrid distributions. Application of the hybrid distributions to the S &P 500 index financial data set is also carried out.

Abstract In late 2023, the United Nations conference on climate change (COP28), which was held in Dubai, encouraged a quick move from fossil fuels to renewable energy. Solar energy is one of the most promising forms of energy that is both sustainable and renewable. Generally, photovoltaic systems transform solar irradiance into electricity. Unfortunately, instability and intermittency in solar radiation can lead to interruptions in electricity production. The accurate forecasting of solar irradiance guarantees sustainable power production even when solar irradiance is not present. Batteries can store solar energy to be used during periods of solar absence. Additionally, deterministic models take into account the specification of technical PV systems and may be not accurate for low solar irradiance. This paper presents a comparative study for the most common Deep Learning (DL) and Machine Learning (ML) algorithms employed for short-term solar irradiance forecasting. The dataset was gathered in Islamabad during a five-year period, from 2015 to 2019, at hourly intervals with accurate meteorological sensors. Furthermore, the Grid Search Cross Validation (GSCV) with five folds is introduced to ML and DL models for optimizing the hyperparameters of these models. Several performance metrics are used to assess the algorithms, such as the Adjusted R 2 score, Normalized Root Mean Square Error (NRMSE), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE) and Mean Square Error (MSE). The statistical analysis shows that CNN-LSTM outperforms its counterparts of nine well-known DL models with Adjusted R 2 score value of 0.984. For ML algorithms, gradient boosting regression is an effective forecasting method with Adjusted R 2 score value of 0.962, beating its rivals of six ML models. Furthermore, SHAP and LIME are examples of explainable Artificial Intelligence (XAI) utilized for understanding the reasons behind the obtained results.

To address the challenges posed by inadequate data and data utilization in multiple scenarios of fatigue loading, a Physics-informed Transfer Learning (PITL) model has been developed to predict the fatigue life of IN718 superalloy. Strain-controlled low-cycle fatigue tests were carried out at 400 °C with three distinct strain ratios, which were subsequently segmented for individual transfer learning tests. PITL models with significant engineering value were built by integrating transfer learning methodologies rooted in TrAdaBoost with a physics-based model that hinges on the principles of equivalent strain theory. The findings suggest that PITL models exhibit improved accuracy and greater robustness compared to both transfer learning and physics models.

Mathematical modelling of physical phenomena is based on the laws of physics, but for complicated processes, phenomenological models could enhance the descriptive and prescriptive power of the analysis. This paper describes some hybrid models, where in addition to the physics-driven part, some phenomenological variables (based on observations) are added. The internal variables widely used in continuum mechanics for modelling dissipative processes and the phenomenological variables used in modelling neural impulses are described and compared. The appendices describe two models of neural impulses and test problems for two classical cases: the wave equation and the diffusion equation. These test problems demonstrate the usage of phenomenological variables for describing dissipation as well as amplification.

Precise estimation of daily reference crop evapotranspiration (ET0) is critical for water resource management and agricultural irrigation optimization worldwide. In China, diverse climatic zones pose challenges for accurate ET0 prediction. Here, we evaluate the performance of a support vector machine (SVM) and its hybrid models, PSO-SVM and WOA-SVM, utilizing meteorological data spanning 1960–2020. Our study aims to identify a high-precision, low-input ET0 estimation tool. The findings indicate that the hybrid models, particularly WOA-SVM, demonstrated superior accuracy with R2 values ranging from 0.973 to 0.999 and RMSE values between 0.123 and 0.863 mm/d, outperforming the standalone SVM model with R2 values of 0.955 to 0.989 and RMSE values of 0.168 to 0.982 mm/d. The standalone SVM model showed relatively lower accuracy with R2 values of 0.822 to 0.887 and RMSE values of 0.381 to 1.951 mm/d. Notably, the WOA-SVM model, with R2 values of 0.990 to 0.992 and RMSE values of 0.092 to 0.160 mm/d, emerged as the top performer, showcasing the benefits of the whale optimization algorithm in enhancing SVM's predictive capabilities. The PSO-SVM model also presented improved performance, especially in the temperate continental zone (TCZ), subtropical monsoon region (SMZ), and temperate monsoon zone (TMZ), when using limited meteorological data as the input. The study concludes that the WOA-SVM model is a promising tool for high-precision daily ET0 estimation with fewer meteorological parameters across the different climatic zones of China. [ABSTRACT FROM AUTHOR]

As a consequence of human activity, waste generation is unavoidable, and its volume and complexity escalate with urbanization, economic progress, and the elevation of living standards in cities. Annually, the world produces about 2.01 billion tons of municipal solid waste, which often lacks environmentally safe management. The importance of solid waste management lies in its role in sustainable development, aimed at reducing the environmental harms from waste creation and disposal. With the expansion of urban populations, waste management systems grow increasingly complex, necessitating more sophisticated optimization strategies. This analysis thoroughly examines the optimization techniques used in solid waste management, assessing their application, benefits, and limitations by using PRISMA 2020. This study, reviewing the literature from 2010 to 2023, divides these techniques into three key areas: waste collection and transportation, waste treatment and disposal, and resource recovery, using tools like mathematical modeling, simulation, and artificial intelligence. It evaluates these strategies against criteria such as cost-efficiency, environmental footprint, energy usage, and social acceptability. Significant progress has been noted in optimizing waste collection and transportation through innovations in routing, bin placement, and the scheduling of vehicles. The paper also explores advancements in waste treatment and disposal, like selecting landfill sites and converting waste to energy, alongside newer methods for resource recovery, including sorting and recycling materials. In conclusion, this review identifies research gaps and suggests directions for future optimization efforts in solid waste management, emphasizing the need for cross-disciplinary collaboration, leveraging new technologies, and adopting tailored approaches to tackle the intricate challenges of managing waste. These insights offer valuable guidance for policymakers, waste management professionals, and researchers involved in crafting sustainable waste strategies. [ABSTRACT FROM AUTHOR]

In this paper, we develop a Fuzzy Cognitive Map (FCM)-based framework for investigating user satisfaction in information services and further focus on how various affecting factors are connected to the overall user service experience. Conventional approaches usually perform poorly with extensive uncertainties or difficult, complex relationships between service quality, response time, usability and personalization. As a case in point, FCMs give us an appropriate mathematical framework to model causal relationships and simulate dynamic interplays between these factors. In the study, critical factors are taken as nodes in FCM and then it establishes causal weights between these so that their importance can be quantified. The state of every concept is then updated via matrix-vector operation and iterative updates with sigmoid activation function until convergence. A comprehensive case study illustrates an actual usage of the FCM framework, and highlights its ability to isolate key drivers that impact satisfaction and suggests avenues for improvement. Next steps include integrating IoT sensors for real-time monitoring, hybrid models with machine learning to improve predictions and relevant applications in different fields which goes from e-commerce to healthcare. This experimentation underscores FCMs potential in decision-making procedures which presents good insight towards enhancing users experience when dealing with information service. [ABSTRACT FROM AUTHOR]

Introduction: Type 1 Diabetes (T1D) affects over 9 million worldwide and necessitates meticulous self-management for blood glucose (BG) control. Utilizing BG prediction technology allows for increased BG control and a reduction in the diabetes burden caused by self-management requirements. This paper reviews BG prediction models in T1D, which include nutritional components. Method: A systematic search, utilizing the PRISMA guidelines, identified articles focusing on BG prediction algorithms for T1D that incorporate nutritional variables. Eligible studies were screened and analyzed for model type, inclusion of additional aspects in the model, prediction horizon, patient population, inputs, and accuracy. Results: The study categorizes 138 blood glucose prediction models into data-driven (54%), physiological (14%), and hybrid (33%) types. Prediction horizons of ≤30 min are used in 36% of models, 31–60 min in 34%, 61–90 min in 11%, 91–120 min in 10%, and >120 min in 9%. Neural networks are the most used data-driven technique (47%), and simple carbohydrate intake is commonly included in models (data-driven: 72%, physiological: 52%, hybrid: 67%). Real or free-living data are predominantly used (83%). Conclusion: The primary goal of blood glucose prediction in T1D is to enable informed decisions and maintain safe BG levels, considering the impact of all nutrients for meal planning and clinical relevance. [ABSTRACT FROM AUTHOR]

Mathematical modelling of physical phenomena is based on the laws of physics, but for complicated processes, phenomenological models could enhance the descriptive and prescriptive power of the analysis. This paper describes some hybrid models, where in addition to the physics-driven part, some phenomenological variables (based on observations) are added. The internal variables widely used in continuum mechanics for modelling dissipative processes and the phenomenological variables used in modelling neural impulses are described and compared. The appendices describe two models of neural impulses and test problems for two classical cases: the wave equation and the diffusion equation. These test problems demonstrate the usage of phenomenological variables for describing dissipation as well as amplification. [ABSTRACT FROM AUTHOR]

Groundwater, a fundamental asset, isn't effectively accessible in some parts of the world. The current research work pointed toward obtaining precise maps of potential groundwater zones. This study aimed for potential groundwater modeling and extracting the precise maps using four new advanced hybrid ML models (Dagging-HP, Bagging-HP, AdaBoost-HP, Decorate-HP) and one single model Hyperpipes (HP) in the Doji Watershed, situated in the eastern part of Golestan province, Iran. Among the selected models, the AdaBoost-HP model is the most efficient, with an AUC - ROC of 0.972, accuracy (0.922), sensitivity (0.906), and specificity (0.938), which gives the most promising values, when determining the collinearity between the 14 training factors, which are, in descending order of significance, LULC, Distance to stream (DtS), Topography wetness index (TWI), HAND, Distance to the road (DtR), Geomorphology, Topography position index (TPI), Lithology, Drainage density (DD), Elevation, Slope, Rainfall, and Clay (%). The AUC-ROC approach was employed to assess the model's performance along with Accuracy, Specificity, and Sensitivity. This model revealed that 7.37% has very high groundwater potential in the eastern and south-western parts of the study, whereas 36.8% has a very low groundwater potential in the north-western and south-eastern parts of the study. It can be said from this assessment that results obtained from this investigation are better and more reliable, which gives essential encouragement for further study put on this method for groundwater potential mapping of other areas of the world along with other areas of hydrogeological investigations. [ABSTRACT FROM AUTHOR]

Growing degree‐days (GDD), an estimate of an organism's growing season length, has been shown to be an important predictor of Lepidopteran species' distributions and could be influencing Lepidopteran range shifts to climate change. Yet, one understudied simplification in this literature is that the same thermal threshold is used in the calculations of GDD for all species instead of a species‐specific threshold. By characterizing the phenological process influenced by climate, a species‐specific estimate of GDD should improve the accuracy of species distribution models (SDMs). To test this hypothesis, we used published, experimentally estimated thermal thresholds and modeled the current geographic distribution of 30 moth species native to North America. We found that the predictive performance of models based on a species‐specific estimate of GDD was indistinguishable from models based on a standard estimate of GDD. This is likely because GDD was not an important predictor of these species' distributions. Our findings suggest that experimentally estimated thermal thresholds may not always scale up to be predictive at broad scales and that more work is needed to leverage the data from lab experiments into SDMs to accurately predict species' range shifts in response to climate change. [ABSTRACT FROM AUTHOR]

Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing the basis of sophistication in planning and decision-making. This paper examines two decision-making schemes in active inference based on "planning" and "learning from experience". Furthermore, we also introduce a mixed model that navigates the data complexity trade-off between these strategies, leveraging the strengths of both to facilitate balanced decision-making. We evaluate our proposed model in a challenging grid-world scenario that requires adaptability from the agent. Additionally, our model provides the opportunity to analyse the evolution of various parameters, offering valuable insights and contributing to an explainable framework for intelligent decision-making. [ABSTRACT FROM AUTHOR]

Increasing sediment yield is one of the important environmental challenges in river basins resulting from changing land use. The current study develops an adaptive neuro fuzzy inference system (ANFIS) hybridized with evolutionary algorithms to predict annual sediment yield at the catchment scale considering some key factors affecting the alteration of the sediment yield. The key factors consist of the area of the sub-catchments, average slope of the sub-catchments, rainfall, and forest index, and the output of the model is sediment yield. Several indices such as the Nash–Sutcliffe efficiency (NSE), root mean square error and vulnerability index (VI) were applied to evaluate the performance of the models. Moreover, hybrid models were compared in terms of complexities to select the best approach. Based on the results in Talar River basin in Iran, several hybrid models in which particle swarm optimization (PSO), genetic algorithm, invasive weed optimization, biogeography-based optimization, and shuffled complex evolution used to train the neuro fuzzy network are able to generate reliable sediment yield models. The NSE of all previously listed models is more than 0.8 which means they are robust for assessing sediment yield resulting from land use change with a focus on deforestation. The proposed models are fairly similar in terms of computational complexities which implies no priority for selecting the best model. However, PSO-ANFIS performed slightly better than the other models especially in terms of accuracy of the outputs due to a high NSE (0.92) and a low VI (1.9 Mg/ha). Using the proposed models is recommended due to the lower required time and data compared to a physically based models such as the The Soil and Water Assessment Tool. However, some drawbacks restrict the application of the proposed model. For example, the proposed models cannot be used for small temporal scales. [ABSTRACT FROM AUTHOR]

Time-series forecasting is crucial in the efficient operation and decision-making processes of various industrial systems. Accurately predicting future trends is essential for optimizing resources, production scheduling, and overall system performance. This comprehensive review examines time-series forecasting models and their applications across diverse industries. We discuss the fundamental principles, strengths, and weaknesses of traditional statistical methods such as Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ES), which are widely used due to their simplicity and interpretability. However, these models often struggle with the complex, non-linear, and high-dimensional data commonly found in industrial systems. To address these challenges, we explore Machine Learning techniques, including Support Vector Machine (SVM) and Artificial Neural Network (ANN). These models offer more flexibility and adaptability, often outperforming traditional statistical methods. Furthermore, we investigate the potential of hybrid models, which combine the strengths of different methods to achieve improved prediction performance. These hybrid models result in more accurate and robust forecasts. Finally, we discuss the potential of newly developed generative models such as Generative Adversarial Network (GAN) for time-series forecasting. This review emphasizes the importance of carefully selecting the appropriate model based on specific industry requirements, data characteristics, and forecasting objectives. [ABSTRACT FROM AUTHOR]

This review paper is a foundational resource for power distribution and management decisions, thoroughly examining short-term load forecasting (STLF) models within power systems. The study categorizes these models into three groups: statistical approaches, intelligent-computing-based methods, and hybrid models. Performance indicators are compared, revealing the superiority of heuristic search and population-based optimization learning algorithms integrated with artificial neural networks (ANNs) for STLF. However, challenges persist in ANN models, particularly in weight initialization and susceptibility to local minima. The investigation underscores the necessity for sophisticated predictive models to enhance forecasting accuracy, advocating for the efficacy of hybrid models incorporating multiple predictive approaches. Acknowledging the changing landscape, the focus shifts to STLF in smart grids, exploring the transformative potential of advanced power networks. Smart measurement devices and storage systems are pivotal in boosting STLF accuracy, enabling more efficient energy management and resource allocation in evolving smart grid technologies. In summary, this review provides a comprehensive analysis of contemporary predictive models and suggests that ANNs and hybrid models could be the most suitable methods to attain reliable and accurate STLF. However, further research is required, including considerations of network complexity, improved training techniques, convergence rates, and highly correlated inputs to enhance STLF model performance in modern power systems. [ABSTRACT FROM AUTHOR]

Failure of industrial assets can cause financial, operational and safety hazards across different industries. Monitoring their condition is crucial for successful and smooth operations. The colossal volume of sensory data generated and acquired throughout industrial operations supports real-time condition monitoring of these assets. Leveraging digital technologies to analyze acquired data creates an ideal environment for applying advanced data-driven machine learning techniques, such as convolutional neural networks (CNNs) and vision transformer (ViT) to detect faults and classify, enabling accurate prediction and timely maintenance of industrial assets. In this paper, we present a novel hybrid framework based on the local feature extraction ability of CNN with comprehensive understanding of transformer within a global context. The proposed method leverages the complex weight-sharing properties of CNNs and ability of transformers to understand the larger context of spatial relationships in large-scale patterns, making it applicable to datasets of varying sizes. Preprocessing methods such as data augmentation are used to train the model on the Case Western Reserve University (CWRU) dataset in order to increase generalization through computational efficiency. An average fault classification accuracy of 99.62% is accomplished over all three fault classes with an average time-to-fault detection of 38.4 ms. MFPT fault dataset is used to further validate the method with an accuracy of 99.17% for outer race and 99.26% for inner race. Moreover, the proposed framework can be modified to accommodate alternative convolutional models.

The development of cell cultures to produce monoclonal antibodies is a multi-step, time-consuming, and labor-intensive procedure which usually lasts several years and requires heavy investment by biopharmaceutical companies. One key aspect of process optimization is improving the feeding strategy. This step is typically performed though design of experiments (DoE) during process development, in such a way as to identify the optimal combinations of factors which maximize the productivity of the cell cultures. However, DoE is not suitable for time-varying factor profiles because it requires a large number of experimental runs which can last several weeks and cost tens of thousands of dollars. We here suggest a methodology to optimize the feeding schedule of mammalian cell cultures by virtualizing part of the experimental campaign on a hybrid digital model of the process to accelerate experimentation and reduce experimental burden. The proposed methodology couples design of dynamic experiments (DoDE) with a hybrid semi-parametric digital model. In particular, DoDE is used to design optimal experiments with time-varying factor profiles, whose experimental data are then utilized to train the hybrid model. This will identify the optimal time profiles of glucose and glutamine for maximizing the antibody titer in the culture despite the limited number of experiments performed on the process. As a proof-of-concept, the proposed methodology is applied on a simulated process to produce monoclonal antibodies at a 1-L shake flask scale, and the results are compared with an experimental campaign based on DoDE and response surface modeling. The hybrid digital model requires an extremely limited number of experiments (nine) to be accurately trained, resulting in a promising solution for performing in silico experimental campaigns. The proposed optimization strategy provides a 34.9% increase in the antibody titer with respect to the training data and a 2.8% higher antibody titer than the optimal results of two DoDE-based experimental campaigns comprising different numbers of experiments (i.e., 9 and 31), achieving a high antibody titer (3,222.8 mg/L) —very close to the real process optimum (3,228.8 mg/L).

Predicting the nearshore sediment transport and shifts in coastlines in view of climate change is important for planning and management of coastal infrastructure and requires an accurate prediction of the regional wave climate as well as an in-depth understanding of the complex morphology surrounding the area of interest. Recently, hybrid shoreline evolution models are being used to inform coastal management. These models typically apply the one-line theory to estimate changes in shoreline morphology based on littoral drift gradients calculated from a 2DH coupled wave, flow, and sediment transport model. As per the one-line theory, the calculated littoral drift is uniformly distributed over the active coastal profile. A key challenge facing the application of hybrid models is that they fail to consider complex morphologies when updating the shorelines for several scenarios. This is mainly due to the scarcity of field datasets on beach behavior and nearshore morphological change that extends up to the local depth of closure, leading to assumptions in this value in overall shoreline shift predictions. In this study, we propose an improved hybrid model for shoreline shift predictions in an open sandy beach system impacted by human interventions and changes in wave climate. Three main conclusions are derived from this study. First, the optimal boundary conditions for modeling shoreline evolution need to vary according to local coastal geomorphology and processes. Second, specifying boundary conditions within physically realistic ranges does not guarantee reliable shoreline evolution predictions. Third, hybrid 2D/one-line models have limited applicability in simple planform morphologies where the active beach profile is subject to direct impacts due to wave action and/or human interventions, plausibly due to the one-line theory assumption of a constant time-averaged coastal profile. These findings provide insightful information into the drivers of shoreline evolution around sandy beaches, which have practical implications for advancing the shoreline evolution models.

Mapping the spatial distribution of soil organic carbon (SOC) is crucial for monitoring soil health, understanding ecosystem functions, and contributing to global carbon cycling. However, few studies have directly compared the influence of hybrid models and individual models with varying spatial resolutions on SOC prediction at a national scale. In this study, by combining remote sensing data, we utilized the LUCAS 2018 soil dataset to evaluate the potential capacities of hybrid models for predicting SOC content at different spatial resolutions in Germany. The hybrid models PLSRK and RFK consisted of partial least square regression (PLSR) with residual original kriging (OK) models, and random forest (RF) models with residual OK models, respectively. Individual PLSR and RF models were used as reference models. All these models were applied to estimate SOC content at 10 m, 50 m, 100 m, and 200 m spatial resolutions. Sentinel-2 bands, band indices, and topography variables were as predictors. The results revealed that hybrid models had a more accurate prediction of SOC content with higher explanations and lower prediction errors compared with individual models. The RFK model at the spatial resolution of 100 m was the fittest model with R2 = 0.416, RMSE = 0.545, and RPIQ = 1.647, which enhanced 3.74% of explanation compared with the performance of RF model. The results also showed that hybrid models at a relatively coarse resolution (100 m) had better accuracy instead of those at high spatial resolution (10 m, 50 m). Sentinel-2 remote sensing data showed significant predictive capabilities for estimating SOC content. The predicted spatial distribution of SOC content revealed that the high SOC concentrated in the northwest grassland, central and southwestern mountains, and the Alps in Germany. Our study provided a benchmark SOC map in Germany for monitoring the changes resulting from land use and climate impacts, and we illustrated the accuracy of hybrid models and the effects of spatial resolutions on SOC predictions at a national scale.

Given the numerous factors that can influence stock prices such as a company's financial health, economic conditions, and the political climate, predicting stock prices can be quite difficult. However, the advent of the newer learning algorithm such as extreme learning machine (ELM) offers the potential to integrate ARIMA and ANN methods within a hybrid framework. This study aims to examine how hybrid time series models and an artificial neural network (ANN)-based ELM performed when analyzing daily Johannesburg Stock Exchange/Financial Times Stock Exchange (JSE/FTSE) closing stock prices over 5 years, from 15 June 2018 to 15 June 2023, encompassing 1,251 data points. The methods used in the study are autoregressive integrated moving average (ARIMA), ANN-based ELM, and a hybrid of ARIMA-ANN-based ELM. The ARIMA method was used to model linearity, while nonlinearity was modeled using an ANN-based ELM. The study further modeled both linearity and non-linearity using the hybrid ARIMA-ANN-based ELM model. The model was then compared to identify the best model for closing stock prices using error matrices. The error metrics revealed that the hybrid ARIMA-ANN-based ELM model performed better than the ARIMA [1, 6, 6] and ANN-based ELM models. It is evident from the literature that better forecasting leads to better policies in the future. Therefore, this study recommends policymakers and practitioners to use the hybrid model, as it yields better results. Furthermore, researchers may also delve into assessing the effectiveness of models by utilizing additional conventional linear models and hybrid variants such as ARIMA-generalized autoregressive conditional heteroskedasticity (GARCH) and ARIMA-EGARCH. Future studies could also integrate these with non-linear models to better capture both linear and non-linear patterns in the data.

This paper proposes two hybrid approaches based on Autoencoders (AEs) for long-term temperature prediction. The first algorithm comprises an AE trained to learn temperature patterns, which is then linked to a second AE, used to detect possible anomalies and provide a final temperature prediction. The second proposed approach involves training an AE and then using the resulting latent space as input of a neural network, which will provide the final prediction output. Both approaches are tested in long-term air temperature prediction in European cities: seven European locations where major heat waves occurred have been considered. The long-term temperature prediction for the entire year of the heatwave events has been analysed. Results show that the proposed approaches can obtain accurate long-term (up to 4 weeks) temperature prediction, improving Persistence and Climatology in the benchmark models compared. In heatwave periods, where the persistence of the temperature is extremely high, our approach beat the persistence operator in three locations and works similarly in the rest of the cases, showing the potential of this AE-based method for long-term temperature prediction.

Using machine learning methods is efficient in predicting floods in areas where complete data is not available. Therefore, this study considers the Adaptive Neuro-Fuzzy Inference System (ANFIS) model combined with evolutionary algorithms, namely Harris Hawks Optimization (HHO) and Arithmetic Optimization Algorithm (AOA), to predict the flood of Shahrchay River in the northwest of Iran. The data used included the daily data of precipitation, evaporation, and runoff in the years 2016 and 2017, where 70% of the data were used for model training and the rest for testing the models. The results showed that although the ANFIS model provided values with high errors in several steps, especially in steps with maximum or minimum values, the use of HHO and AOA optimization algorithms resulted in a significant reduction in the error values. The ANFIS-AOA model utilizing an input scenario including the flow in the previous one to three days exerted the most promising results in the test data, with Nash Sutcliffe Efficiency (NSE) Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) of 0.93, 1.34, and 0.69, respectively. According to Taylor's diagram, the ANFIS-AOA hybrid algorithm predicts flood values with greater performance than the other models. HIGHLIGHTS Integration of ANFIS methods with optimization algorithms was done.; Effective flood estimation with limited data was done.; Quantitative assessment metrics and model validation were performed.; Optimal input pattern selection was done.; Practical implications for water management were studied.;

Recently, the interest of researchers in the use of hybrid models in the process of analyzing model time series with fluctuations and forecasting fluctuations in financial time series has increased significantly. Hybrid ARMA-GARCH models were created for medium- and long-term forecasts of time series of financial market index prices: ARMA models are used to analyze their linear component, which is a combination of autoregressive models and moving average models, and GARCH models are used to analyze the nonlinear component. which are generalized autoregressive models that depend on the nonconstancy of variance models. Hybrid ARMA-GARCH models eliminate the weaknesses and gaps that exist in each group of models (ARMA and GARCH) separately, which increases their forecasting accuracy and reliability, so they have already been successfully applied to model and forecast daily stock returns for three standard indices in the USA. The purpose of this article is to investigate which of the hybrid ARMA-GARCH models is optimal for forecasting the return of the DAX index, which is the most important stock index of the German securities market. It is the German equivalent of the American Dow Jones Index, has been calculated since 1988 by Deutsche Börse AG and reflects the total return on capital of the largest stock companies listed on the Frankfurt Stock Exchange (currently 40; by 2021 – 30): calculated as a weighted average of capitalization of the value of Free Float share prices on the Xetra electronic exchange, and also takes into account dividends on shares, assuming that the dividend is reinvested in the share on which it was accrued. The database of this study consisted of the daily closing prices of the DAX index presented on the official website of the Frankfurt Stock Exchange during the period from 01.01.2018 to 09.30.2023 (altogether about 1,500 observations), the stability of the time series was assessed using Expanded Dickey Fuller Liquidity (ADF). The article proposes 7 hybrid models, from which the one that is best suited for modeling the volatility of the DAX index is selected. It is an ARMA (2,3)-EGARCH (1,1) model because it captures volatility and leverage effects on DAX returns and its expected returns more than other models. The selection of the best alternative from the developed array of hybrid models was carried out according to the following criteria: AIC (Akaike Information Criterion), BIC (Bayesian Information Criterion), H-QIC (Hannan-Quinn Information Criterion).

Abstract The state of New York admitted 143 million metric tons of carbon emissions from fossil fuels in 2020, prompting the ambitious goal set by the CLCPA to achieve carbon neutrality. The paper focused on analyzing and predicting carbon emissions using four different machine-learning algorithms. It examined emissions from fossil fuel combustion from 1990 to 2020 and validated four different algorithms to choose the most effective one for predicting emissions from 2020 to 2050. The analysis covered various economic sectors including transportation, residential, commercial, industrial, and electric power. By analyzing policies, the paper forecasted emissions for 2030 and 2050, leading to the identification of different pathways to reach carbon neutrality. The research concluded that in order to achieve neutrality, radical measures must be taken by the state of New York. Additionally, the paper compared the most recent data for 2021 with the forecasts, showing that significant measures need to be implemented to achieve the goal of carbon neutrality. Despite some studies assuming a trend of decreased emissions, the research revealed different results. The paper presents three pathways, two of which follow the ambitious plan to reach carbon neutrality. As a result, the emission amount by 2050 for the different pathways was projected to be 31.1, 22.4, and 111.95 of MMt CO2 e, showcasing the need for urgent action to combat climate change.

Rock samples' TOC content is the best indicator of the organic matter in source rocks. The origin rock samples’ analysis is used to calculate it manually by specialists. This method requires time and resources because it relies on samples from many well intervals in source rocks. Therefore, research has been done to aid this effort. Machine learning algorithms can estimate total organic carbon instead of well logs and stratigraphic studies. In light of these efforts, the current work present a study on automating the total organic carbon estimation using machine learning approaches improved by an evolutionary methodology to give the model flexibility and precision. Genetic algorithms, differential evolution, particle swarm optimization, grey wolf optimization, artificial bee colony, and evolution strategies were used to improve machine learning models to predict TOC. The six metaheuristics were integrated into four machine learning methods: extreme learning machine, elastic net linear model, linear support vector regression, and multivariate adaptive regression splines. Core samples from the YuDong-Nan shale gas field, located in the Sichuan basin, were used to evaluate the hybrid strategy. The findings show that combining machine learning models with an evolutionary algorithms in a hybrid fashion produce flexible models that accurately predict TOC. The results show that, independent of the metaheuristic used to guide the model selection, optimized extreme learning machines attained the best performance scores according to six metrics. Such hybrid models can be used in exploratory geological research, particularly for unconventional oil and gas resources.

Improving the reliability of blade bearings is essential for the safe operation of wind turbines. This challenge can be met with the help of virtual testing and digital-twin driven condition monitoring. For such approaches, a precise digital representation of the blade bearing and its test bench is an essential prerequisite. However, various factors prevent the capture of all parameters of the blade bearing and the associated test bench. Parameters such as bearing preload, rolling element and raceway dimensions, and bolt preload during assembly vary with each bearing and test bench setup. As these parameters cannot be measured directly, an alternative solution is required. This article presents a methodology to efficiently estimate non-measurable parameters of the test bench using a combination of model-based and data-driven approaches, improving the detailed and accurate virtual testing of blade bearings. It must be ensured to enable the fastest possible, most computationally efficient estimation of parameters during virtual testing or condition monitoring. The developed methodology is evaluated using the example of bolt preload on the test bench. By employing a random forest model and the strain gauge measurements attached to the blade bearing, the bolt preload parameters are estimated. The results demonstrate that the accuracy of the digital model of the blade bearing test bench is improved by up to 11 % in three out of four test bench setups. The great improvement in the accuracy of the digital model highlights the effectiveness of the proposed methodology in enhancing virtual blade bearing testing and digital-twin driven condition monitoring.

In this study, three novel machine learning algorithms of additive regression-random forest (AR-RF), Iterative Classifier Optimizer (ICO-AR-RF), and multi-scheme (MS-RF) were explored for carbon dioxide (CO2) flux rate prediction from three agricultural fields. To build the dataset, 401 samples were collected from two fields in Prince Edward Island (PEI) and 122 samples from the New Brunswick (NB), Canada. In addition, soil moisture (SM), temperature (ST), and electrical conductivity (EC), alongside eight climatic variables including wind speed (WS), solar radiation (SR), relative humidity (RH), precipitation (PCP), air temperature (AT), dew point (DP), vapour pressure difference (VPD) and reference evapotranspiration (ETo) were also collected. Greedy stepwise (GS) approach was implemented for feature selection. Finally, different qualitative (scatter plot, line graph, Taylor diagram, box plot, and Rug plot), and quantitative (uncertainty analysis, root mean square error (RMSE), percent of BIAS (PBIAS), Nash Sutcliff efficiency (NSE) and RMSE-observations standard deviation ratio (RSR)) techniques were used for model evaluation and comparison. Results of feature selection approaches revealed that DP, AT, SM, and ST are the four most effective variables at CO2 prediction in PEI, while AT, RH, DP, and ST are the most effective in the NB study area. For optimum input scenario, the GS algorithm was applied, and results showed that a combination of DP, AT, ST, SM, and ETo was the best for the PEI study area, while for NB, all input variables should be involved. Our analysis, for prediction of CO2 fluxes, confirmed that the ICO-AR-RF model performed the best at both PEI (RMSE=0.70, NSE=0.76, PBIAS=-5.11, RSR=0.48) and NB (RMSE=0.74, NSE=0.75, PBIAS=3.23, RSR=0.50), followed by MS-RF and AR-RF. Uncertainty analysis showed that CO2 prediction is more sensitive to input scenario selection than models in both study areas. Results revealed that climatic variables are more effective in CO2 prediction than soil characteristics and the developed hybrid model ICO-AR-RF can be a promising tool for decision-makers and beneficial for stakeholders.

Landslide susceptibility maps (LSMs) can play a bigger role in promoting the understanding of future landslides. This paper explores and compares the capability of three state-of-the-art bivariate models, namely the frequency ratio (FR), statistical index (SI), and weights of evidence (WoE), with ensembles of multivariate logistic regression (LR), for LSM in part of Tibet. Firstly, a landslide inventory map with 829 landslide records is obtained from field surveys and interpretation. Secondly, 15 landslide conditioning factors (LCFs) are considered and prepared from multi-data sources. Subsequently, a multicollinearity analysis is conducted to calculate the independence between different factors. Then, the Information Gain Ratio method (IGR) is performed to confirm the predictive ability of the LCFs. Finally, LSMs are constructed by, SI, WoE, LR and their combination through 12 preferred LCFs. The performance of different methods are validated and compared in term of areas under the receiver operating characteristic curve (AUC) and statistical measures. The results from this study indicate the hybrid models FR-LR, WoE-LR and SI-LR achieved higher AUC value than all corresponding single methods. The ensemble frameworks are well in line with the distribution pattern of historical landslides in the research area. Therefore, the proposed high-performance ensemble frameworks are expected to provide a useful reference for landslide hazard prevention in similar areas.

Using machine learning methods is efficient in predicting floods in areas where complete data is not available. Therefore, this study considers the Adaptive Neuro-Fuzzy Inference System (ANFIS) model combined with evolutionary algorithms, namely Harris Hawks Optimization (HHO) and Arithmetic Optimization Algorithm (AOA), to predict the flood of Shahrchay River in the northwest of Iran. The data used included the daily data of precipitation, evaporation, and runoff in the years 2016 and 2017, where 70% of the data were used for model training and the rest for testing the models. The results showed that although the ANFIS model provided values with high errors in several steps, especially in steps with maximum or minimum values, the use of HHO and AOA optimization algorithms resulted in a significant reduction in the error values. The ANFIS-AOA model utilizing an input scenario including the flow in the previous one to three days exerted the most promising results in the test data, with Nash Sutcliffe Efficiency (NSE) Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) of 0.93, 1.34, and 0.69, respectively. According to Taylor’s diagram, the ANFIS-AOA hybrid algorithm predicts flood values with greater performance than the other models. [ABSTRACT FROM AUTHOR]

Accurately predicting the potential wind power generation is of paramount importance in advancing the contribution of wind energy within the overall energy production landscape. To reduce dependence on fossil fuels, there is an urgent need to accelerate the integration of renewable energy sources, such as wind power. Moreover, ensuring a stable equilibrium between energy supply and demand hinges upon a profound understanding of the anticipated energy generation capacity. This paper presents a short-term forecasting model using data from the West of Duddon Sands, Barrow, and Horns Power sites. In pursuit of this goal, we have meticulously developed hybrid prediction models based on long short-term memory (LSTM) and bi-directional LSTM (Bi-LSTM) architectures. These models entail an initial data decomposition stage followed by the prediction phase. While some models solely incorporate the empirical mode decomposition (EMD) method for decomposition, others combine EMD with wavelet decomposition (WD) and swarm decomposition (SWD) for a more comprehensive approach. This investigation encompasses a range of models, including EMD–LSTM, EMD–WD–LSTM, EMD–SWD–LSTM, Bi-LSTM, EMD–Bi-LSTM, EMD–WD–Bi-LSTM, and EMD–SWD–Bi-LSTM. After a meticulous analysis of the outcomes generated by each model, a consistent trend emerges: the EMD–SWD–LSTM model consistently yields elevated R² values, signifying a heightened level of predictive accuracy and success [ABSTRACT FROM AUTHOR]

Cyberbullying is a serious problem in online communication. It is important to find effective ways to detect cyberbullying content to make online environments safer. In this paper, we investigated the identification of cyberbullying contents from the Bangla and Chittagonian languages, which are both low-resource languages, with the latter being an extremely low-resource language. In the study, we used both traditional baseline machine learning methods, as well as a wide suite of deep learning methods especially focusing on hybrid networks and transformer-based multilingual models. For the data, we collected over 5000 both Bangla and Chittagonian text samples from social media. Krippendorff's alpha and Cohen's kappa were used to measure the reliability of the dataset annotations. Traditional machine learning methods used in this research achieved accuracies ranging from 0.63 to 0.711, with SVM emerging as the top performer. Furthermore, employing ensemble models such as Bagging with 0.70 accuracy, Boosting with 0.69 accuracy, and Voting with 0.72 accuracy yielded promising results. In contrast, deep learning models, notably CNN, achieved accuracies ranging from 0.69 to 0.811, thus outperforming traditional ML approaches, with CNN exhibiting the highest accuracy. We also proposed a series of hybrid network-based models, including BiLSTM+GRU with an accuracy of 0.799, CNN+LSTM with 0.801 accuracy, CNN+BiLSTM with 0.78 accuracy, and CNN+GRU with 0.804 accuracy. Notably, the most complex model, (CNN+LSTM)+BiLSTM, attained an accuracy of 0.82, thus showcasing the efficacy of hybrid architectures. Furthermore, we explored transformer-based models, such as XLM-Roberta with 0.841 accuracy, Bangla BERT with 0.822 accuracy, Multilingual BERT with 0.821 accuracy, BERT with 0.82 accuracy, and Bangla ELECTRA with 0.785 accuracy, which showed significantly enhanced accuracy levels. Our analysis demonstrates that deep learning methods can be highly effective in addressing the pervasive issue of cyberbullying in several different linguistic contexts. We show that transformer models can efficiently circumvent the language dependence problem that plagues conventional transfer learning methods. Our findings suggest that hybrid approaches and transformer-based embeddings can effectively tackle the problem of cyberbullying across online platforms. [ABSTRACT FROM AUTHOR]

The greenhouse effect formed by the massive emission of carbon dioxide has caused serious harm to the Earth's environment, in which the power sector constitutes one of the primary contributors to global greenhouse gas emissions. Reducing carbon emissions from electricity plays a pivotal role in minimizing greenhouse gas emissions and mitigating the ecological, economic, and social impacts of climate change, while carbon emission prediction provides a valuable point of reference for the formulation of policies to reduce carbon emissions from electricity. The article provides a detailed review of research results on deep learning-based carbon emission prediction. Firstly, the main neural networks applied in the domain of carbon emission forecasting at home and abroad, as well as the models combining other methods and neural networks, are introduced, and the main roles of different methods, when combined with neural networks, are discussed. Secondly, neural networks were used to predict electricity carbon emissions, and the performance of different models on carbon emissions was compared. Finally, the application of neural networks in the realm of the prediction of carbon emissions is summarized, and future research directions are discussed. The article provides a reference for researchers to understand the research dynamics and development trend of deep learning in the realm of electricity carbon emission forecasting. [ABSTRACT FROM AUTHOR]

In this study, a novel hybrid framework named HVK/HVA-HEM was designed to predict river discharge with outliers. Firstly, the Hampel filter (HF) identifies and corrects outliers in the discharge series. Next, this series was denoised and decomposed using ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) respectively. The HF-VMD components were employed to K-nearest neighbor (KNN) and autoregressive integrated moving average (ARIMA) models, while the HF-EEMD series was applied to the multilayer perceptron (MLP) model to obtain the predictions of the proposed HVK(HF-VMD-KNN), HVA(HFVMD-ARIMA), and HEM(HF-EEMD-MLP) hybrid models. Lastly, using the mean absolute error (MAE) weights of HVK, HVA and HEM predictions, the HVK-HEM and HVA-HEM models were formulated. The application of the new hybrid framework was displayed using the discharge of four rivers in Pakistan. In terms of the RMSE of Kabul River, the HEM hybrid model had better performance than MLP (175.2053 m³ /s), HF-MLP (156.1853 m³ / s), EEMD-MLP (133.4049 m³ /s) and VMD-MLP (170.1337 m³ /s). Similarly, the proposed HVK and HEM hybrid models are more efficient than their respective single, HF, EEMD, and VMD-based models. Overall, the proposed HVA-HEM hybrid model outperformed all competing and proposed models. [ABSTRACT FROM AUTHOR]

This paper aims to highlight in a relevant way the interest of hybrid models (coupling of ARIMA processes and machine learning models) for economic or financial agents. These models are likely to allow better consideration of certain stylized facts (not necessarily taken into account by often-used models such as ARIMA-GARCH), observed in the analysis of financial time series. Most hybrid models assume that the random perturbation of the chosen ARIMA process follows a normal distribution. Thus, the literature on hybrid models remains on this Gaussian framework and it would be necessary to consider a non-Gaussian and much more realistic framework. We consider hybrid models with the assumption that the random disturbance process follows a Student's distribution (denoted by ARIMA T), allowing us to take into account the leptokurticity often observed when analyzing financial time series returns. Under certain assumptions, the empirical results show the power of the hybrid models considered. [ABSTRACT FROM AUTHOR]

Background and Objectives: Determining the amount of soil erosion and its spatial distribution can effectively provide appropriate management practices to reduce erosion problems. Direct measurement of soil erosion takes a lot of time and money, and the results are often regional and limited. This issue has led to the development of various models for estimating soil erosion and sediment production. Since most of the watersheds in Iran need more accurate information, models that require relatively few inputs make more sense than models with high inputs. Along with empirical and process-based models, a number of erosion estimation models are known as hybrid models. One of the hybrid models is the Thornes model, which requires relatively little input data, and there has been no research related to this model in Iran. Therefore, this study was conducted to determine spatial variation of the soil erosion rate and sediment yield in a part of the Sanandaj Gheshlagh Dam watershed using the Thornes model utilizing GIS and remote sensing (RS). Materials and Methods: Two hundred soil samples were collected using a stratified random sampling method and the parameters of soil texture, particle size distribution, organic carbon, and soil CaCO3 equivalent in the laboratory were measured by conventional methods. In order to determine the input parameters of the studied model, laboratory results, Landsat 8 satellite images over six years, and some monthly meteorological data, including precipitation, precipitation days number and potential evapotranspiration, were analyzed. Finally, using ArcMap, Saga GIS, and ENVI software, the required parameters and maps of the models were prepared, and the studied models were run. Sediment delivery ratios (SDRs) are assumed to be a function of the travel time of surface runoff from catchment cells to the nearest downstream channel. Results: The results showed that the estimated average erosion of the Thornes model was 0.76 mm per year or 10.24 tons per hectare per year (assuming a bulk density of 1.4 gr/cm3), and according to the calculated SDR, the estimated sediment was calculated by the model as 4.34 tons per hectare per year. The results of the Thornes model showed that the sensitivity of this model to some parameters, including potential evapotranspiration and potential water storage capacity, was very high. Small changes in these parameters caused a significant difference in the results, which would reduce the efficiency of the model. Conclusion: According to the field observations and the investigation of erosion and sedimentation situations in the studied watershed, as well as long-term information about sediment discharged from the hydrometric station (3.10 tons per hectare per year), it seems that the Thornes model has been a relatively reasonable estimate of erosion in many parts of the studied watershed. However, the type of model used to estimate the sediment delivery ratio and then the sediment yield can have a significant effect on the model's efficiency. Considering that this model requires relatively few data, it may be possible to use it to predict erosion in watersheds with no information or with poor information. [ABSTRACT FROM AUTHOR]

The state of New York admitted 143 million metric tons of carbon emissions from fossil fuels in 2020, prompting the ambitious goal set by the CLCPA to achieve carbon neutrality. The paper focused on analyzing and predicting carbon emissions using four different machine-learning algorithms. It examined emissions from fossil fuel combustion from 1990 to 2020 and validated four different algorithms to choose the most effective one for predicting emissions from 2020 to 2050. The analysis covered various economic sectors including transportation, residential, commercial, industrial, and electric power. By analyzing policies, the paper forecasted emissions for 2030 and 2050, leading to the identification of different pathways to reach carbon neutrality. The research concluded that in order to achieve neutrality, radical measures must be taken by the state of New York. Additionally, the paper compared the most recent data for 2021 with the forecasts, showing that significant measures need to be implemented to achieve the goal of carbon neutrality. Despite some studies assuming a trend of decreased emissions, the research revealed different results. The paper presents three pathways, two of which follow the ambitious plan to reach carbon neutrality. As a result, the emission amount by 2050 for the different pathways was projected to be 31.1, 22.4, and 111.95 of MMt CO2 e, showcasing the need for urgent action to combat climate change. [ABSTRACT FROM AUTHOR]