Search Results (1,576)

Accurate prediction of wastewater influent quality is critical for optimizing treatment plant operations, minimizing environmental impact, and enabling proactive management under dynamic conditions. However, the complex, nonlinear, and temporally dependent nature of influent processes poses significant challenges to traditional modeling approaches. This study introduces a robust stacked ensemble learning framework that integrates Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) to forecast three key influent quality parameters: biochemical oxygen demand (BOD₅), total phosphorus (TP), and total solids (TS) at a municipal wastewater treatment plant (WWTP) in Canada. Through sequential backward feature selection and SHapley Additive exPlanations (SHAP), the model achieves both high predictive accuracy and interpretability, providing insights into temporal, environmental, and process-based drivers of influent variability. The ensemble consistently outperforms individual models, delivering high generalization performance across all three influent quality targets. This work demonstrates that stacked ensemble models, when coupled with explainable AI techniques, can bridge the gap between black-box performance and operational transparency in wastewater forecasting. The proposed framework lays the groundwork for more resilient, data-driven decision-making in municipal WWTPs. Full article

Optimizing fertilizer management is crucial for increasing crop yields while reducing environmental impact. However, traditional methods rely on extensive field trials, which are costly and limit their scalability. To overcome these limitations, this study developed data-driven yield prediction models (YPM) for wheat, rice, and maize by integrating multiple feature selection and machine learning algorithms with explainable ensemble learning, namely stacking regression (SR) and voting mean (VM). The optimal YPM was subsequently combined with the hybrid optimization strategy to construct an intelligent fertilization decision model (IFDM), and the economic–environmental benefits were subsequently evaluated. The best-performing models were SHAP-SR for wheat and rice and GBM-SR for maize, achieving R² values of 0.79, 0.69, and 0.67, and RMSEs of 681.69, 725.35, and 1091.49 kg ha⁻¹, respectively. Based on the IFDM, the recommended application ranges for nitrogen (N), phosphorus (P₂O₅), and potassium (K₂O) were as follows: for wheat, 122.1–256.3, 45.4–98.2, and 30.6–60.7 kg ha⁻¹; for rice, 170.8–261.2, 55.1–91.4, and 40.6–98.5 kg ha⁻¹; and for maize, 157.5–293.4, 84.2–156.4, and 30.1–62.7 kg ha⁻¹. Simulation-based evaluation suggested that adopting these recommendations could potentially increase average yields by 9.2–12.4% and enhance economic–environmental benefits by 32.86–97.73% across the three crops. This study indicates that coupling interpretable ensemble learning with a hybrid optimization strategy can support efficient decision-making for field-scale fertilization and provides a data-driven and cost-effective approach for precision fertilization, with potential applicability to arid agricultural regions under similar agro-ecological conditions. Full article

Biochar production from lignocellulosic waste represents a sustainable route for biomass valorization and carbon management within circular bioeconomy frameworks. In this study, biochar was produced from two abundant agricultural wastes in Türkiye—tea-brewing residues and almond husks—via controlled non-isothermal pyrolysis, and biochar yield was modeled using data-driven machine learning approaches. The effects of key process parameters, including carbonization temperature (37–850 °C covering drying/pre-pyrolysis and pyrolysis regions), residence time (1–150 min), and heating rate (10–60 °C min⁻¹), were evaluated using regression-based, ensemble, and deep learning models. Model performance was evaluated using cross-validation on training and testing datasets. The results showed that linear models exhibited limited predictive capability (R² < 0.95), while regularized and ensemble models improved performance (R² ≈ 0.97–0.99). Among all approaches, Gaussian Process Regression (GPR) achieved the highest predictive performance (R² ≈ 0.99, RMSE ≈ 0.06), indicating its superior ability to capture nonlinear relationships, particularly for limited datasets. Sensitivity and partial dependence analyses identified carbonization temperature as the dominant factor controlling biochar yield, with sharp declines observed above 600 °C. Optimal yields of 52–55% were obtained at 400–500 °C and residence times of 10–15 min, while lower heating rates enhanced yield stability. Overall, the results demonstrate that advanced machine learning models provide reliable tools for optimizing biochar production and supporting sustainable thermochemical conversion of lignocellulosic waste for energy and carbon-oriented sustainability applications. Full article

This study investigates the prediction of carbon emissions from fly ash and ground granulated blast furnace slag-based geopolymer concrete (GPC) using advanced ensemble machine learning (ML) techniques. Although ML has been extensively utilized to model GPC’s mechanical performance, its application in estimating environmental impacts, specifically carbon emissions, is limited. The research employs six ensemble ML models, such as random forest, gradient boosting, extreme gradient boosting (XGB), CatBoost, and light gradient boosting machine (LGBM), including versions optimized using ant colony optimization (ACO). Among them, the ACO-enhanced XGB model demonstrated the highest predictive accuracy with a coefficient of determination (R²) of 0.97, with low prediction errors (MAE = 3.92, RMSE = 6.17). However, cross-validation and uncertainty analyses indicate that the performance differences among top models are relatively small. Conversely, LGBM exhibited the least predictive reliability. Feature importance analysis revealed that curing parameters, specifically initial curing time, curing temperature, and the dosage of dry sodium hydroxide, had the most influence on carbon emissions. To evaluate model robustness and interpretability, Monte Carlo simulation and Gaussian white noise analyses were conducted. Results confirmed that CatBoost and ACO–gradient boosting (ACO-GB) demonstrated greater stability under varying and noisy conditions, whereas XGB-based models, although highly accurate, were comparatively more sensitive to input variability. Overall, the research establishes a data-driven, efficient framework for quantifying carbon emissions in GPC, highlighting the importance of evaluating both predictive accuracy and model robustness, advancing sustainable material design through intelligent modelling. Full article

Wastewater membrane bioreactors (MBRs) have become an important advanced treatment technology due to their ability to produce high-quality effluent suitable for discharge and water reuse. However, their broader and more sustainable application remains constrained by membrane fouling, elevated energy demand, and the operational complexity of coupled biological and membrane separation processes. This comprehensive review critically evaluates the growing application of machine learning (ML), explainable artificial intelligence (XAI), and digital twin (DT) technologies in MBR systems. Published studies on fouling prediction, energy optimization, effluent quality estimation, and intelligent operational support are critically evaluated, with explicit attention to model performance, dataset limitations, and generalizability. The reviewed literature shows that ML models, particularly ensemble methods, support vector machines, and deep learning approaches, have demonstrated strong potential for predicting major MBR performance indicators, including transmembrane pressure, permeate flux, fouling resistance, and selected effluent-quality variables. In parallel, XAI methods such as SHAP, LIME, and Anchors are increasingly being used to enhance model transparency and to reveal the dominant factors controlling process performance. Digital twin frameworks further extend this potential by enabling the integration of mechanistic understanding, online sensor data, data-driven prediction, and interpretable decision support within real-time operational platforms. Nevertheless, several barriers continue to hinder practical implementation, including the limited number of full-scale studies, the scarcity of openly accessible and standardized datasets, insufficient consideration of uncertainty and model drift, and the early-stage maturity of DT deployment in operational plants. The evidence reviewed suggests that integrating ML, XAI, and DT can substantially improve the reliability, interpretability, and operational efficiency of MBR systems. Future research should therefore focus on full-scale validation, the development of benchmark datasets, uncertainty-aware modeling, and practical deployment strategies for interpretable intelligent MBR management. Full article

In semi-supervised learning scenarios, the presence of limited labeled data and abundant unlabeled samples poses significant challenges to model robustness and generalization. Although the semi-supervised broad learning system (SSBLS) effectively exploits manifold structure through graph Laplacian regularization, its optimization is typically formulated under the mean square error (MSE) criterion, which is sensitive to noise and outliers. To address this limitation, this paper introduces the maximum mixture correntropy criterion (MMC) into the SSBLS framework and proposes a model termed M2C-SSBLS. By replacing the conventional MSE loss with a mixture correntropy-based objective, the proposed method enhances robustness against non-Gaussian noise and abnormal samples while preserving the computational efficiency and analytical solution property of the BLS. Furthermore, to improve representation diversity and reduce model variance, a multi-view ensemble extension, named EC-SSBLS, is proposed. This method constructs multiple feature views through a random feature subspace strategy, and independently trains an M2C-SSBLS base learner on each subspace. Finally, the predicted results of each view are fused through a voting mechanism. Experiments on benchmark UCI datasets under noise-free, 10% and 20% label noise settings demonstrate that the proposed M2C-SSBLS consistently outperforms conventional SSBLS and other advanced semi-supervised learning approaches. The ensemble extension EC-SSBLS further enhances performance, particularly in noisy environments, validating the effectiveness of combining MMC-based optimization with multi-view ensemble learning. Full article

Robust exercise recognition is essential for robot-assisted lower-limb rehabilitation, where misclassifications of sensor-derived movements can degrade therapy execution and supervision. This study proposes a novel hybrid weighted stacking ensemble to increase the efficiency of the intelligent module of the LegUp parallel robotic system for lower limb rehabilitation. The approach combines a Residual Multilayer Perceptron (ResMLP) and an optimized Kernel Extreme Learning Machine (KELM), where model hyperparameters are tuned using Optuna and the base-model probability outputs are fused through optimized weighting and a meta-learner. Experiments were conducted on a five-class dataset built from nine IMU orientation features acquired from three sensors placed on the healthy limb. Four meta-learners were evaluated (Logistic Regression, Random Forest, Gradient Boosting, and AdaBoost), with AdaBoost providing the best overall performance. To further assess the robustness and generalization capability of the proposed approach, a 5-fold cross-validation procedure was performed for the ResMLP, KELM, and the hybrid ensemble models. The proposed stacking hybrid ensemble consistently surpassed the performance of the strongest individual classifiers as well as the original LegUp Multilayer Perceptron model. These results indicate that combining residual learning with kernel-based classification in a weighted stacking framework yields a stable and high-performing solution for multi-class rehabilitation exercise recognition. Full article

Concrete compressive strength is critical to structural safety, durability, and material cost. Conventional machine learning models are often limited in capturing complex nonlinear dependencies and generalizing. To address this, a residual fusion framework is proposed that combines a least squares support vector machine (LSSVM) optimized by DE with multi-level residual structure bagged decision trees (TreeBagger) and least squares boosting (LSBoost). DE-tuned LSSVM hyperparameters are followed by a multi-level residual scheme that compensates errors layer by layer, with LSBoost performing adaptive nonlinear fusion. Experiments under varied splits, ablation, and multiple seeds show the model outperforms traditional single and ensemble methods in accuracy, generalization, and stability. The ablation attributes the improvements to complementary residual mechanisms and the fusion architecture, rather than simply adding learners. Across multiple runs, an average coefficient of determination (R²) of 0.9490, a mean absolute error (MAE) of 3.7873 MPa, a root mean square error (RMSE) of 2.4998 MPa, and an R² standard deviation of 0.0029 were obtained, confirming stability. Shapley additive explanations (SHAP) analysis further reveals that age and water–cement parameters dominate, with patterns consistent with hydration and water–binder theory. The proposed framework thus offers high accuracy, physical interpretability, and engineering applicability. Full article

The development of renewable energy is vital for addressing future climate change and environmental degradation. Nevertheless, the irregular and fluctuating essential features of wind power presents a considerable barrier to grid operational stability. Hence, precise prediction of wind energy output is crucial for improving power system management, boosting the reliability of the supply, and minimizing reserve expenditure. This study presents a predictive model designed for predicting short-term wind speeds using a stacking ensemble approach, which is based on an enhanced Multi-Feature Zebra Optimization Algorithm (IZOA-Stacking). In the data preprocessing phase, to minimize computational costs and prevent overfitting, a module tailored to the various features affecting wind power is developed for the IZOA-Stacking model. Grey relational analysis and Pearson correlation analysis are employed to determine and filter feature correlations. Critically, the preprocessing module demonstrates strong robustness: the One-Class Support Vector Machine (OneSVM) model is applied to identify and replace 100% of anomalous wind speed data, which leads to a substantial and measurable increase in feature correlation and overall model performance. For instance, when retaining wind speed features, the One-Class Support Vector Machine (OneSVM) model is employed to eliminate anomalous wind speed data. During model construction, a stacking ensemble learning strategy integrates multiple prediction models, including Long Short-Term Memory (LSTM) net-works, Extreme Gradient Boosting (XGBoost), ridge regression (RR), and Residual Networks (ResNets). This integration leverages the predictive strengths of each model. Additionally, the improved Zebra Optimization Algorithm (ZOA) optimizes the hyperparameters of each constituent model, further enhancing forecasting accuracy. The findings suggest that the proposed model demonstrates better performance than reference competitor models with regard to predictive accuracy. Full article

Accurate estimation of tree Above-Ground Biomass (AGB) is critical for the timely monitoring of forest dynamics. However, the scarcity of high-quality in situ measured data introduces considerable uncertainty into the precise spatial mapping of AGB. In this study, a novel method for AGB mapping is proposed to enhance the accuracy of AGB estimation based on the Semi-Supervised Ensemble Learning (SSEL) strategy. By expanding the sample set via an iterative self-training approach based on an Inverted Query-by-Committee (I-QBC) strategy, the model significantly enhances the accuracy of AGB estimation. Using Sentinel-2 data, the experimental results show that: (1) The I-QBC-driven SSEL model demonstrated significantly higher estimation accuracy for AGB compared to conventional tree-based ensemble models. Optimal stability (${\mathrm{R}}^2$ = 0.80) and peak accuracy (${\mathrm{R}}^2$ = 0.88) were achieved at sample increments of 20 and 30, respectively. (2) Among various feature types, Recursive Feature Elimination with Cross-Validation (RFECV) identified GNDVI, PSSRa, slope and texture correlation as the most critical predictors for AGB estimation in the study area. (3) The total AGB stock in the study area is estimated to range from 1.46 × 10⁷ Mg to 1.71 × 10⁷ Mg. The SSEL model provides a valuable reference for AGB estimation under sparse ground-truth sample conditions, while offering a novel approach for large-scale AGB mapping. Full article

Late deliveries represent one of the most persistent operational disruptions in global supply chains, eroding service reliability, triggering contractual penalties, and undermining the resilience of logistics networks. As supply chains become increasingly digitalized, the integration of advanced predictive analytics into operational decision-making offers a pathway toward proactive rather than reactive disruption management. This study develops and evaluates a digital analytics framework in which eXtreme Gradient Boosting (XGB), a high-performance ensemble learning algorithm, is optimized by three recent population-based metaheuristic algorithms: the weighted mean of vectors algorithm (INFO), Harris Hawks Optimization (HHO), and the Red-Billed Blue Magpie Optimizer (RBMO). Four critical XGB hyperparameters, number of estimators, maximum tree depth, learning rate, and complexity penalty, are tuned on a supply chain dataset. A population-size sensitivity analysis at two swarm configurations reveals that all three optimizers converge to functionally equivalent solutions at sufficient population diversity, providing practical guidance for computational resource allocation. The best-performing configuration, HHO-XGB, achieves a test accuracy of 97.47% and a Matthews correlation coefficient of 0.949, substantially outperforming the baseline XGB and other benchmark classifiers. To ensure transparency and support data-driven decision-making, SHapley Additive exPlanations (SHAP) analysis is applied to the optimized model, revealing that shipping mode, scheduled shipment days, shipping date, order day, order status, and order month are the dominant predictive features, confirming that late-delivery risk is primarily driven by shipment configuration and temporal patterns. The proposed framework demonstrates that integrating metaheuristic intelligence with machine learning delivers better predictive performance. Interpretability is essential to trustworthy, resilient supply chain decision-support systems. Full article

Polymer-based product use is rapidly increasing worldwide, resulting in critical social, environmental, ecological, economic, and health effects. Worldwide efforts have increasingly focused on solutions to the equilibrium consumption, production, and disposal of plastics to tackle these issues. The frontiers of biodegradable and bio-based polymers are continually advancing in pursuit of sustainability. Therefore, designing ecological bioplastics made of both biodegradable and bio-based polymers reveals chances to overcome plastic pollution and resource depletion. Polymeric materials are mainly used to manufacture different products at the beginning of their lifespans and which become waste after usage. Numerous sustainability strategies and polymer recycling methods are described and mostly classified into chemical, mechanical, and thermal recycling processes. This manuscript presents a New Polymers Frontier in Recycling and Sustainability Using an Ensemble of Deep Learning with a Heuristic Search Algorithm (NPFRS-EDLHSA). This work is devoted to computational polymer typology, which is based on machine learning algorithms applied to data on physicochemical properties. Although polymer classification can facilitate downstream materials research, the present study does not directly simulate recycling, environmental impacts, or sustainability. The main contributions made by this work include (i) an exploratory analysis of ensemble deep learning models to classify polymers by type on a small and unbalanced dataset; (ii) an evaluation of the effect of feature selection with a heuristic optimization methodology; and (iii) a comparison of the effects on classification performance under limited data conditions. This research sets out to provide a methodological explanation, not arguments for industrial-scale applicability. For the polymer-type classification process, the proposed NPFRS-EDLHSA model designs an ensemble of deep learning techniques, namely a bidirectional recurrent neural network (BiRNN) model, a bidirectional gated recurrent unit (BiGRU) method, and a graph autoencoder (GAE) technique. Finally, the grasshopper optimization algorithm (GOA) adjusts the hyperparameter values of the ensemble models optimally and results in an improved classification performance. A wide-ranging set of experiments was conducted to validate the performance of the NPFRS-EDLHSA method. The experimental results indicated that the NPFRS-EDLHSA technique achieved a better performance than an existing model. Full article

Real-world time series forecasting is often challenging due to non-stationarity and distribution shifts, where the optimal forecasting model varies across different temporal regimes and horizons. In this work, we introduce a method called Adaptive Future-Guided Ensemble Learning (AFG-EL), a two-stage framework that performs drift-aware, sample-level routing over a heterogeneous model zoo. AFG-EL learns dynamic fusion weights from meta-features of the historical window and incorporates a future-guided training signal from a relative-future teacher or scorer, emphasizing learning on regime transitions and drift-sensitive segments. Crucially, the inference process remains strictly causal, requiring only historical data and extracted meta-features. We further use sparse routing with an entropy-based fallback mechanism to enhance stability when routing confidence is low. Our experiments on several commonly used forecasting datasets demonstrate that AFG-EL consistently outperforms strong single-model baselines, uniform averaging, and adaptive fusion baselines. Full article

Accurate in-season rice (Oryza sativa L.) yield prediction is crucial for improved nitrogen management and climate-smart decision making, yet rigorous comparative benchmarking of machine learning (ML) models using multi-temporal UAV spectral data with independent temporal validation remains limited. This study systematically evaluated four ML algorithms (Random Forest, XGBoost, Neural Network, and Linear Regression) and two Bayesian model averaging ensembles for rice yield prediction using UAV multispectral imagery. Field experiments spanning three growing seasons (2023–2025) at Louisiana State University comprised 9–10 varieties and six nitrogen rates (0–235 kg N ha⁻¹; 576 plots). Vegetation indices and spectral bands from three growth stages were extracted as predictors. Models were compared using 300 random train–test iterations with systematic hyperparameter optimization, followed by independent validation on 2025 data. Among the individual models, XGBoost achieved the highest internal accuracy (R² = 0.87, RMSE = 0.85 t ha⁻¹), substantially outperforming Linear Regression (R² = 0.66, RMSE = 1.32 t ha⁻¹), while reduced BMA reached R² = 0.89. XGBoost demonstrated robust temporal generalization (R² = 0.62, NRMSE = 8.47%) despite environmental variation. The Enhanced Vegetation Index and Normalized Difference Red Edge at 90 days after planting (reproductive stage) were the most stable predictors across 300 iterations. Tree-based ML models substantially outperform traditional linear approaches, providing reliable pre-harvest yield forecasting for operational precision rice production. Full article

Background/Objectives: Poly(lactic-co-glycolic acid) (PLGA) microspheres are widely used in long-acting injectable (LAI) formulations because PLGA exhibits well-established biocompatibility and undergoes controlled hydrolytic degradation into metabolizable byproducts. However, optimization of microspheres typically requires time-consuming in vitro testing. Therefore, we developed a predictive machine learning model for early-stage and full time-dependent release profiles of drug-loaded PLGA microspheres. Methods: Using a published dataset comprising 321 release profiles from 89 drugs, we first developed a classification model to identify slow-release behavior (≤20% release within 3 days) and subsequently integrated the predicted early-release probability into a regression model to estimate cumulative release over time. Results: Among tree-based ensemble models, XGBoost achieved the lowest mean absolute error (MAE = 0.126) and highest Pearson correlation coefficient (r = 0.831). SHapley Additive exPlanations (SHAP) analysis revealed that drug and polymer molecular weight, predictive slow-release probability, and polymer concentration substantially influence release behavior. We also assessed this framework with external datasets. Drug release data for olaparib-loaded PLGA microspheres were obtained in-house, whereas those for semaglutide-based microspheres were obtained from the published literature. In both datasets, this framework demonstrated low MAE values (0.096 and 0.068, respectively). Conclusions: This suggests that the proposed framework can predict in vitro drug release and support efficient optimization of PLGA-based LAI formulations. Full article