Forecasting the strength of graphene nanoparticles-reinforced cementitious composites using ensemble learning algorithms

Results in Engineering, Год журнала: 2024, Номер 21, С. 101837 - 101837

Опубликована: Фев. 6, 2024

Contemporary infrastructure requires structural elements with enhanced mechanical strength and durability. Integrating nanomaterials into concrete is a promising solution to improve However, the intricacies of such nanoscale cementitious composites are highly complex. Traditional regression models encounter limitations in capturing these intricate compositions provide accurate reliable estimations. This study focuses on developing robust prediction for compressive (CS) graphene nanoparticle-reinforced (GrNCC) through machine learning (ML) algorithms. Three ML models, bagging regressor (BR), decision tree (DT), AdaBoost (AR), were employed predict CS based comprehensive dataset 172 experimental values. Seven input parameters, including graphite nanoparticle (GrN) diameter, water-to-cement ratio (wc), GrN content (GC), ultrasonication (US), sand (SC), curing age (CA), thickness (GT), considered. The trained 70 % data, remaining 30 data was used testing models. Statistical metrics as mean absolute error (MAE), root square (RMSE) correlation coefficient (R) assess predictive accuracy DT AR demonstrated exceptional accuracy, yielding high coefficients 0.983 0.979 training, 0.873 0.822 testing, respectively. Shapley Additive exPlanation (SHAP) analysis highlighted influential role positively impacting CS, while an increased (w/c) negatively affected CS. showcases efficacy techniques accurately predicting nanoparticle-modified concrete, offering swift cost-effective approach assessing nanomaterial impact reducing reliance time-consuming expensive experiments.

Язык: Английский

---

Explainable machine learning methods for predicting water treatment plant features under varying weather conditions

Results in Engineering, Год журнала: 2024, Номер 21, С. 101930 - 101930

Опубликована: Март 1, 2024

Accurately predicting key features in WWTPs is essential for optimizing plant performance and minimizing operational costs. This study assesses the potential of various machine learning models inflow to anoxic sludge reactors. Firstly, it conducts a comprehensive evaluation diverse models, including k-Nearest Neighbors (kNN), Random Forest (RF), XGBoost, CatBoost, LightGBM, Decision Tree Regression (DTR), flow into Anoxic section under weather conditions (dry, rainy, stormy). Secondly, introduces parsimonious guided by variable importance from XGBoost algorithm. Furthermore, employs SHAP (SHapley Additive exPlanations) elucidate model predictions, providing insights contribution each feature. Data COST Benchmark Simulation Model (BSM1) used verify investigated models' effectiveness. Each dataset consists 14 days influent data at 15-minute intervals, with 80% training. Results show that ensemble methods, particularly CatBoost demonstrate satisfactory predictive results presence increased variability rainy stormy conditions. Notably, achieve average Mean Absolute Percentage Error values 1.33% 1.59%, outperforming other methods.

Язык: Английский

---

Watershed sediment load modeling based on runoff erosion energy

Journal of Hydrology, Год журнала: 2025, Номер 652, С. 132694 - 132694

Опубликована: Янв. 13, 2025

Язык: Английский

---

A novel hybrid machine learning framework for spatio-temporal analysis of reference evapotranspiration in India

Journal of Hydrology Regional Studies, Год журнала: 2025, Номер 58, С. 102271 - 102271

Опубликована: Фев. 27, 2025

Язык: Английский

---

Advanced Prediction Models for Scouring Around Bridge Abutments: A Comparative Study of Empirical and AI Techniques

Water, Год журнала: 2024, Номер 16(21), С. 3082 - 3082

Опубликована: Окт. 28, 2024

Scouring is a major concern affecting the overall stability and safety of bridge. The current research investigated effectiveness various artificial intelligence (AI) techniques, such as neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), random forest (RF), for scouring depth prediction around bridge abutment. This study attempted to make comparative analysis between these AI models empirical equations developed by researchers. paper utilized dataset water (Y), flow velocity (V), discharge (Q), sediment particle diameter (d50) from controlled laboratory setting. An efficient optimization tool (MATLAB Optimization Tool (version R2023a)) was used develop scour estimation formula abutments. findings investigation demonstrated superior performance models, especially ANFIS model, over precisely capturing non-linear complex interactions parameters. Moreover, result sensitivity be most influencing parameters results highlight precise accurate abutment using models. However, equation (Equation 2) better with higher R-value 0.90 lower MSE value 0.0012 compared other equations. revealed that ANFIS, when combined fuzzy logic systems, produced highly ANN

Язык: Английский

---

Predicting scale deposition in oil reservoirs using machine learning optimization algorithms

Results in Engineering, Год журнала: 2024, Номер 22, С. 102263 - 102263

Опубликована: Май 14, 2024

Scale deposition, a form of formation damage, not only affects the reservoir but also damages well and equipment. This phenomenon occurs due to changes in temperature, pressure, injection incompatible salt water, leading ionic reactions. study investigated permeability reduction scale deposition examined how parameters such as pressure drop, ion concentration affect prediction accuracy. The deposits this include CaSO4, BaSO4, SrSO4. paper uses Python employ different machine-learning algorithms predict results. Each machine learning model has certain hyper-parameters that need adjustment. Failure do so will result reduced accuracy incomplete interpretation input data. support vector regression (SVR) algorithm was significantly affected by variation epsilon parameter dataset used. Therefore, before hyperparameter optimization, SVR had lowest at 0.575. After adjusting hyper-parameters, our findings show highest increase R-squared value, which 0.900, most minor growth KNN, went from 0.995 0.996. Additionally, value for K-Nearest Neighbor is Furthermore, errors were related XGBoost algorithms, while negligible Decision Tree KNN algorithms.

Язык: Английский

---

Intercomparison of sediment transport curve and novel deep learning techniques in simulating sediment transport in the Wadi Mina Basin, Algeria

Environmental Earth Sciences, Год журнала: 2025, Номер 84(2)

Опубликована: Янв. 1, 2025

Язык: Английский

---

Fusion of In-Situ and Modelled Marine Data for Enhanced Coastal Dynamics Prediction Along the Western Black Sea Coast

Journal of Marine Science and Engineering, Год журнала: 2025, Номер 13(2), С. 199 - 199

Опубликована: Янв. 22, 2025

This study explores the use of Temporal Fusion Transformers (TFTs), an AI/ML technique, to enhance prediction coastal dynamics along Western Black Sea coast. We integrate in-situ observations from five meteo-oceanographic stations with modelled geospatial marine data Copernicus Marine Service. TFTs are employed refine predictions shallow water by considering atmospheric influences, a particular focus on wave-wind correlations in regions. Atmospheric pressure and temperature treated as latitude-dependent constants, specific investigations into extreme events like freezing solar radiation-induced turbulence. Explainable AI (XAI) is exploited ensure transparent model interpretations identify key influential input variables. Data attribution strategies address missing concerns, while ensemble modelling enhances overall robustness. The models demonstrate significant improvement accuracy compared traditional methods. research provides deeper understanding atmosphere-marine interactions demonstrates efficacy Artificial intelligence (AI)/Machine Learning (ML) bridging observational gaps for informed zone management decisions, essential maritime safety

Язык: Английский

---

Modeling, evaluation and forecasting of suspended sediment load in Kal-e Shur River, Sabzevar Basin, in northeast of Iran

Applied Water Science, Год журнала: 2025, Номер 15(3)

Опубликована: Фев. 6, 2025

Язык: Английский

---

Toward Trustworthy Machine Learning for Daily Sediment Modeling in the Riverine Systems: An Integrated Framework With Enhanced Uncertainty Quantification and Interpretability

Water Resources Research, Год журнала: 2025, Номер 61(5)

Опубликована: Май 1, 2025

Abstract Accurately predicting sediment dynamics and understanding their intrinsic contributors are pivotal for sustainable environment water management. While machine learning (ML) enables precise predictions, its “black‐box” nature hinders transparency credibility, posing challenges in interpretability uncertainty quantification (UQ). To achieve trustworthy ML riverine timeseries this study proposes an integrated framework, enhancing key steps: feature selection, UQ, interpretation. Lagged hydro‐environmental variables incorporated via rigorous selection. SHapley Additive exPlanations (SHAP) conformal prediction utilized to refine respectively. Based on 41‐year multi‐source data three ensemble algorithms (LightGBM, XGBoost, random forest (RF)), models daily suspended concentration (SSC) separately seven subtropical watersheds evaluates overall local accuracy. Key findings include: (a) Discharge precipitation dominate SSC variability (explaining ∼56.8% ∼18.9% of the variability, respectively). Sampling‐day discharge accumulative lagged should be prioritized as predictors. Precipitation‐discharge interaction effects exhibit simple threshold effects, whereas hydrological (precipitation, discharge) environmental (SPEI, land cover) factors involve complex, bidirectional effects. (b) LightGBM XGBoost excel long‐term/general prediction, while RF outperform short‐term/extreme value predictions. (c) Conformal prediction‐based UQ provides probabilistic information quantify reliability efficiency, alongside sources: (∼38.9%) > (∼33.4%) cover (∼19.6%) SPEI (∼8.1%). This framework advances modeling, algorithm‐agnostic design ensures potential scalability support broader applications informed decision‐making.

Язык: Английский

---