Predictive modeling of land surface temperature (LST) based on Landsat-8 satellite data and machine learning models for sustainable development

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 444, P. 141035 - 141035

Published: Feb. 8, 2024

Language: Английский

---

Transfer learning enables prediction of steel corrosion in concrete under natural environments

Cement and Concrete Composites, Journal Year: 2024, Volume and Issue: 148, P. 105488 - 105488

Published: Feb. 24, 2024

Language: Английский

---

Utilization of tailing aggregates in cast-in-situ concrete: the enhancement in resistance to sulfate-chloride aggressive environment

Journal of Cleaner Production, Journal Year: 2025, Volume and Issue: unknown, P. 145127 - 145127

Published: Feb. 1, 2025

Language: Английский

---

Prediction of high strength ternary blended concrete containing different silica proportions using machine learning approaches

Results in Engineering, Journal Year: 2023, Volume and Issue: 17, P. 100973 - 100973

Published: Feb. 25, 2023

The most often utilized material in construction is concrete. High plasticity, good economy, safety, and exceptional durability are a few of its characteristics. Concrete type structural that needs to be strong enough withstand different loads. compressive strength the concrete members crucial mechanical characteristic because brittleness. Furthermore, with ternary blended cementitious materials sophisticated composite material. present study explores binary mixes silica fume, ceramic powder, bagasse ash, alccofine, determine flexural strength. Results compression tests show mixes, including ultra-fine have higher impact additional on surface morphology was examined using scanning electron microscopy various mixes. This investigates linear regression, KNearest Neighbors (KNN), Bayesian-optimized extreme gradient boosting estimate (BO-XGBoost). Using coefficient determination (R2), mean absolute error (MAE), square (MSE), prediction results further validated. In comparison, regression BO-XGBoost models high accuracy towards outcome as indicated by R2 value equal 0.883 0.880, respectively, while for KNN 0.736. Additionally, normalized feature importance included determining input variables significantly influenced sensitivity model indicates CaO SiO2 shows significant predict

Language: Английский

---

Optimization of waste tyre steel fiber and rubber added foam concretes using Taguchi method and artificial neural networks

Structures, Journal Year: 2024, Volume and Issue: 61, P. 106098 - 106098

Published: Feb. 29, 2024

Language: Английский

---

Exploring Cement Production's Role in GDP Using Explainable AI and Sustainability Analysis in Nepal

Case Studies in Chemical and Environmental Engineering, Journal Year: 2025, Volume and Issue: 11, P. 101128 - 101128

Published: Jan. 31, 2025

Language: Английский

---

Enhancing sediment transport predictions through machine learning-based multi-scenario regression models

Results in Engineering, Journal Year: 2023, Volume and Issue: 20, P. 101585 - 101585

Published: Nov. 14, 2023

Machine learning is one effective way of increasing the accuracy sediment transport models. captures patterns in sequence both structured and unstructured data uses it for forecasting. In this research, different regression models were train to forecast using 8 years measured collected Sg. Linggui suspended station. Data from scenarios used where each scenario indicates number lags. Seven models, namely, Linear Regression, Regression Trees, Support Vector Machines, Gaussian Process Kernel Approximation, Ensemble Neural Network trained compared. The evaluated Root Mean Square Error (RMSE) Coefficient Determination (R2). best-performing two types chosen they tested test find Relative Percentage (RPE) predicted data. Exponential model performs much better than other terms RMSE R2 values. When exponential all 3 are compared, seems have a better-performing but only by very small margin, after testing data, result shows has less RPE compared Hence, can be deduced that gaussian process overall RSME, R2, RPE.

Language: Английский

---

Efficient machine learning model to predict dynamic viscosity in phosphoric acid production

Results in Engineering, Journal Year: 2023, Volume and Issue: 18, P. 101024 - 101024

Published: March 20, 2023

The rheological behavior of the phosphoric acid slurry, during production process, strongly depends on its dynamic viscosity. Controlling this property limits P2O5 losses, minimizes energy consumption and ensures optimal flow conditions. Thus, reliable simulation tools predicting viscosity are needed for analysis process optimization. To end, three machine learning (ML) methods: single-layer artificial neural network (ANN), gradient boosting (GB) random forest (RF), were tested using 456 data at different solid content, shear rate temperature, obtained from industry. performance these models was evaluated compared diverse precision metrics. GB has shown to be outperforming model with determination coefficient greater than 99%, Root Mean Squared Error lower 0.750, both training validation datasets. Based importance explanatory variables, all agree large effect content viscosity, followed by rate, then temperature. relative partial dependence diagram made it possible deduce operating intervals pulp fed reactor, leading suspension level attack maturation units.

Language: Английский

---

Forecasting the compressive strength of GGBFS-based geopolymer concrete via ensemble predictive models

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 405, P. 133299 - 133299

Published: Sept. 16, 2023

Language: Английский

---

Local scour depth at piles group exposed to regular waves: On the assessment of expressions based on classification concepts and evolutionary algorithms

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101810 - 101810

Published: Jan. 22, 2024

An accurate estimation of local scour depth around piles group is inevitably essential to provide stability marine structures. Over the past decades, many investigations have been made understand scouring process at exposed waves for field and experimental scales. This study aims predict wave-induced by various robust Data Driven Models (DDMs) Machine Learning (MLMs) developed classification evolutionary concepts: Model Tree (MT), Evolutionary Polynomial Regression (EPR), Multivariate Adaptive Spline (MARS), Gene-Expression Programming (GEP). From relevant literature, 125 data series were employed empirical relationships predictions. The raw variables related bed sediment, pile configuration, geometry, approaching flow, wave characteristics. Non-dimensional parameters obtained through Buckingham theorem in order control depth. In this way, ratio spacing between diameter (G/D), sediment number (Ns), arrangement (ratio parallel flow; m; normal n), Shields parameter (θ), Keulegan-Carpenter (KC) considered. training testing stages Artificial Intelligence (AIMs), it was found that regression equation given MARS model provided better performance (e.g., Correlation Coefficient [R] = 0.9297, Root Mean Square Error [RMSE] 0.3489, Scatter Index [SI] 0.2765) than other AI models' efficiency. Additionally, models assessed ranges dimensionless (i.e., G/D, Ns, θ) versus KC variation. had best G/D 0–1 < 10 (R 0.9917 RMSE 0.2198) 0.4≤θ 0.5 15 25 whereas EPR promising efficiency its highest level Ns 1–3 ≤ 0.9941 0.0771) models. For sensitivity analysis, mutation rate chromosomes are examined GEP model, K-fold algebraic terms model. Furthermore, ranking analysis indicated (Ranking Performance [RPI] 0.7348) followed (0.3412), M5MT (0.2999), (0.2848).

Language: Английский

---