| 1. |
- Javed, Muhammad Faisal, et al.
(författare)
-
Evaluation of machine learning models for predicting TiO2 photocatalytic degradation of air contaminants
- 2024
-
Ingår i: Scientific Reports. - : Nature Research. - 2045-2322. ; 14:1
-
Tidskriftsartikel (refereegranskat)abstract
- The escalation of global urbanization and industrial expansion has resulted in an increase in the emission of harmful substances into the atmosphere. Evaluating the effectiveness of titanium dioxide (TiO2) in photocatalytic degradation through traditional methods is resource-intensive and complex due to the detailed photocatalyst structures and the wide range of contaminants. Therefore in this study, recent advancements in machine learning (ML) are used to offer data-driven approach using thirteen machine learning techniques namely XG Boost (XGB), decision tree (DT), lasso Regression (LR2), support vector regression (SVR), adaBoost (AB), voting Regressor (VR), CatBoost (CB), K-Nearest Neighbors (KNN), gradient boost (GB), random Forest (RF), artificial neural network (ANN), ridge regression (RR), linear regression (LR1) to address the problem of estimation of TiO2 photocatalytic degradation rate of air contaminants. The models are developed using literature data and different methodical tools are used to evaluate the developed ML models. XGB, DT and LR2 models have high R2 values of 0.93, 0.926 and 0.926 in training and 0.936, 0.924 and 0.924 in test phase. While ANN, RR and LR models have lowest R2 values of 0.70, 0.56 and 0.40 in training and 0.62, 0.63 and 0.31 in test phase respectively. XGB, DT and LR2 have low MAE and RMSE values of 0.450 min-1/cm2, 0.494 min-1/cm2 and 0.49 min-1/cm2 for RMSE and 0.263 min-1/cm2, 0.285 min-1/cm2 and 0.29 min-1/cm2 for MAE in test stage. XGB, DT, and LR2 have 93% percent errors within 20% error range in training phase. XGB has 92% and DT, and LR2 have 94% errors with 20% range in test phase. XGB, DT, LR2 models remained the highest performing models and XGB is the most robust and effective in predictions. Feature importances reveal the role of input parameters in prediction made by developed ML models. Dosage, humidity, UV light intensity remain important experimental factors. This study will impact positively in providing efficient models to estimate photocatalytic degradation rate of air contaminants using TiO2.
|
|
| 2. |
- Khan, Inamullah, et al.
(författare)
-
Engineering Characteristics of SBS/Nano-Silica-Modified Hot Mix Asphalt Mixtures and Modeling Techniques for Rutting
- 2023
-
Ingår i: Buildings. - : MDPI. - 2075-5309. ; 13:9
-
Tidskriftsartikel (refereegranskat)abstract
- Flexible pavements are mostly affected by meteorological factors in addition to traffic loads, which results in premature pavement failures like rutting and moisture-induced damage. This study focuses on the impacts of adding various contents of nano-silica (NS), i.e., 2%, 4%, 6%, and 8% (percentage weight of asphalt), along with a constant value of 4.5% styrene-butadiene-styrene (SBS). To assess the effectiveness of modified and unmodified mixtures, the indirect tensile strength (ITS) test, resilient modulus (MR) test, and wheel tracking test were conducted. The MR test was performed at dual temperature values, i.e., 25 °C and 40 °C, and demonstrated different metrological conditions in this region. The tensile strength ratio was used to estimate the mitigation of water losses in hot mix asphalt (HMA) mixtures (specimens) utilizing ITS test results of the conditioned and unconditioned specimens. Moreover, a model was developed for the rutting potential of the modified specimens using multi expression programming (MEP), a sophisticated technique that employs experimental data and suggests an equation for different input variables. The results indicated that the addition of NS to SBS-modified bitumen enhanced different mechanical properties of the specimens, including the stiffness and moisture and rutting resistances. The temperature had adverse effects on the stiffness of the specimens, while the modifiers had a direct relationship with the stiffness. The two-way factorial method justified the effect of the temperature and modifiers on MR with 95% precision, while the MEP model for rutting showed an R2 value of >0.95, which revealed a good relationship between the experimental and predicted data. Furthermore, NS and SBS had a good impact on the mechanical properties of the HMA specimens.
|
|
