Conventional methods of estimating pressure coefficients of buildings retain time and cost constraints. Recently, machine learning (ML) has been successfully established to predict wind pressure coefficients. However, regardless of the accuracy, ML models are incompetent in providing end-users’ confidence as a result of the black-box nature of predictions. In this study, we employed tree-based regression models (Decision Tree, XGBoost, Extra-tree, LightGBM) to predict surface-averaged mean pressure coefficient (C_p,mean), fluctuation pressure coefficient (C_p,rms), and peak pressure coefficient (C_p,peak) of low-rise gable-roofed buildings. The accuracy of models was verified using Tokyo Polytechnic University (TPU) wind tunnel data. Subsequently, we used Shapley Additive Explanations (SHAP) to explain the black-box nature of the ML predictions. The comparison revealed that tree-based models are efficient and accurate in wind-predicting pressure coefficients. Interestingly, SHAP provided human-comprehensible explanations for the interaction of variables, the importance of features towards the outcome, and the underlying reasoning behind the predictions. Moreover, SHAP confirmed that tree-based predictions adhere to the flow physics of wind engineering, advancing the fidelity of ML-based predictions.

Green curb was introduced to be an alternative material for a traditional road curb. This green curb is having a different concrete mix but the dimension and other requirement with respect to JKR requirement is still the same. The coarse aggregate will be replaced with crumb rubber (CR) that was extracted from vehicle tires after been shredded to the specified size from 15-20 mm as coarse aggregate. Testing such as slump test, compressive strength test and rebound hammer test was conducted to obtain the results. From the results, the slump test shows a high workability and decrease in compressive strength as the percentage of CR increase. The total weight of road curb is reduced by almost 8% compared to the control specimen. This 20% CR mixtures shows good result among other mixtures. The percentage of CR used are 20%, this particular percentage has good workability, satisfy the concrete grade 25 as required by JKR guideline (JKR/SPJ/1988).

Oil and water separation due to gravitation is extensively applied in water and wastewater treatment to get rid of the oil droplets. Optimum inlet baffle configuration may facilitate the formation of favorable flow fields and heighten the separator tank’s removal efficiency. Experimental tests were carried out to ascertain appropriate position for an inlet baffle in a rectangular separator tank. There are four parts in the experimental measurements. First of all, measured velocity fields make use of an acoustic Doppler velocimeter. Second of all, the uniformity of flow is measured by drawing a comparison of the standard deviation of the velocity profile. The oil concentration at both inlet and outlet points was later on assessed. Finally, the separation tank’s removal efficiency was evaluated. The results provide an indication that a uniform flow pattern improved when the inlet baffle position gave a minimum standard deviation value. In this case, the minimum concentration of oil at the outlet and the highest removal efficiency have been obtained.