Numerical models of hydrodynamics and marine debris in the Malacca Strait

The Malacca Strait is a very strategic world trade route and the potential for environmental pollution is also very large, especially pollution from ship and people activities. This study aims to perform numerical simulations to determine the movement of marine debris particles around the waters of Rupat Island, Malacca Strait. The modelling was carried out from June to December 2020 using a modelling application with the basic principles of mesh discretization and the Lagrangian method. The results showed maximum current velocity during the simulation around the distribution area of debris is a maximum of 0.92 m/s. Marine debris around the waters of Rupat Island, the Malacca Strait has the potential to be stranded on the mainland of Rupat Island, mainland Riau, Bengkalis Island and also mainland Malaysia.

Bayesian Neural Network-based Uncertainty Modelling: Application to Soil Compressibility and Undrained Shear Strength Prediction

This study adopts the Bayesian neural network (BNN) integrated with a strong non-linear fitting capability and uncertainty, which has not previously been used in geotechnical engineering, to propose a modelling strategy in developing prediction models for soil properties. The compression index Cc and undrained shear strength su of clays are selected as examples. Variational inference (VI) and Monte Carlo dropout (MCD), two theoretical frameworks for solving and approximating BNN, respectively, are employed and compared. The results indicate that the BNN focuses on identifying patterns in datasets, and the predicted Cc and su show excellent agreement with the actual values. The reliability of the predicted results using BNN is high in the area of dense datasets. In contrast, the BNN demonstrates low reliability in the predicted result in the area of sparse datasets. Additionally, a novel parametric analysis method in combination with the cumulative distribution function is proposed. The analysis results indicate that BNN-based models are capable of capturing the relationships of input parameters to the Cc and su. BNN, with its strong prediction capability and reliable evaluation, therefore shows great potential to be applied in geotechnical design.