Abstract
The Pearl River Estuary (PRE) and Hong Kong (HK) Waters are identified as two of the most important habitats worldwide for Indo-Pacific humpback dolphin ( Sousa chinensis ). However, the extremely rapid growth of coastal cities and near-shore reclamation lands posed great threats to delicate marine ecosystems and protected species. Dredging operations can exert non-negligible negative impacts on humpback dolphins, with high sediment concentrations standing out as a particularly significant threat. This study aims to apply a new risk assessment approach based on computational fluid dynamics (CFD) and unsupervised machine learning technique for quantitatively estimating the risk of high turbidity to marine mammals. As an extension, the risk to the natural habitat in PRE was statistically compared among five possible dredging locations according to HK reclamation projects. The results showed that sediment plumes could be enlarged quickly if dredging sites are close to places with high density of macro-vortices, such as the north corner of Lantau Island. In terms of temporal effects, dredging under scenarios with northeast wind has a higher probability of posing significant risks to dolphin habitats. In accordance with this strategy, reliable suggestions on the choice of construction location or period could be provided to the decision-makers before or during the coastal projects. The proposed strategy can also be flexibly extended to any coastal environment, serving as a valuable example for coastal and environmental management.