The Hong Kong-Zhuhai-Macau Bridge crosses the Pearl River Estuary and is the largest bridge and tunnel project in the world. During the construction period of this project, the excessive suspended sediment was found in the construction region. The suspended sediment generated by sand excavation in the upstream was assumed to have a significant impact on the suspended sediment in the tunnel region. In this study, we assessed the impact of upstream sand excavation on the suspended sediment in the Hong Kong-Zhuhai-Macau Bridge construction area using Landsat OLI, ETM+, and TM data. Regional suspended sediment algorithms were developed for Landsat using a symbolic regression method based on data from in situ measurements in the study area from 2003 to 2014. A band shift was conducted on the remote sensing reflectance data from Landsat ETM+ and OLI to produce a time series of the suspended sediment concentrations that was internally consistent with that of the Landsat TM data. The suspended sediment distribution was extracted and used to compare under two different conditions, with and without sand excavation. The correlations of the time series of the suspended sediment concentrations in different regions in the surrounding waters, including the correlations between the construction regions and the sand excavation regions, were calculated. Our results indicated that the sand excavation north of the Pearl River Estuary had a limited impact on the surface suspended sediment concentrations in the Hong Kong-Zhuhai-Macau Bridge tunnel area.

Sea surface temperature (SST) is important for marine environment, and the variation of SST in the North Indian Ocean (NIO) might influence the climate in the local and surrounding area significantly. The empirical orthogonal function (EOF) was used to analyze the spatiotemporal variation characteristics of SST in the NIO. Simultaneously, seven hydrometeorological elements, including 10-m zonal wind (U10), 10-m meridional wind (V10), SST, 2-m dew-point temperature (D2M), 2-m air temperature (T2M), mean sea level pressure (MSLP), and total cloud cover (TCC), were selected as input factors to construct a daily SST forecast model based on deep learning method with convolutional neural networks (CNN). A linear and unsaturated Relu function was used in this model as activation function, which could overcome vanishing gradients and accelerate training speed. The results indicate that the annual mean SST in the NIO exhibits an increasing trend from 1980 to 2021 with a spatial gradual increase from northwest to southeast. The EOF analysis shows that the first mode contributes 28.4% of the variance, exhibiting a basin-wide uniform warming pattern over the Indian Ocean. Contribution of the second mode is 10.1%, displaying the characteristic zonal dipole pattern of the Indian Ocean Dipole (IOD). Additionally, the SST in the NIO is positively correlated with D2M, T2M, and TCC, while exhibits a negative correlation with MSLP. The correlations with U10 and V10 exhibit significant spatial variability. The constructed SST forecast model has a small prediction error, which is basically stable between ±1°C, and does not exceed 0.5°C in most of the NIO. In spite that the overall prediction error increases with the increase of prediction days, the increase of error is smooth, indicating that the forecast model has a good stability. The SST prediction results preserved the contour and distribution characteristics of the actual images holistically, and the spatiotemporal variation patterns are identical to those of the NIO.