Search

• Spectral features related to Fe and OC held potentials in estimating sediment heavy metals. • XGBoost model provided good accuracy in estimating sediment heavy metals. • The integration of CWT and RFE method was recommended for heavy metal estimation. • The samples with high Fe concentration were suitable to estimate sediment heavy metals. • A model transferability index was developed to quantitatively compare the model transferability. Soil or sediment spectral reflectance do not directly reflect information of spectrally featureless heavy metals. With mangrove sediment samples collected in five regions and four habitat types, this study aimed to explore the spectral features related to spectrally active constituents (Fe and organic carbon (OC)) in estimating low and moderate concentrations of four heavy metals (Cr, Ni, Cu and Pb). A total of 27 modeling strategies using XGBoost (extreme gradient boosting) model were compared for estimating each heavy metal: three types of spectral features (Fe, OC and heavy metal) * three spectral transformation methods (Log(1/R), first derivative (FD) and continuous wavelet transform (CWT)) * three variable selection methods (genetic algorithm (GA), successive projection algorithm (SPA) and recursive feature elimination (RFE)). The results showed that the combination of CWT and RFE was recommended for heavy metal estimation, and the ranking of model accuracy was Cu > Pb > Ni > Cr. The optimal XGBoost model was found using spectral features related to Fe for Cr (R Val 2 (determination coefficient of independent validation) = 0.42, RMSE (root mean square error) = 0.32 and RPIQ (the ratio of performance to interquartile range) = 1.53) and Cu estimation (R Val 2 = 0.87, RMSE = 0.19 and RPIQ = 2.20), spectral features related to OC for Ni estimation (R Val 2 = 0.63, RMSE = 0.26 and RPIQ = 2.38) and spectral features related to Pb itself for Pb estimation (R Val 2 = 0.82, RMSE = 0.23 and RPIQ = 2.59). Moreover, the XGBoost model transferability across different habitat types outperformed that across different regions and data ranges of Fe and OC. We conclude that the modeling strategy using spectral features related to spectrally active constituents has great potentials in quantifying low and moderate concentration of sediment heavy metals, and the samples with high Fe concentration (31.62–37.29 g kg−1) are recommended to improve estimation accuracy of low and moderate concentrations of heavy metals, which could provide sampling strategy development and early warning of heavy metal pollution in mangrove ecosystem. [ABSTRACT FROM AUTHOR]

[Display omitted] • The growth of exotic mangrove was significantly faster than that of native species. • The morphological patterns can be used to indicate the hotspots of mangroves. • Sonneratia species was found in the forest gap and forest edge of native mangroves. • The spread of Sonneratia species is fast in bare tidal flat and tidal creek zones. • Invasive potentials of Sonneratia mangrove in Shenzhen Bay should not be ignored. Mangroves are essential forest communities in tropical and subtropical coastal zones, providing unique ecological functions and significant social and economic value. Accurate and efficient monitoring of mangroves is crucial for their protection and management. The impact of exotic species on native species is still debated, especially for mangroves, the spatiotemporal dynamics of introduced species and native mangrove species need to be closely monitored. This study aimed to investigate how exotic mangrove species affects the spatial dynamics of mangroves in Shenzhen Bay, China. Yearly Landsat images from 2000 to 2011 and Chinese high spatial resolution images during 2012–2022 were obtained and the pixel-based and multiscale object-based methods were used to obtain mangrove distribution. The results showed that: (1) Overall, mangroves in the study area increased from 281.51 ha to 526.43 ha from 2000 to 2022, with different spatiotemporal patterns in Shenzhen (+5.14%) and Hong Kong (+2.38%); (2) rapid spread of Sonneratia species was one of the main contributions to the growth of mangrove hotspots, and growth hotspots were mainly concentrated in the estuary delta; and (3) Sonneratia mangrove species was dominant in interspecific competition, not only invading the habitat of local mangroves, but also preventing the expansion of native mangrove growth. The results provide a reference for fine-scale and accurate mangrove mapping with high spatial and temporal resolutions, and highlight the need to pay more attentions to the spread and invasive potential of exotic mangrove species in the study area, as well as cooperation in adjacent reserves. [ABSTRACT FROM AUTHOR]

[Display omitted] • Single and composite heavy metal pollution indices of mangrove sediment were explored. • Four types of spectral transformation methods were compared. • XGBoost and physicochemical properties were integrated to estimate pollution indices. • Composite pollution index was more accurately estimated than the other indices. • Fe and organic carbon significantly affected estimation accuracy of pollution indices. Single and composite pollution indices (SPI and CPI) of heavy metals are calculated with background heavy metal concentrations. They are efficient evaluation indicators of sediment pollution levels and could be directly compared among different regions and habitat types, however, they are rarely investigated in mangrove sediment with visible and near-infrared spectroscopy (VNIRS). With mangrove sediment samples collected from five regions and four habitat types, this study aimed to develop estimation models of heavy metal (Cr, Ni, Cu, Zn and Pb) pollution indices using XGBoost (extreme gradient boosting) method, and further to explore the effect of physicochemical properties (Fe, organic carbon (OC), clay and salinity) on the estimation accuracy. Kruskal-Walls test showed that regions and habitat types were significant factors affecting the six pollution indices. Compared with first derivative, second derivative and continuum removal reflectance, standard normal variate (SNV) reflectance was more accurate for estimating SPIs and CPI using XGBoost model. The XGBoost models with sensitive wavelengths of SNV reflectance outperformed that with whole spectrum (410 bands) in estimating the six pollution indices, and the ranking of estimation accuracy was CPI > SPI Cu > SPI Zn > SPI Pb > SPI Ni > SPI Cr. Compared with the XGBoost model with sensitive wavelengths alone, the model with additional physicochemical properties could increase R 2 and RPD (the ratio of standard deviation to RMSE of validation in the test subset) values by 0.795–7.282% and 1.199–8.780%, and decrease RMSE values by 4.101–26.866% in estimating SPI Cr , SPI Ni and SPI Cu. Moreover, Fe and OC had greater effect on the estimation accuracy than clay and salinity. We conclude the integration of XGBoost and physicochemical properties holds potentials for accurately assessing heavy metal pollution indices in mangrove sediment with VNIRS, which can provide methodological basis for evaluating environment quality and ecological risk in mangrove ecosystem at the plot or landscape scale. [ABSTRACT FROM AUTHOR]