Remote sensing for the monitoring of chlorophyll-a (Chl-a) is essential to compensate for the shortcomings of traditional water quality monitoring, strengthen red tide disaster monitoring and early warnings, and reduce marine environmental risks. In this study, a machine learning approach called the Gradient-Boosting Decision Tree (GBDT) was employed to develop an algorithm for estimating the Chl-a concentrations of the coastal waters of the Beibu Gulf in Guangxi, using Landsat 8 OLI image data as the image source in combination with field measurements of Chl-a concentrations. The GBDT model with B4, B3 + B4, B3, B1 − B4, B2 + B4, B1 + B4, and B2 − B4 as input features exhibited higher accuracy (MAE = 0.998 μg/L, MAPE = 19.413%, and RMSE = 1.626 μg/L) compared with different physics models, providing a new method for remote sensing inversion of water quality parameters. The GBDT model was used to study the spatial distribution and temporal variation of Chl-a concentrations in the coastal sea surface of the Beibu Gulf of Guangxi from 2013 to 2020. The results showed a spatial distribution with high concentrations in nearshore waters and low concentrations in offshore waters. The Chl-a concentration exhibited seasonal changes (concentration in summer > autumn > spring ≈ winter).

The Amur River is one of the top ten longest rivers in the world, and its hydrological response to future climate change has been rarely investigated. In this study, the outputs of four GCMs in the Coupled Model Intercomparison Project Phase 6 (CMIP6) were corrected and downscaled to drive a distributed hydrological model. Then, the spatial variations of runoff changes under the future climate conditions in the Amur River Basin were quantified. The results suggest that runoffs will tend to increase in the future period (2021–2070) compared with the baseline period (1961–2010), particularly in August and September. Differences were also found among different GCMs and scenarios. The ensemble mean of the GCMs suggests that the basin-averaged annual precipitation will increase by 14.6% and 15.2% under the SSP2-4.5 and SSP5-8.5 scenarios, respectively. The increase in the annual runoff under the SSP2-4.5 scenario (22.5%) is projected to be larger than that under the SSP5-8.5 scenario (19.2%) at the lower reach of the main channel. Future climate changes also tend to enhance the flood peak and flood volume. The findings of this study bring new understandings of the hydrological response to future climate changes and are helpful for water resource management in Eurasia.

Chlorophyll-a (Chl-a) concentration is a measure of phytoplankton biomass, and has been used to identify ‘red tide’ events. However, nearshore waters are optically complex, making the accurate determination of the chlorophyll-a concentration challenging. Therefore, in this study, a typical area affected by the Phaeocystis ‘red tide’ bloom, Qinzhou Bay, was selected as the study area. Based on the Gaofen-1 remote sensing satellite image and water quality monitoring data, the sensitive bands and band combinations of the nearshore Chl-a concentration of Qinzhou Bay were screened, and a Qinzhou Bay Chl-a retrieval model was constructed through stepwise regression analysis. The main conclusions of this work are as follows: (1) The Chl-a concentration retrieval regression model based on 1/B4 (near-infrared band (NIR)) has the best accuracy (R2 = 0.67, root-mean-square-error = 0.70 μg/L, and mean absolute percentage error = 0.23) for the remote sensing of Chl-a concentration in Qinzhou Bay. (2) The spatiotemporal distribution of Chl-a in Qinzhou Bay is varied, with lower concentrations (0.50 μg/L) observed near the shore and higher concentrations (6.70 μg/L) observed offshore, with a gradual decreasing trend over time (−0.8).

No abstract

Aims Inundation frequency (IF) is an important influencing factor on dynamics of wetland vegetation. This study analyzed the temporal and spatial variations of IF and enhanced vegetation index (EVI) of wetland vegetation and their correlation in Poyang Lake, so as to maintain the stability of wetland ecosystem. MethodsIn view of the significant seasonal changes of Poyang Lake, its impact on wetland vegetation needs to be analyzed with a high temporal resolution method. Based on MODIS image data from 2000-03-01 to 2020-02-29, this study mapped the annual water inundation frequency of Poyang Lake, analyzed the temporal and spatial variations of EVI under different flooding conditions, and explored the response of EVI of wetland vegetation to changes in flooding conditions. Important findingsThe following conclusions are drawn: (1) The hydrological rhythm of Poyang Lake has changed significantly in the past 20 years. The water area with high inundation frequency (IF > 75%) decreased from 1 435.3 km 2 in 2000 to 510.25 km 2 in 2019, with a decrement of 64.45%. (2) The regional average EVI showed a significant upward trend. Vegetation expansion was mainly concentrated in the middle region of Poyang Lake which was also the main region of IF declining. (3) By analyzing the changes of average EVI value under different total IF regions, it was found that the variation trend of IF was similar to that of EVI. After 2009, the shrinking trend of the Poyang Lake water area was alleviated, and the growth rate of EVI decreased. (4) In the past 20 years, the changing trend of IF and EVI in Poyang Lake was highly consistent in spatial distribution. Wetland vegetation was mainly expanded along the decreasing direction of water area. This spatial heterogeneity further confirms that hydrological variation plays a role in regulating vegetation dynamics.