Milk vetch (Astragalus sinicus L.) is a winter-growing plant that can enhance soil fertility and provide essential nutrients for subsequent season crops. The fertilizing capacity of milk vetch is closely related to its above-ground biomass. Compared to the manual measurement methods of milk vetch biomass, remote sensing-based estimation methods have the advantages of rapid, noninvasive, and large-scale measurement. However, few studies have been conducted on remote sensing-based estimation of milk vetch biomass. To address this shortcoming, this study proposes combining unmanned aerial vehicle (UAV)-based hyperspectral imagery and machine learning algorithms for accurate estimation of milk vetch biomass. Through the analysis of hyperspectral images and feature selection based on the Pearson correlation and principal component analysis, vegetation indices (VIs), including near-infrared reflectance (NIR), red-edge spectral transform index (RE), and difference vegetation index (DVI), are selected as estimation metrics of the model development process. Four machine learning methods, including random forest (RF), multiple linear regression (MLR), deep neural network (DNN), and support vector machine (SVM), are used to construct the biomass models. The results show that the RF estimation model exhibits the highest coefficient of determination (R²) of 0.950 and the lowest relative root-mean-squared error (RRMSE) of 14.86% among all the models. Notably, the DNN model demonstrates promising performance on the test set, with the R² and RRMSE values slightly superior and inferior to those of the RF, respectively. The proposed method based on UAV imagery and machine learning can provide an accurate and reliable large-scale estimation of milk vetch biomass.

Salt marshes are declining due to the dual pressures of coastal erosion and land reclamation. However, there remains a lack of quantitative analysis regarding this reduction process and its driving mechanisms. This study examines the dynamics and influencing factors of salt marsh vegetation along the eroding coastline of Sheyang County, Jiangsu Province, China, between 1985 and 2020, using remote sensing to analyze changes in artificial coastlines, water boundaries, vegetation front edge, and its topography. Our results showed an extensive seaward movement of artificial coastlines due to reclamation, coupled with severe reductions in salt marsh area and width. Coastal erosion further caused a 10.5% decline in vegetation elevation and a 46.7% increase in slope steepness, amplifying vulnerability to wave action. Native species were largely replaced by Spartina alterniflora, reducing ecological diversity. Currently, human pressure on the landward side has been alleviated; thus, addressing coastal erosion is vital to preventing the further loss of salt marshes. Sediment retention engineering and native vegetation restoration efforts can gradually facilitate the recovery of salt marshes. This study provided critical insights for sustainable coastal management under bidirectional pressures.

Yield prediction is an important agriculture management for crop policy making. In recent years, unmanned aerial vehicles (UAVs) and spectral sensor technology have been widely used in crop production. This study aims to evaluate the ability of UAVs equipped with spectral sensors to predict oilseed rape yield. In an experiment, RGB and hyperspectral images were captured using a UAV at the seedling (S1), budding (S2), flowering (S3), and pod (S4) stages in oilseed rape plants. Canopy reflectance and spectral indices of oilseed rape were extracted and calculated from the hyperspectral images. After correlation analysis and principal component analysis (PCA), input spectral indices were screened to build yield prediction models using random forest regression (RF), multiple linear regression (MLR), and support vector machine regression (SVM). The results showed that UAVs equipped with spectral sensors have great potential in predicting crop yield at a large scale. Machine learning approaches such as RF can improve the accuracy of yield models in comparison with traditional methods (e.g., MLR). The RF-based training model had the highest determination coefficient (R²) (0.925) and lowest relative root mean square error (RRMSE) (5.91%). In testing, the MLR-based model had the highest R² (0.732) and lowest RRMSE (11.26%). Moreover, we found that S2 was the best stage for predicting oilseed rape yield compared with the other growth stages. This study demonstrates a relatively accurate prediction for crop yield and provides valuable insight for field crop management.

The pollutants from the Yangtze River will diffuse along the coastal zones with the action of the current. However, whether they will reach Zhoushan city or not and the impact, diffusion path of the pollutants from the Yangtze River is not clear. At present, there are few studies on the large-scale diffusion of pollutants from the Yangtze River into the sea. In this study, the transport and diffusion of chemical oxygen demand (COD) from the Yangtze River to Zhoushan sea area were studied by numerical simulation. The results showed that the diffusion of pollutants from the Yangtze River could reach Zhoushan. Both Hangzhou Bay and Zhoushan Island were greatly affected, resulting in an increase of COD concentration of 0.5-0.8 mg/L in most of Zhoushan sea areas. Because of the low background concentration of COD in Zhoushan, the percentage of COD increment caused by pollution in the Yangtze Estuary was more than 50%.

Coastal artificial lakes were encouraged to construct in China for coastal areas remediation. However, it was difficult to keep good water quality. This study investigated water quality improvement strategies for a new coastal artificial lake, located on the coast of Zhejiang Province, China. The expected objectives of water quality in the lake were identified as controlling of algae outbreak accidents under medium eutrophication state, transparency of 1.2 m and ensuring other water quality indicators to maintain or lower than the source water quality. Water exchange was implemented, and the water retention time was designed to be less than 30 days. The sediment could be mostly removed after precipitation in the preliminary precipitation basin. For phosphorus reduction, phosphorus concentration change was predicted by box model. Suppose the active phosphate concentration of inflow water was 0.02 mg/L, when the supplied water volume increased to 18 million m³/a, the active phosphate concentration of the lake could achieve 0.03mg/L. As the water quality was poor in summer, the amount of water supplied was suggested increased. This study established feasible water quality guidelines for sustainable operation, and suggested effective water quality improvement strategies for similar coastal artificial lakes.