ABSTRACT
Soil organic matter is an important indicator of soil fertility, and it is necessary to improve the accuracy of regional organic matter spatial distribution prediction. In this study, we analyzed the organic matter content of 1 690 soil surface layers (0-20 cm) and collected data on the natural environment and human activities in the Weining Plain of the Yellow River Basin. The SOM spatial distribution prediction model was established with 1 348 points using classical statistics, deterministic interpolation, geostatistical interpolation, and machine learning, respectively, and 342 sample points data were used as the test set to test and analyze the prediction accuracy of different models. The results showed that the average SOM content of the surface soil of the Weining Plain was 14.34 g·kg-1, and the average soil organic matter variation across 1 690 sampling points was 34.81%, indicating a medium degree of variability. The results also revealed a spatial distribution trend, with low soil organic matter content in the northeast and southwest, high soil organic matter on the left and right banks of the Yellow River in the middle, and relatively high soil organic matter in the sloping terrain of the Weining Plain. The four types of methods in order of high to low prediction accuracy were the machine learning method, geostatistical interpolation method, deterministic interpolation method, and classical statistical method. Through comparison, the BP neural network that was improved based on the optimized sparrow search algorithm had the best prediction accuracy, and the optimized sparrow search algorithm had better convergence accuracy, avoided falling into local optimization, prevented data overfitting, and had better prediction ability. This optimization algorithm can improve the accuracy of SOM prediction and has good application prospects in soil attribute prediction.
ABSTRACT
The composition and concentrations of trace metals in coastal seawater have changed in parallel with variations in geochemical processes, climate and anthropogenic activities. To evaluate the response of trace metals in coastal seawater to climatic changes and human disturbances, we report annual-resolution trace element data for a Porites coral core covering ~100years of continuous growth from a fringing reef in Xiaodonghai Bay in the northern South China Sea. The results suggested that the trace metal contents in the coral skeleton demonstrated decadal to interdecadal fluctuations with several large or small peaks in certain years with remarkable environmental significances. All of the trace metals in coastal surface seawater, especially Cr and Pb (related to industrial or traffic emissions), were impacted by terrestrial inputs, except for Sr and U, which were impacted by the surface seawater temperature (SST). Moreover, Mn, Ni, Fe and Co were also contributed by weapons and military supplies during wars, and Cu, Cd and Zn were further impacted by upwelling associated with their biogeochemical cycles. Ba and rare earth element (REE) in coastal surface seawater were dominated by runoff and groundwater discharge associated with precipitation. This study provided the potential for some trace metals (e.g., REE, Ba, Cu, Cd, and Zn) in coral skeletons to be used as proxies of natural (e.g., upwelling and precipitation) and anthropogenic (e.g., war and coastal construction) variability of seawater chemistry to enable the reconstruction of environmental and climatic changes through time.
