Surface sediments were collected from 122 sites in the upstream of the Yellow River, China. The concentration of Fe, Mn, Cu, Ni, Zn, Cr, Pb, and Cd in sediments was investigated to explore the spatial distribution based on statistics and interpolation method. The results suggested that the concentrations of heavy metals were lower than potential effect levels (PEL). The samples above threshold effect level (TEL) for Pb and Zn were less than 10%, while almost 50% of samples for Ni exceeded PEL. Pb and Zn in sediments performed little or no adverse effects on the aquatic ecosystems. Higher concentrations of all heavy metals occurred in Qinghai and Gansu sections; the concentrations of Cu, Ni, and Zn were significantly higher than the Inner Mongolia section. Lower concentration of Fe, Mn, Cu, Ni, and Zn appeared in Qinghai section; the concentrations of Fe, Mn, Cr, and Pb manifested relatively steady and similar distributions and approximately decreasing tendency along the upstream of Yellow River.
Data-driven techniques are used extensively for hydrologic time-series prediction. We created various data-driven models (DDMs) based on machine learning: long short-term memory (LSTM), support vector regression (SVR), extreme learning machines, and an artificial neural network with backpropagation, to define the optimal approach to predicting streamflow time series in the Carson River (California, USA) and Montmorency (Canada) catchments. The moderate resolution imaging spectroradiometer (MODIS) snow-coverage dataset was applied to improve the streamflow estimate. In addition to the DDMs, the conceptual snowmelt runoff model was applied to simulate and forecast daily streamflow. The four main predictor variables, namely snow-coverage (S-C), precipitation (P), maximum temperature (Tmax), and minimum temperature (Tmin), and their corresponding values for each river basin, were obtained from National Climatic Data Center and National Snow and Ice Data Center to develop the model. The most relevant predictor variable was chosen using the support vector machine-recursive feature elimination feature selection approach. The results show that incorporating the MODIS snow-coverage dataset improves the models' prediction accuracies in the snowmelt-dominated basin. SVR and LSTM exhibited the best performances (root mean square error = 8.63 and 9.80) using monthly and daily snowmelt time series, respectively. In summary, machine learning is a reliable method to forecast runoff as it can be employed in global climate forecasts that require high-volume data processing. 相似文献
Environmental Science and Pollution Research - In the process of water treatment, excessive nitrogen and phosphorus pollutants are of great concern. Therefore, we prepared nanoscale zerovalent iron... 相似文献
Environmental Science and Pollution Research - Co3O4 nanorods with diameters of ~0.15 μm and lengths of ~1 μm were prepared using a hydrothermal method via the assembly of microcrystals... 相似文献
Environmental Science and Pollution Research - Nitrosamines (NAms) are potent genotoxic and carcinogenic but widely detected in drinking water. This study aimed to investigate the occurrence of... 相似文献