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
Plastic pollution is a major environmental issue worldwide, calling for advanced methods to recycle waste plastics in the context of the circular economy. Here we review methods and strategies to convert waste plastics into value-added carbon materials, with focus on sources, properties, pretreatment of waste plastics, and on preparation of carbon materials. Pretreatment techniques include mechanical crushing, plastic stabilization and electrospinning. Carbon materials such as carbon nanotubes, graphene, carbon nanosheets, carbon spheres and porous carbon are prepared by oxygen-limited carbonization, catalytic carbonization, the template-based method, and pressure carbonization. We emphasize the conversion of polyethene terephthalate, polyethylene, polypropylene, polystyrene, halogenated plastics, polyurethane and mixed plastics.
Environmental Chemistry Letters - Wastewater from the uranium mining industry contains toxic arsenate (AsO43–), selenate (SeO42–), and molybdate (MoO42–) that can be removed by... 相似文献
• Isotope dilution method was developed for the determination of 27 PPCPs in water.• The established method was successfully applied to different types of water samples.• The correction effect of corresponding 27 ILSs over 70 d was investigated.• Benefit of isotopic dilution method was illustrated for three examples. Pharmaceuticals and personal care products (PPCPs) are a unique group of emerging and non-persistent contaminants. In this study, 27 PPCPs in various water samples were extracted by solid phase extraction (SPE), and determined by isotope dilution method using liquid chromatography coupled to tandem triple quadruple mass spectrometer (LC-MS/MS). A total of 27 isotopically labeled standards (ILSs) were applied to correct the concentration of PPCPs in spiked ultrapure water, drinking water, river, effluent and influent sewage. The corrected recoveries were 73%–122% with the relative standard deviation (RSD)<16%, except for acetaminophen. The matrix effect for all kinds of water samples was<22% and the method quantitation limits (MQLs) were 0.45–8.6 ng/L. The developed method was successfully applied on environmental water samples. The SPE extracts of spiked ultrapure water, drinking water, river and wastewater effluent were stored for 70 days, and the ILSs-corrected recoveries of 27 PPCPs were obtained to evaluate the correction ability of ILSs in the presence of variety interferences. The recoveries of 27 PPCPs over 70 days were within the scope of 72%–140% with the recovery variation<37% in all cases. The isotope dilution method seems to be of benefit when the extract has to be stored for long time before the instrument analysis. 相似文献