AI-based runoff simulation based on remote sensing observations: A case study of two river basins in the United States and Canada

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 (T_max), and minimum temperature (T_min), 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.     

Road-deposited sediments mediating the transfer of anthropogenic organic matter to stormwater runoff

Environmental Geochemistry and Health - It has been regarded that road-deposited sediment (RDS) is one of the important sinks of anthropogenic pollutants as well as the major source of pollutants...     

Selective separation of cobalt versus nickel by split-phosphinate complexation using a phosphonium-based ionic liquid

Environmental Chemistry Letters - The rising demand of metals for batteries is calling for advanced methods to separate metallic mixtures in mineral ores and electronic waste. In particular, the...     

Supervisor expediency to employee expediency: The moderating role of leader–member exchange and the mediating role of employee unethical tolerance

We utilize social learning theory to test the role‐modeling effect of supervisor expediency (i.e., a supervisor's use of unethical practices to expedite work for self‐serving purposes). In particular, we examine the relationship between supervisor expediency and employee expediency, as moderated by leader–member exchange (LMX) and mediated by employee unethical tolerance. We predict that employees are more likely to model their supervisors' expedient behaviors when their relationship is characterized by high‐LMX (a high‐quality exchange relationship that is rich in socioemotional support). Furthermore, we argue that supervisor expediency, especially when LMX is high, influences employees' attitudes of unethical tolerance, which then affects employees' expedient behaviors. Across 2 multisource field studies and a third time‐lagged field study, we found general support for our theoretical predictions. Theoretical and practical implications are discussed.     

Urban development and landscape change in the Yangtze River Delta region in China

The impact of large-scale urban development on land resources has long been debated by urban planners and designers. This study investigated the extent to which different urban characteristics are associated with land-cover change. The Yangtze River Delta region in China, forming one of the largest sprawling urban landscapes among the regions around the world, was chosen for the study area. Spatial analysis and multiple regression methods were applied to empirically investigate the pattern of resource sites lost to urban development in the area between the 1950s and 2017. The results showed that contrary to the widespread notion that large-sized cities are predominantly responsible for a region’s environmental degradation, city size was not a significant factor in determining the rate of resource loss. Large-sized cities gained their populations with far lesser impacts on land than small-sized cities and towns if normalized to the same number of populations. One explanation for the diminishing effect of city size on land-cover change relates to the degree of spatial dispersion of urban development and local differences in social valuation of diversified lands by cities.     

Reductive dissolution and sequestration of arsenic by microbial iron and thiosulfate reduction

Environmental Geochemistry and Health - Iron oxide and oxy-hydroxide are commonly used for remediation and rehabilitation of arsenic (As)-contaminated soil and water. However, the stability of As...     

Methyl methacrylate (MMA) and alumina recovery from waste artificial marble powder pyrolysis

Journal of Material Cycles and Waste Management - Owing to various advantages of artificial marble compared to natural marble, its application has been rising exponentially, which has resulted in...