Micro-pollutants especially estrogens, progesterone, androgens, glucocorticoids, and growth hormones, are biological and chemical impurities that find their way into natural aquatic environments in trace quantities (ng/L), and possess a significant disturbance by impacting human and aquatic life. Due to the significant progress in in the analysis and detection techniques, these trace elements have been observed and quantified in several studies. However, as a result of limited methods and management technology, the adverse effects by these micro-pollutants in surface and coastal water is largely unknown. For this study, the compounds of estrogens, progesterone, androgens, glucocorticoids, and growth hormones have been selected according to their high frequent detection value in environmental waters. The concentration of the selected steroid and hormones ranges from 0.1–196 ng/L (estrogens), less than 0.1 to 439 ng/L (progesterone), 0.06–86 ± 2 (androgens), less than 0.1 to 433 ng/L (glucocorticoids), and 26.6 ng/g to 100 ng/L (growth hormones), and their percentage of removal efficiency varies from less than 10% to 99%, as the measurement of compounds concentration was found to be very low. Here, we report that future studies are necessary to detect the entry routes of these compounds into the environmental water, as well as to explore the technological approaches which are able to resolve this issue permanently.

Data-driven flow forecasting models, such as Artificial Neural Networks (ANNs), are increasingly used for operational flood warning systems. In this research, we systematically evaluate different machine learning techniques (random forest and decision tree) and compare them with classical methods of the NAM rainfall run-off model for the Vésubie River, Nice, France. The modeled network is trained and tested using discharge, precipitation, temperature, and evapotranspiration data for about four years (2011–2014). A comparative investigation is executed to assess the performance of the model by using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and a correlation coefficient (R). According to the result, Feed Forward Neural Network (FFNN) (a type of ANN) models are less efficient than NAM models. The precision parameters correlation coefficient of ANN is 0.58 and for the NAM model is 0.76 for the validation dataset. In all machine learning models, the decision tree which performed best had a correlation coefficient of 0.99. ANN validation data prediction is good compared to the training, which is the opposite in the NAM model. ANN can be improved by fitting more input variables in the training dataset for a long period.

Distribution of the water flow path and residence time (HRT) in the hyporheic zone is a pivotal aspect in anatomizing the transport of environmental contaminants and the metabolic rates at the groundwater and surface water interface in fluvial habitats. Due to high variability in material distribution and composition in streambed and subsurface media, a pragmatic model setup in the laboratory is strenuous. Moreover, investigation of an individual streamline cannot be efficiently executed in laboratory experiments. However, an automated generation of water flow paths, i.e., streamlines in the hyporheic zone with a range of different streambed configurations could lead to a greater insight into the behavior of hyporheic water flow. An automated approach to quantifying the water flow in hyporheic zone is developed in this study where the surface water modeling tool, HER-RAS, and subsurface water flow modelling code, MIN3P, are coupled. A 1m long stream with constant water surface elevation of 2 cm to generate hydraulic head gradients and a saturated subsurface computational space with the dimensions of x:y:z = 1:0.1:0.1 m is considered to analyze the hyporheic exchange. Response in the hyporheic streamlines and residence time due to small-scale changes in the gravel-sand streambed were analyzed. The outcomes of the model show that the size, shape, and distribution of the gravel and sand portions have a significant influence on the hyporheic flow path and HRT. A high number and length of the hyporheic flow path are found in case of the highly elevated portion of gravel pieces. With the increase in the base width of gravel pieces, the length of hyporheic flow path and HRT decreases. In the case of increased amounts of gravel and sand portions on the streambed, both the quantity and length of the hyporheic flow path are reduced significantly.

River renaturation can be an effective management method for restoring a floodplain’s natural capacity and minimizing the effects during high flow periods. A 1D-2D Hydrologic Engineering Center–River Analysis System (HEC-RAS) model, in which the flood plain was considered as 2D and the main channel as 1D, was used to simulate flooding in the restored reach of the Spree River, Germany. When computing in this model, finite volume and finite difference approximations using the Preissmann approach are used for the 1D and 2D models, respectively. To comprehend the sensitivity of the parameters and model, several scenarios were simulated using different time steps and grid sizes. Additionally, dikes, dredging, and changes to the vegetation pattern were used to simulate flood mitigation measures. The model predicted that flooding would occur mostly in the downstream portion of the channel in the majority of the scenarios without mitigation measures, whereas with mitigation measures, flooding in the floodplain would be greatly reduced. By preserving the natural balance on the channel’s floodplain, the restored area needs to be kept in good condition. Therefore, mitigating measures that balance the area’s economic and environmental aspects must be considered in light of the potential for floods.

The environmental issues we are currently facing require long-term prospective efforts for sustainable growth. Renewable energy sources seem to be one of the most practical and efficient alternatives in this regard. Understanding a nation’s pattern of energy use and renewable energy production is crucial for developing strategic plans. No previous study has been performed to explore the dynamics of power consumption with the change in renewable energy production on a country-wide scale. In contrast, a number of deep learning algorithms have demonstrated acceptable performance while handling sequential data in the era of data-driven predictions. In this study, we developed a scheme to investigate and predict total power consumption and renewable energy production time series for eleven years of data using a recurrent neural network (RNN). The dynamics of the interaction between the total annual power consumption and renewable energy production were investigated through extensive exploratory data analysis (EDA) and a feature engineering framework. The performance of the model was found to be satisfactory through the comparison of the predicted data with the observed data, the visualization of the distribution of the errors and root mean squared error (RMSE), and the R2 values of 0.084 and 0.82. Higher performance was achieved by increasing the number of epochs and hyperparameter tuning. The proposed framework has the potential to be used and transferred to investigate the trend of renewable energy production and power consumption and predict future scenarios for different communities. The incorporation of a cloud-based platform into the proposed pipeline to perform predictive studies from data acquisition to outcome generation may lead to real-time forecasting.