River water quality is of utmost importance because the river is not only one of the key water resources but also a natural habitat serving its surrounding environment. In a bid to address whether it has a qualified quality, various analytics are required to be considered, but it is challenging to measure all of them frequently along a river reach. Therefore, estimating water quality index (WQI) incorporating several weighted analytics is a useful approach to assess water quality in rivers. This study explored applications of ten machine learning (ML) models to estimate WQI for the Southern Bug River, which is the second-longest river in Ukraine. The ML methods considered in this study include artificial neural networks (ANNs), Support Vector Regressor (SVR), Extreme Learning Machine, Decision Tree Regressor, random forest, AdaBoost (AB), Gradient Boosting Regressor, XGBoost Regressor (XGBR), Gaussian process (GP), and K-nearest neighbors (KNN). Each data measurement consists of nine analytics (NH₄, BOD₅, suspended solids, DO, NO₃, NO₂, SO₄, PO₄, Cl), while the quantity of data is more than 2700 data points. The results indicated that all ML models demonstrate satisfactory performance in predicting WQI. However, GP outperformed the other models, followed by XGBR, SVR, and KNN. Furthermore, ANN and AB demonstrated relatively weaker performance. Moreover, a reliability assessment conducted on both training and testing datasets also confirmed the results of the comparative analysis. Overall, the results enhance the assertion that ML models can sufficiently predict WQI, thereby enhancing water quality management.

Pier scour is a major problem for the safe and economical design of bridges. Large number of field and laboratory studies have been conducted to investigative the effect of significant variables. Present study is an attempt to develop a generalized scour prediction equation to investigate temporal variation of scour around circular bridges utilizing the data generated from our experimental study as well as data collected by earlier researchers. Nearly 1100 laboratory experimental data-sets were compiled and utilized to develop the generalized scour equation using MLR and GA. The scour depth predicted using GA was found to be more accurate than MLR. Further, the equation developed in the present study was compared to the previously proposed equations. It was found that the present equation complies with observed data better than the previously proposed equations. About 20% and 35% data-sets are found to be within the ±25% error line using previously proposed equations, while GA-based relationship gave about 52% of the data points within ±25% error line.

Ganga River basin, being the largest river basin in India, adheres with its social and spiritual importance for the country. Although many studies have been conducted on the Ganga basin, however, trend observed in flow and sediment yield in Ganga River has been scarcely studied. Alteration in flow pattern and sediment transport in rivers brings remarkable impact on river geomorphology and entire ecosystem of the region. The present paper attempts to identify trends observed in Ganga River in terms of annual maximum and annual minimum discharges, water and sediment yield during monsoon season. The trend analysis was accomplished by performing the Mann-Kendall (M-K), Sen’s slope, and innovative trend analysis at various gauging sites along the river for the monsoon months. Significance of trend tests were tested at 5% significance level. Innovative trend analysis (ITA) revealed non-monotonicity within the time series and provided more detailed understanding of changes in hydrological changes. While observed annual maximum discharge showed a negative trend at almost all the sites, annual minimum discharge showed positive trend at gauging sites upstream of confluence of Yamuna River. Data of discharge and sediment load for monsoon months also revealed declining trends at most of the gauging sites. Water and sediment yields at all sites except Gandhighat showed a negative trend. Decline in trend of sediment and water yield is more pronounced in Western Ganga Plain (WGP) as compared to Eastern Ganga Plain (EGP). Incorporating these trends can be helpful for various water management projects in the future. Both climatic factors and human intervention appear to be responsible for the alteration in flow pattern of Ganga River.

SummaryInfiltration is the process of flow of water into the ground through the soil surface. Soil water although contributes a negligible fraction of total water present on earth surface, but is of utmost importance for plant life. Estimation of infiltration rates is of paramount importance for estimation of effective rainfall, groundwater recharge, and designing of irrigation systems. Numerous infiltration models are in use for estimation of infiltration rates. The conventional graphical approach for estimation of infiltration parameters often fails to estimate the infiltration parameters precisely. The generalised reduced gradient (GRG) solver is reported to be a powerful tool for estimating parameters of nonlinear equations and it has, therefore, been implemented to estimate the infiltration parameters in the present paper. Field data of infiltration rate available in literature for sandy loam soils of Umuahia, Nigeria were used to evaluate the performance of GRG solver. A comparative study of graphical method and GRG solver shows that the performance of GRG solver is better than that of conventional graphical method for estimation of infiltration rates. Further, the performance of Kostiakov model has been found to be better than the Horton and Philip's model in most of the cases based on both the approaches of parameter estimation