Accurate prediction of dissolved oxygen (DO) is essential for effective water quality monitoring and aquatic ecosystem management. However, DO dynamics are governed by complex temporal patterns and nonlinear interactions among physicochemical and meteorological variables, which limit the performance of standalone statistical or machine learning models. To address this challenge, this study proposes a hybrid modeling framework that integrates AutoRegressive Integrated Moving Average (ARIMA), Light Gradient Boosting Machine (LGBM), and Optuna-based hyperparameter optimization. The framework was applied to a 30-year water quality dataset (1989–2019), incorporating key variables such as water temperature, air temperature, depth, salinity, pH, and Secchi depth. The proposed hybrid model achieved excellent predictive performance, yielding a coefficient of determination (R2) of 0.98 and a Root Mean Squared Error (RMSE) of 0.043 mg/L in dissolved oxygen prediction, outperforming the standalone LGBM model (R2 = 0.94, RMSE = 0.081 mg/L). The ARIMA component effectively captured linear temporal dependencies and seasonality, while LGBM modeled complex nonlinear relationships, and Optuna optimization significantly enhanced model generalization and stability. Comparative analysis with existing studies further confirmed the superior accuracy and robustness of the proposed approach. Overall, the results demonstrate that the hybrid ARIMA–LGBM framework provides a reliable and efficient tool for long-term dissolved oxygen forecasting, supporting advanced water quality monitoring and informed environmental management.
The article presents the results of a comprehensive study of ice jam formation processes in small rivers, in the example of the Ala-Archa River, flowing through the territory of Bishkek. The relevance of the work is due to the stable recurrence of ice jams (2.3 ± 0.4 cases/year), causing flooding of urban infrastructure. Visual observations of the duration of ice jams in the studied rivers were conducted, with GPS data collected at observation points along the banks. The hydrological, hydraulic, and morphological conditions of the riverbed were also examined. This study of ice jamming processes found an engineering solution to the problem of protection from the formation of ice jams in dangerous areas.
Studies on the interaction of surface water with groundwater have gradually gained the attention of hydrologists in recent decades as they play a vital role in the hydrological cycle influencing hydrological and water resources processes. The complexity exhibited in the interaction due to the wide range of heterogeneity in the hydrological and hydrogeological properties of catchment makes it challenging to transfer the results of surface water groundwater (SW-GW) interaction from a point scale to a larger scale. Defining the relationship between groundwater and surface water becomes essential to refine the existing surface water groundwater models to aid the hydrologists in adapting better water management policies and decisions in the future. Before any detailed hydrological modelling to study and simulate the surface water groundwater interaction on a regional or point scale, a thorough understanding of the base flow’s contribution to the streamflow becomes indispensable. A brief review of the existing literature on the role of baseflow in SW-GW interaction and available techniques for characterizing the interaction is summarized here in the context of hydrological and geological conditions and data variability. This paper mainly focuses on three methods of baseflow analysis: Flow duration curve approach, baseflow separation and recession analysis. Identifying the best suitable method for its estimation from a wide range of available methods becomes a challenge as baseflow is a component of the hydrological cycle that is not available for measurement. Comparative study of various baseflow analysis methods, on the other hand, might help us assess the overall accuracy.
The article presents information about hydrological gages where observations of water resources of Uzbekistan are made. The water regime of rivers of the Zeravshan River basin is analyzed. Most river catchments are under anthropogenic impact. In addition, catchments may be affected by changing climate factors. A conclusion is made about the hydrological study of the Zeravshan River basin and the possibility of hydrological assessment of water resources.
The Indo-Gangetic Plain exhibits a number of riverine wetlands associated with extinct rivers in the form of interconnected channels, oxbow lakes, meander scars, etc. To develop a model for the revival of these riverine wetlands, the interfluvial zone of the Ganga and Sai Rivers has been taken as the case study area, where, the Bakulahi River is existing an extinct river that has numerous associated riverine wetlands. The SRTM DEM data was acquired from the USGS website, and further, the elevation along the delineated traces of the channels of the Bakulahi River in the DEM map was lowered by 3 m in ArcGIS software, and a modified DEM map was prepared. Applying SWAT to the modified DEM data, a model of the Bakulahi River basin has been developed, which reveals that by excavating along the traces of the Bakulahi River by 3 m, the river can be revived. After the revival, it was found that the catchment area, length, discharge, and number of sub-basins had increased. Out of 125 sub-basins, 14 are notable for high groundwater recharge potential, making them vital for ecosystem conservation and strictly restricted from any construction activities. This model highlights that enhancing longitudinal connectivity not only increases the river’s flow but also reconstructs all the associated wetlands and supports biodiversity. Furthermore, this approach has the potential to serve as a role model for the restoration of Quaternary riverine wetlands in the Gangetic Plain, as well as for similar floodplain systems worldwide facing the threat of extinction.
