Global climate change is becoming an increasingly important issue that threatens the imperiled planet. Quantifying the impact of climate change on the streamflow has been an essential task for the proper management of water resources to mitigate this impact. This study aims to evaluate the skill of an artificial neural network (ANN) method in downscaling precipitation, maximum temperature, and minimum temperature and assess the potential impacts of climate change on the streamflow in the Wabash River Basin of the Midwestern United States (U.S.) using the Soil and Water Assessment Tool (SWAT). A statistical downscaling technique based on an ANN method was employed to estimate precipitation and temperature at a higher resolution. The downscaled climate projections from five general circulation models (GCMs) under the three representative concentration pathway (RCP) scenarios (i.e., RCP2.6, RCP4.5, and RCP8.5) for the periods of 2026–2050 and 2075–2099 as well as the historical period were incorporated into the SWAT model to assess the potential impact of climate change on the Wabash River regime. Calibration and validation of the SWAT model indicated the streamflow simulations matched the observed results very well. The ANN method successfully reproduced the observed maximum/minimum temperature and precipitation; however, bias in precipitation was observed in regard to the frequency distribution. Compared with the simulated streamflow in the historical period, the predicted streamflow based on the RCP scenarios showed an obvious decreasing trend, where the annual streamflows will be decreased by 13.00%, 17.59%, and 6.91% in the midcentury periods and 25.29%, 27.61%, and 15.04% in the late-century periods under the RCP2.6, RCP4.5, and RCP8.5 scenarios, respectively. Climate warming dominated the streamflow decrease under the RCP2.6 and RCP4.5 scenarios. By contrast, under RCP8.5, the streamflow was affected by the joint actions of changes in temperature and precipitation.

We evaluated precipitation estimates, TRMM (Tropical Rainfall Measuring Mission 3B42V7), CFSR (Climate Forecast System Reanalysis), GHCN-D (Global Historical Climatology Network-Daily Version 3.24), and Daymet, using the Soil and Water Assessment Tool (SWAT). The suitability and quality of TRMM, CFSR and Daymet in forcing the SWAT-based hydrological model was examined by means of model calibration. A calibrated TRMM-driven model slightly overestimated streamflow, while a calibrated CFSR-driven model performed worst. The Daymet-driven model performance was as good as the GHCN-D-driven model in reproducing observations. In addition, the temperature was far less sensitive compared with precipitation in driving SWAT. TRMM 3B42V7 showed great potential in streamflow simulation. The results and findings from this study provide new insights into the suitability of precipitation products for hydrological and climate impact studies in large basins, particularly those in typical climates and physiographic settings similar to the Midwestern USA.

Pump-and-treat (P&T) techniques are among the most commonly applied methods for groundwater contamination remediation. This study develops a groundwater flow model and a solute transport model using MODFLOW and RT3D to design and optimize P&T strategies for a polluted chemical park in northern China. Five scenarios were analyzed to evaluate the effects of well placement and pumping rates on remediation performance. Simulation results indicate that the existing number of extraction wells is inadequate to meet remediation targets. While increasing the pumping rate of individual wells accelerates remediation, it also increases the total extracted water volume. Similarly, higher extraction rates in heavily contaminated areas shorten remediation times but lead to greater water extraction. The findings demonstrate that numerical modeling can effectively optimize P&T designs, enabling the minimization of water extraction volumes while achieving remediation objectives within the required timeframe.

Groundwater vulnerability assessments serve as essential tools for sustainable groundwater management, particularly in regions with intensive anthropogenic activities. However, improving the objectivity and predictive reliability of vulnerability assessment frameworks remains a critical scientific challenge in groundwater science, especially for coastal aquifer systems characterized by strong heterogeneity and complex hydrogeological processes. The traditional DRASTIC model is a widely recognized method but suffers from subjectivity in assigning parameter ratings and weights, often leading to arbitrary and potentially inaccurate vulnerability maps. This limitation also restricts its applicability in areas with complex hydrogeological conditions. To enhance the accuracy and adaptability of the traditional DRASTIC model, a hybrid PSO-BP-DRASTIC framework was developed and applied it to a coastal city in China. Specifically, the model employs a backpropagation neural network (BP-NN) to optimize indicator weights and integrates the particle swarm optimization (PSO) algorithm to refine the initial weights and thresholds of the BP-NN. By introducing a data-driven and globally optimized weighting mechanism, the proposed framework effectively overcomes the inherent subjectivity of conventional empirical weighting schemes. Using ten-fold cross-validation and observed nitrate concentration data, the traditional DRASTIC, BP-DRASTIC, and PSO-BP-DRASTIC models were systematically validated and compared. The results demonstrate that (1) the PSO-BP-DRASTIC model achieved the highest classification accuracy on the test set, the highest stability across ten-fold cross-validation, and the strongest correlation with the nitrate concentrations; (2) the importance analysis identified the aquifer thickness and depth to the groundwater table as the most influential factors affecting groundwater vulnerability in Yantai; and (3) the spatial assessments revealed that high-vulnerability zones (7.85% of the total area) are primarily located in regions with intensive agricultural activities and high aquifer permeability. The hybrid PSO-BP-DRASTIC model effectively mitigates the subjectivity of the traditional DRASTIC method and the local optimum issues inherent in BP-NNs, significantly improving the assessment accuracy, stability, and objectivity. From a scientific perspective, this study demonstrates the feasibility of integrating swarm intelligence and neural learning into groundwater vulnerability assessment, providing a transferable and high-precision methodological paradigm for data-driven hydrogeological risk evaluation. This novel hybrid model provides a reliable scientific basis for the reasonable assessment of groundwater vulnerability. Moreover, these findings highlight the importance of integrating a hybrid optimization strategy into the traditional DRASTIC model to enhance its feasibility in coastal cities and other regions with complex hydrogeological conditions.