Understanding the interaction of surface water and groundwater affected by anthropogenic activities is of great importance for water resource and water quality management. The Xiong’an New Area, located in the North China Plain, has been designated a new building area by China’s government. Groundwater has been over pumped and artificial water was transferred to meet the water supply in this region. Therefore, the natural interaction of surface water and groundwater has been greatly changed and there has been a complex impact of the groundwater from anthropogenic activities. In this study, we used water chemical ions and stable isotopes of δ²H and δ¹⁸O to assess the interaction of surface water and groundwater in the Xiong’an New Area. We carried out field surveys and water sampling of the Fu River (domestic waste water discharge), Lake Baiyangdian (artificial water transfer), and the underlying groundwater along the water bodies. Results show that the artificial surface water (discharged and transferred) became the major recharge source for the local groundwater due to the decline of groundwater table. We used groundwater table observations, end-member mixing analysis of the stable isotopic composition and chloride tracers to estimate the contributions of different recharge sources to the local groundwater. Due to the over pumping of groundwater, the lateral groundwater recharge was dominant with a contribution ratio ranging from 12% to 78% in the upper reach of the river (Sections 1–3). However, the contribution of lateral groundwater recharge was estimated to be negligible with respect to the artificial water recharge from Lake Baiyangdian. Seepage from the Fu River contributed a significant amount of water to the connecting aquifer, with a contribution ranging from 14% to 75% along the river. The extent of the river influence into the aquifer ranges as far as 1400 m to the south and 400 m to the north of the Fu River. Estimations based on isotopic fractionation shows that about 22.3% of Lake Baiyangdian water was lost by evaporation. By using the stable isotopes of oxygen and hydrogen in the lake water, an influencing range of 16 km west of the lake was determined. The interaction of the surface water and groundwater is completely changed by anthropogenic activities, such as groundwater over pumping, waste water discharge and water transfer. The switched interaction of surface water and groundwater has a significant implication on water resources management.

Quantifying the impact of climate change and human activities on runoff changes is beneficial for developing sustainable water-management strategies within the local ecosystem. Machine-learning models were widely used in scientific research; yet, whether it is applicable for quantifying the contribution of climate change and human activities to runoff changes is not well understood. To provide a new pathway, we quantified the contribution of climate change and human activities to runoff changes using a machine-learning method (random forest model) in two semi-humid basins in this study. Results show that the random forest model provides good performances for runoff simulation; the contributions of climate change and human activities to runoff changes from 1982 to 2014 were found between 6–9% and 91–94% in the Zijinguan basin, and 31–44% and 56–69% in the Daomaguan basin, respectively. Furthermore, the model performances were also compared with those of well-known elasticity-based and double-mass curve methods, and the results of these models are approximate in the investigated basins, which implies that the random forest model has the potential for runoff simulation and for quantifying the impact of climate change and human activities on runoff changes. This study provides a new methodology for studying the impact of climate change and human activities on runoff changes, and the limited numbers of parameters make this methodology important for further applications to other basins elsewhere. Nevertheless, the physical interpretation should be made with caution and more comprehensive comparison work must be performed to assess the model’s applicability.