The increase in world population, added to socioeconomic development and climate change, have highlighted one of the biggest problems worldwide: the depletion of water resources. The La Ligua and Petorca river basins, in central Chile, are an example of this problem, as rainfall has decreased in recent years, while socio-economic activities, mainly agriculture have increase. This situation has led to a severe water stress, and the need for integrated and sustainable river basin management, aimed at understanding the behavior of basins, aquifers, and the exchange of flows between them. Therefore, the main objective of this research is to quantify the impacts of climate change, in terms of groundwater scarcity, in semi-arid basins using integrated modeling of water resources. For this purpose, groundwater/surface waters integrated models of La Ligua and Petorca basins were developed using WEAP and MODFLOW. Both basins present different hydrological, social, and geographical characteristics. Different scenarios were evaluated to quantify groundwater depletion. These scenarios depend on climatic forcings, such as precipitation and temperature, which were obtained from the Phase 6 of the Coupled Model Intercomparison Project (CMIP6). Results forecast that annual precipitation will decrease, whereas average annual temperature will increase in these semi-arid regions. As a consequence, the aquifer’s recovery rate will reduce, decreasing the number of wells that provide drinking water in rural and agricultural areas. In conclusion, the coupling of hydrological and hydrogeological models is a tool that allows researchers and stakeholders to make opportune and appropriate decisions on the management of basins and aquifers, which is even more important in basins that are expected to be or are already under severe water stress.

The use of modeling tools for integrated water resources management is a complex task due to the large number of processes involved in a basin. Moreover, these modeling tools commonly require information that is not readily available, such as illegal water withdrawals, or other data difficult to obtain, which results in groundwater models that fail to capture the aquifer dynamics. In recent years, machine learning algorithms have shown outstanding performance as prediction tools. Despite being questioned for not having a physical basis, they have been used in areas such as hydrology and hydrogeology (e.g., for flow prediction, rain forecast). Thus, the objective of this research is to estimate groundwater withdrawals using machine learning algorithms and integrated water management models. To achieve this objective, ensembles of groundwater levels were generated with a previously calibrated groundwater/surface water integrated model. Then, these ensembles were used as input parameters for Gaussian process regression (GPR) and artificial neural network (ANN) models to construct time series of water withdrawals throughout a basin. This method was applied in the Petorca and La Ligua basins, in central Chile, as they exhibit a contrasting reality in terms of water availability even when they have geographical proximity. Also, these basins are within an effective extraction monitoring program lead by the Chilean water authority that can be used to validate the users’ water withdrawal. Our results show that the GPR model, compared to ANNs, adequately estimates the spatiotemporal distribution of groundwater withdrawals in the pilot basins. Thus, the use of machine learning algorithms improves the performance of integrated water resources management models.