Data-driven reconstruction of the main traits of the large-scale Po River basin subsurface system

We discuss the definition and implementation of an integrated groundwater and surface water flow modeling framework focused on the Po River basin (Italy; with an extension of about 72.000 km²). At such a scale, it is possible to characterize global (space‐time) patterns of groundwater response in a way that is typically overshadowed when considering analyses at the scale of a single aquifer. We create a georeferenced three-dimensional platform that unifies the diverse types of data available in the basin area. The data collected merge streams of information from a variety of sources, including, e.g., climate satellite data, soil properties and land use data, and lithological/sedimentological information. In this context, we consider two key inputs of the large-scale groundwater model: i) the estimation recharge rates and ii) the reconstruction of the subsurface architecture. We then focus on the latter element and analyze the most critical steps associated with data collection, organization, and interpretation. We obtain an operational model of the domain upon relying on lithological and sedimentological information to reconstruct the spatial distribution of subsurface geomaterials which we integrated within a machine learning approach based on Artificial Neural Networks. Results are compared with available geological interpretations in the area. We discuss feedbacks between (a) the characterization of the system, as driven by domain discretization, that aims at considering a high-resolution hydrogeological reconstruction and (b) computational efficiency. Our results are discussed in the framework of future developments of the study with a view to establishing a physically-based three-dimensional characterization of large-scale groundwater flow accounting for a variety of processes taking place across multiple scales.