Conceptual Model of Arsenic Mobility in the Shallow Alluvial Aquifers Near Venice (Italy) Elucidated Through Machine Learning and Geochemical Modeling

This work proposed a novel method to elucidate the controls of As mobility in complex aquifers based on an unsupervised machine learning algorithm, Self-Organizing Map (SOM), and process-based geochemical modeling. The approach is tested in the shallow aquifers of the Venetian Alluvial Plain (VAP) near Venice, Italy, where As concentrations seasonally and locally exceed recommended drinking water limits. SOM was fed using information from two geochemical surveys on eight VAP boreholes, and continuous reading of hourly groundwater head levels and weekly geochemical analyses from three VAP boreholes between mid-October 2017 and end of January 2018. The SOM analysis is consistent with redox-controlled dissolution-precipitation hydrous ferric oxides (HFOs) as a key control of As mobility in the aquifer. Dissolved As is positively correlated to Fe and NHþ 4 and negatively to the oxidizing-reducing potential (ORP). Negative correlation between As and groundwater head levels suggests a redox control by rainfall-driven recharge, which adds oxidants to the aquifer while progressively attenuating As. This mechanism is tested using process-based geochemical modeling, which simulates different transport modalities of oxidants entering the aquifer. Starting from reducing aquifer conditions, the model reproduces correctly the observed ORP and the trends in As and Fe, when the function describing the occurrence of oxidizing events scales according to the temporal occurrence of rainfall events. Heterogeneity can strongly control the local-scale effectiveness of recharge as a natural As attenuating factor, requiring a different model analysis to be properly assessed and to be developed in a follow-up study.