A machine learning-based approach for mapping leachate contamination using geoelectrical methods

Leachate is the main source of pollution in landfills and its negative impacts continue for several years even after landfill closure. In recent years, geophysical methods are recognized as effective tools for providing an imaging of the leachate plume. However, they produce subsurface cross-sections in terms of individual physical quantities, leaving room for ambiguities on interpretation of geophysical models and uncertainties in the definition of contaminated zones. In this work, we propose a machine learning-based approach for mapping leachate contamination through an effective integration of geoelectrical tomographic data. We apply the proposed approach for the characterization of two urban landfills. For both cases, we perform a multivariate analysis on datasets consisting of electrical resistivity, chargeability and normalized chargeability (chargeability-to -re-sistivity ratio) data extracted from previously inverted model sections. By executing a K-Means cluster analysis, we find that the best partition of the two datasets contains ten and eleven classes, respectively. From such classes and also introducing a distance-based colour code, we get updated cross-sections and provide an easy and less ambiguous identification of the leachate accumulation zones. The latter turn out to be characterized by coor-dinate values of cluster centroids<3 omega m and >27 mV/V and 11 mS/m. Our findings, also supported by borehole data for one of the investigation sites, show that the combined use of geophysical imaging and unsupervised machine learning is promising and can yield new perspectives for the characterization of leachate distribution and pollution assessment in landfills.