The case of arsenic contamination in the Sardinian Geopark, Italy, analyzed using symbolic machine learning

Germana Manca, Guido Cervone

Research output: Contribution to journalArticlepeer-review

6 Scopus citations


This paper analyzes the relationship among different chemical pollutants retrieved from in situ measurements of underground and surface water in a region of possible development. The area of study is the former mine of the Iglesiente district, which is now a United Nations Educational, Scientific, and Cultural Organization (UNESCO) protected region in the island of Sardinia (Italy). A full chemical analysis of water/soil samples were collected at the site in 2004. The data show the presence of several toxic contaminants above the national legal threshold. A symbolic machine learning classifier is employed to learn strong patterns associated with a high level of arsenic (As) in the soil samples. The patterns discovered show complex relationships that include both high and low concentrations of different chemicals. The strongest patterns are found between As and the chemicals which are usually found in the soil. This implies that when As is dissolved in the water table, it is expected these other chemicals are also present. It emerges that a specific relationship of As-phosphates is outlined and is clearly shown by applying the symbolic machine learning classifier. This leads to an understanding of the behavior of these elements in the soil, potential impacts on ecosystems, as well as the pollution of groundwater. Finally, an assertion of the advantages of the algorithm quasi-optimal learning method is clarified in term of applicability in such circumstances.

Original languageEnglish (US)
Pages (from-to)400-406
Number of pages7
Issue number6
StatePublished - Sep 2013

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Ecological Modeling


Dive into the research topics of 'The case of arsenic contamination in the Sardinian Geopark, Italy, analyzed using symbolic machine learning'. Together they form a unique fingerprint.

Cite this