{"id":22415,"date":"2025-01-23T09:29:53","date_gmt":"2025-01-23T15:29:53","guid":{"rendered":"https:\/\/uwm.edu\/engineering\/?p=22415"},"modified":"2025-01-23T09:29:54","modified_gmt":"2025-01-23T15:29:54","slug":"nosonovsky-blends-surface-science-with-machine-learning-to-predict-beach-contamination","status":"publish","type":"post","link":"https:\/\/uwm.edu\/engineering\/nosonovsky-blends-surface-science-with-machine-learning-to-predict-beach-contamination\/","title":{"rendered":"Nosonovsky blends surface science with machine learning to predict beach contamination"},"content":{"rendered":"\n

A interdisciplinary 51ÁÔÆæ research team, including Michael Nosonovsky, professor, mechanical engineering, collaborated to determine how to predict E. coli outbreaks at beaches more effectively.<\/p>\n\n\n\n

Their goal was to identify the key sand conditions linked to E. coli growth and determine the best machine-learning method to predict these conditions.<\/p>\n\n\n\n

\"\"
Michael Nosonovsky<\/figcaption><\/figure>\n\n\n\n

Their findings were published in an article<\/a> that appeared in a 2024 volume of the journal Surface Innovations<\/em>.<\/p>\n\n\n\n

E. coli bacteria are often used as indicators of water contamination, and elevated levels are one of the main reasons for beach closures. The researchers focused on how the physical and chemical properties of sand influence the survival and spread of these bacteria.<\/p>\n\n\n\n

\u201cBacterial contamination of beach sand poses a public health problem,\u201d Nosonovsky said. \u201cSo, it\u2019s important to establish correlations between surface properties of sand and biocontamination, allowing us to predict and prevent the latter.\u201d<\/p>\n\n\n\n

Nosonovsky, whose expertise is tribology \u2013 the study of surfaces and friction \u2013 said that how sand interacts with water plays an important role in bacterial growth.<\/p>\n\n\n\n

The work was conducted using data from Bradford Beach on Milwaukee\u2019s lakefront. The researchers tested five different machine learning techniques and concluded the artificial neural network (ANN) technique outperformed other models in predicting\u00a0E. coli\u00a0concentrations.<\/p>\n\n\n\n

The ANN model identified three critical factors predicting E. coli levels in sand:<\/p>\n\n\n\n