This seed project spans two interdisciplinary collaborations across the College of Engineering, and College of Public Health that harness the power of information science and signal processing towards better understanding of contaminant fingerprints in the environment. In particular, the PI will investigate data-driven associations linking contaminant clusters to environmental, geographic and social drivers. This project will develop a data-driven infrastructure towards robust interpretation of raw signal and processed field  data, along with prediction models for success of intervention methods. While the focus of the work is chemical contaminants, the methods here apply equally to biological contaminants, e.g. water-borne fecal pathogens in soil and water.