Chronic exposure to arsenic (As) in groundwater is a staggering global public health crisis and yet, we lack a complete understanding of the environmental conditions that govern As mobility and toxicity in groundwater and are unable predict groundwater As concentrations with enough confidence to make effective management decisions. The objective of this project is to identify key hydrologic and biogeochemical variables that control groundwater As concentrations and heterogeneity across spatial scales in Southeast Asia and the USA. We then aim to develop clear mechanistic linkages and high-resolution geospatial information that can be used with machine learning to evaluate and predict groundwater As contamination. This project involves the integration of various types of large datasets from remotely-sensed and field-collected measurements (e.g., surface hydrology and topography, groundwater geochemistry, climate, and population density). We are looking for a student to advance the connections between key environmental variables and groundwater As contamination across scales. The student will receive experience and mentorship in cutting-edge research that crosses interdisciplinary fields, and will have the opportunity to lead their own project and acquire analytical skills using creative measures, which can involve remote sensing, geospatial methods, statistics and graphing, machine learning, and predictive modeling.

This is an UNPAID research project.

Faculty Advisor

Project Timeline

  • Earliest starting date: 3/2/2021
  • End date:
  • Number of hours per week of research expected during Spring 2021: ~20
  • Number of hours per week of research expected during Summer 2021: ~20

Candidate requirements

  • Skill sets:
    • The student’s anticipated tasks may include:
      1. The aggregation of existing datasets and generation of new data types
      2. Data synthesis and analysis using geospatial and visualization techniques
      3. Development of mechanistic linkages with groundwater As contamination
    • The student will also have the opportunity to:
      1. Leverage machine learning to predict groundwater As concentrations across spatial scales
      2. Pair predictions with population density data to evaluate risk of exposure within vulnerable or underserved communities
      3. Integrate temporal climate data to evaluate future scenarios. All tasks can be completed remotely if necessary.
    • These tasks require the following desired (although not necessary) skills:
      1. Coursework in environmental science, geoscience, and statistics
      2. Proficiency and interest in large data analysis
      3. Familiarity and interest to learn geographical information system (GIS) software and R statistical computing platform
      4. Experience or interest in learning data graphing and visualization techniques in R
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: eligible
  • Academic Credit Possible: No