Postdoctoral Scholar - AI in Earth and Environmental Sciences

Postdoctoral Scholar – AI in Earth and Environmental Sciences

Position in the Hydrogeochemistry and Environmental Data Sciences (HANDS) research group, focusing on AI/ML, foundation‑AI models, and data‑intensive Earth and environmental research.

Develop and apply artificial intelligence, machine learning, foundation‐model, and environmental data science approaches to large geochemical, hydrologic, geospatial, regulatory, and related Earth system datasets. Conduct research on energy and environmental systems, including oil and gas well condition and integrity‑related questions, and on global water and elemental cycles.

• Develop and apply AI/ML, foundation‑model, and data science approaches to large geochemical, hydrologic, geospatial, regulatory, and related Earth system datasets.
• Develop AI/ML‑enabled workflows to characterize energy and environmental systems, including oil and gas well condition and integrity‑related questions.
• Investigate foundation‑AI model applications in catchment sciences, including riverine hydrogeochemistry, watershed elemental cycles, water quality, terrestrial water and solute fluxes, and environmental prediction across scales.
• Integrate, clean, manage, and analyze heterogeneous observational, geospatial, remote‑sensing, modeled, regulatory, and environmental datasets from multiple sources.
• Build reproducible computational workflows for data synthesis, model development, feature engineering, representation learning, transfer learning, uncertainty assessment, visualization, and scientific interpretation.
• Evaluate and interpret model outputs in the context of hydrologic, geochemical, geologic, engineering, climatic, land‑use, and anthropogenic controls.
• Contribute to interdisciplinary research design, technical reporting, project coordination, and communication with collaborators and project partners.
• Prepare manuscripts for peer‑reviewed publication and contribute to conference abstracts, presentations, reports, and other scholarly products.
• Mentor and support graduate and undergraduate students in coding workflows, data analysis, reproducible research practices, and scientific communication.
• Participate in regular research group meetings and contribute to a collaborative, interdisciplinary environment.

• Ph.D. in geoscience, hydrology, geochemistry, environmental science, civil/environmental engineering, data science, computational geoscience, Earth system science, or a closely related field.
• Demonstrated experience in AI/ML, environmental data science, statistical modeling, or related quantitative methods.
• Strong quantitative, programming, and data analysis skills.
• Experience handling complex environmental, geospatial, hydrologic, geochemical, or Earth system datasets.
• Ability to develop reproducible computational workflows.
• Evidence of scientific communication through publications, presentations, reports, software, datasets, or other scholarly products.
• Ability to work independently and collaboratively in an interdisciplinary research environment.

• Experience with AI/ML or foundation‑model approaches in energy and environmental systems.
• Experience with oil and gas well datasets, well characterization, or subsurface energy systems.
• Experience with foundation AI models, representation learning, transfer learning, self‑supervised learning, deep learning, interpretable ML, uncertainty quantification, data assimilation, or related AI/ML approaches for scientific datasets.
• Experience applying AI/ML to catchment sciences, hydrology, hydrogeochemistry, water quality, watershed elemental cycles, river networks, or Earth system prediction.
• Experience with large environmental, geochemical, hydrologic, geospatial, regulatory, remote‑sensing, or Earth system datasets.
• Experience integrating diverse datasets such as stream chemistry, discharge, hydroclimatic forcings, land cover, lithology, soils, well records, regulatory data, remote‑sensing products, geospatial attributes, monitoring data, or modeled Earth system outputs.
• Experience developing predictive, interpretable, and transferable models for environmental, geologic, energy,…