Postdoc Fellowship in Data Science: Ann Arbor, MI

University of Michigan, Cooperative Institute for Great Lakes Research (CIGLR)
Ann Arbor, MI
Job Category
Post Doctoral Appointments
Last Date to Apply
The Cooperative Institute for Great Lakes Research (CIGLR) is seeking outstanding candidates for a postdoctoral scholar position in data science. In collaboration with the National Oceanic and Atmospheric Administration (NOAA) Great Lakes Environmental Research Laboratory (GLERL) and School for Environment and Sustainability (SEAS), the successful candidate will lead research that utilizes data science to advance hydrometeorological prediction and water management decision support. The postdoctoral fellow will be part of a large interdisciplinary team at GLERL, CIGLR, and SEAS that is developing the next generation prediction system for determining the mean and extreme water levels. This new system will provide the foundation for defining the risk of coastal inundation impacts across subseasonal to annual time scales for the Laurentian Great Lakes. Specifically, the postdoctoral fellow will utilize data-driven approaches to optimize the design of a next generation water level prediction system for subseasonal to annual predictions. Approaches will leverage the latest advancements in hydrometeorological data; modeling of meteorology, climate, and hydrology; and forecasting to characterize hydrometeorological variability across space-time scales, identify sources of uncertainty, and improve predictability of water supply and water levels. Work will be conducted as part of an interdisciplinary team bringing together expertise in meteorology and climate, hydrology, water management, and stakeholder engagement.
Required Qualifications PhD in hydroinformatics, statistics, mathematics, water resources engineering, or similar field. Demonstrated ability to conduct data-driven hydroclimate research using gridded atmospheric, land-surface, and/or hydrological model outputs for subseasonal, seasonal, and/or annual prediction time scales. Example approaches include use of stochastic methods, statistical modeling, and artificial intelligence (e.g., time series analysis, machine learning, deep learning, random forest ensemble learning, spatiotemporal data analysis). Experience with analyses to evaluate sources of uncertainty and/or predictability are particularly preferred. Experience working on gridded outputs from climate, atmospheric, and hydrological models, including netCDF, grib2, and HDF5 storage formats. Strong publication record in the relevant field, including at least one lead-author publication. Strong communication skills and demonstrated ability to work independently in collaboration with an interdisciplinary team. Proficiency with handling various data formats, such as NetCDF, GRIB2, ASCII, and shapefiles. This includes visualization, geospatial data analyses, and dealing with map projections using existing libraries for programming languages such as Python, R, and Matlab. Proficiency with working on a supercomputer or a cluster computing environment. This includes shell scripting, batch job submissions, and data transfer. Desired Qualifications Exposure to atmospheric and hydrological science, such as research that characterizes hydroclimatic variability across space-time scales. Understanding of global circulations, teleconnection patterns, and their impacts on regional climate (e.g., precipitation patterns). Experience using Great Lakes regional hydrological/climate datasets (e.g., Regional Deterministic Reanalysis System, the Canadian Precipitation Analysis system).
Contact Person
See application website
Bookmark the permalink.

Comments are closed.