> Markdown version of [/jobs/ext/4798195-postdoctoral-researcher-machine-learning-river-forecasting](https://www.wearedevelopers.com/jobs/ext/4798195-postdoctoral-researcher-machine-learning-river-forecasting). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Postdoctoral Researcher - Machine Learning River Forecasting - **Company:** University of Minnesota - **Location:** Blacksburg, VA, United States - **Salary:** $62,232 - $65,000 - **Contract:** Permanent contract - **Skills:** 3d Models, Artificial Intelligence, Computer Programming, Github, Python (Programming Language), Laboratory Information Management Systems, Machine Learning, Open Source Technology, Tensorflow, Scientific Computating, Deep Learning, Information Technology, Data Pipelines, Recurrent Neural Networks - **Published:** November 20, 2026 - **Apply:** https://jobs.chronicle.com/apply/38066621/postdoctoral-researcher-machine-learning-river-forecasting?LinkSource=JobDetails ## About the Role The University of Minnesota Climate Adaptation Partnership and Department of Soil, Water, and Climate is seeking a highly motivated, independent Postdoctoral Researcher to lead innovative research at the intersection of knowledge-guided machine learning (KGML), Earth observations, and applied operational hydrology. This position will contribute to jump-starting a dynamic research lab, and play a key role in developing quantitative modeling and scientific approaches of KGML models on a newly awarded NASA-funded project focused on river forecasting and water resources decision-support across the Upper Mississippi River (UMR) Basin. The ideal candidate is an independent thinker and collaborative leader, ready to drive scientific publications immediately, and foster an inclusive, supportive lab culture. While strong experience in deep learning/physics-informed ML is preferred, candidates with quantitative and programming skills with a subject-matter expertise in large-river hydrology, coupled surface water-groundwater dynamics, irrigation/pumping, reservoir operations, and/or coupled human-water systems who are enthusiastic about expanding into AI/ML approaches are strongly encouraged to apply., * Ph.D. in Hydrology, Civil/Environmental Engineering, Geosciences, Data Science, Applied Mathematics, Physics, Computer Science, or a related quantitative field. * Demonstrated track record of peer-reviewed scientific publications. * Proficiency in Python and/or R * Strong communication skills and a commitment to fostering a collaborative, positive lab environment. Preferred / Desired Expertise * Experience and published track record using standard scientific computing and deep learning toolkits (e.g., Torch, TensorFlow, or similar). * Experience with physics-informed machine learning, encoder-decoder architectures, or multi-task learning. * Background in large-scale hydrologic modeling, coupled surface water-groundwater systems, reservoir management, irrigation/pumping dynamics, or human-water interactions. * Experience building real-time workflows and data dashboards (e.g., Shiny apps * Familiarity with satellite remote sensing products (e.g., SWOT, GRACE, soil moisture datasets). * Familiarity with meteorological forecast models and data pipelines, especially in the S2S timeframe (e.g., NOAA GEFS, ECMWF, etc.) ## Description Research & Scientific Publishing (85%) * Develop, train, and evaluate novel knowledge-guided machine learning architectures (e.g., encoder-decoder models, LSTM, multi-task learning) integrating multi-modal NASA Earth Observations (SWOT, GRACE/-FO, SPoRT-LIS, NLDAS-3) to forecast river flow, water surface elevation, and impacts of upstream water use on river channel navigability. * Lead the drafting and submission of high-impact, peer-reviewed journal publications. Lab Leadership & Mentorship (5%) * Serve as a cornerstone researcher helping to build and shape the lab's technical foundation and culture. * Be a resource to graduate and undergraduate researchers on computational workflows, scientific writing, and quantitative methods. Stakeholder Engagement & Transboundary Collaboration (10%) * Collaborate directly with regional and federal partners, including the Upper Mississippi River Basin Association (UMRBA), NOAA, and the US Army Corps of Engineers, to co-design modeling frameworks, support development of educational materials around ML modeling approaches for water resource managers, and participate in project workshops. * Software & Open Science Management + Maintain reproducible, open-source code repositories (GitHub) and dataset pipelines adhering to FAIR data principles.