Argonne National Laboratory, a U.S. Department of Energy National Laboratory located near Chicago, Illinois, has an opening for a Postdoctoral Appointee specialized in deep learning applications for hydrology and hydrodynamic modeling, especially physics-informed machine learning at the Department of Hydrology, Environmental Science Division.

The Postdoctoral Appointee will work toward advancing state-of-the art physics-informed artificial intelligence and machine learning (AI/ML) models to improve hydrologic systems modeling and near real-time forecasting at a high resolution. The project aims to develop a framework and standardized benchmark suite for scalable and robust physics-informed AI/ML for next-generation hydrologic and hydrodynamic modeling. The appointee will join a group of scientists working on this project supported by Argonne’s Center for Climate Resilience and Decision Science (CCRDS). Model development will utilize the leading high performance computing platforms at ALCF (https://www.alcf.anl.gov) and other Department of Energy computing platforms.

This is a two-year position that we want to fill immediately.

This position description documents the general nature and level of work but is not intended to be a comprehensive list of all activities, duties and responsibilities required of job incumbent. Consequently, job incumbent may be required to perform other duties as assigned.

Position Requirements

• Completed PhD within the last 0-5 years in hydrology, civil engineering or a related field
• Knowledge of key approaches for embedding physics in AI/ML models, especially neural operators, physics-informed neural networks, hybrid modeling, and regularization techniques
• Experience with various neural network architectures (e.g., graph neural networks, autoencoders, generative adversarial networks, etc.)
• Understanding of hydrologic and hydrodynamic processes and modeling
• Experience in applying AI/ML for hydrologic and hydrodynamic predictions
• Experience in using AI/ML frameworks (e.g., PyTorch, TensorFlow, Flux, or similar) on HPC systems
• Skilled in data analysis, statistics, and visualization, especially on large datasets
• Knowledge of developing flood observation training datasets from multiple sources
• Experience writing and modifying scientific code in Python, Julia, Fortran, and C++
• Effective written and oral communication skills
• Strong organizational skills and the ability to coordinate across a broad spectrum of activities
• Demonstrated ability to work independently and in a team environment
• Ability to model Argonne’s Core Values: Impact, Safety, Respect, Integrity, and Teamwork

Job Family

Job Profile

Worker Type

Time Type