Postdoctoral Associate - Earth Environmental Planetary Sciences

Rice University • Houston, TX

16h • Onsite

About The Position

The MUSE (Multimodal AI for Earth System Discovery) research cluster at Rice University seeks a Postdoctoral Research Associate to develop multi-domain Graph Neural Networks (GNNs) and foundation models for Earth system modeling, state estimation, and forecasting. The work focuses on reusable, scale-adaptive, graph-based architectures that learn unified representations across Earth science applications, including hydrology, flood dynamics, ice-sheet and aquifer mechanics, and earthquake processes. The research aims to create transferable, physics-informed models that infer hidden Earth states, identify governing relationships, and quantify predictive uncertainty across interconnected Earth domains.

The initial appointment is for one year and may be renewed for up to two to three years, subject to performance and funding availability. The position is exclusively on-site in Houston, Texas. It is grant-funded, and continued employment depends on renewal of funding. The position is salaried and exempt from overtime under the FLSA.

The associate will work with a cross-departmental faculty team and collaborators in Computer Science, Electrical & Computer Engineering, and Earth, Environmental and Planetary Sciences. The role includes developing and benchmarking graph models, evaluating cross-domain transfer learning, incorporating physical constraints and uncertainty quantification, supporting interdisciplinary proposal development, and disseminating findings through publications and conference presentations.

Requirements

• Ph.D. in Computer Science, Data Science, Geophysics/Earth Sciences, Applied Mathematics, Electrical Engineering, Environmental Engineering, or a related quantitative field.
• Strong background in deep learning on graphs (GNNs), geometric deep learning, or large-scale foundation model architectures, with interest or background in applying these methods to physical or geoscientific systems.
• High proficiency in Python and deep learning frameworks such as PyTorch, PyTorch Geometric, or DGL.
• Demonstrated track record of peer-reviewed publications in high-impact computational or geoscience journals and conferences.

Nice To Haves

• Experience with spatio-temporal or irregularly sampled physical data, such as remote sensing, streamflow networks, seismic arrays, InSAR, or terrain data.
• Experience with Physics-Informed Neural Networks (PINNs), neural operators such as FNO or DeepONet, or neural surrogate modeling for physical processes.
• Background in uncertainty quantification or hybrid machine learning frameworks combining data-driven models with physical priors.
• High-performance computing or cloud computing experience, including distributed training such as CUDA or multi-GPU training.

Responsibilities

• Design, build, and benchmark multi-domain graph neural network architectures and neural surrogates for complex spatial networks, irregular geometries, and spatio-temporal prediction tasks.
• Integrate multimodal, heterogeneous Earth observations and evaluate model transferability across water, floods, cryosphere, and earthquake domains.
• Incorporate physical constraints, including partial differential equations and mass or momentum conservation laws, into graph architectures and uncertainty quantification frameworks.
• Assist cluster faculty with interdisciplinary research proposals, including proposals to NSF, DOE, and NASA.
• Collaborate with researchers in Computer Science, Electrical & Computer Engineering, and Earth, Environmental and Planetary Sciences at Rice University.
• Publish research in machine learning venues and geoscientific journals, and present at national and international conferences.

Benefits

• Full Rice University benefits package.
• Interdisciplinary co-mentorship from faculty spanning machine learning, GNN theory, remote sensing, and geophysics.
• Access to Rice’s High-Performance Computing clusters and specialized GPU acceleration nodes.
• Dedicated mentorship and career guidance for academic or industry research careers.
• Competitive salary.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree