Advancing Multimodal Earth Observation Foundation Models for Wildfire Risk and Vegetation Recovery Assessments

About the role

The participant will engage in a NASA-aligned research project advancing data-driven approaches to characterize wildfire risk and post-fire vegetation recovery across the western United States.

Responsibilities

• Develop an extensible, scalable framework that integrates structural, radar, spectral, and temporal information to continually update estimates of vegetation vulnerability and fire response.
• Collaborate on developing structural vegetation representations from LiDAR observations, including GEDI-derived canopy height, vertical structure, and aboveground biomass products.
• Research multimodal data fusion, collecting and analyzing data to explore how LiDAR-based observations can inform representations and encoder adaptations.
• Evaluate L-band SAR, particularly emerging observations from the NASA-ISRO Synthetic Aperture Radar (NISAR) mission, as a scalable source of information for vegetation structure, biomass, disturbance, and recovery.
• Model the relationships between LiDAR-derived metrics and NISAR observations, investigating whether SAR can accurately extrapolate LiDAR-constrained structural data across broader spatial and temporal scales.
• Evaluate encoder adaptations that incorporate both synthetic aperture radar and LiDAR-derived vegetation characterizations into multimodal geospatial learning pipelines.
• Analyze models such as NASA’s Prithvi, alongside other relevant foundation-model architectures and fine-tuning strategies.
• Explore adapting these models for application in California using GEDI products, NISAR L-band SAR, optical Earth observations, climatic indicators, and fire-severity datasets.
• Gain valuable experience in illuminating the critical relationships among pre-fire vegetation structure, climatic stress, and observed burn severity, while using post-fire observations to quantify structural loss and recovery.
• Enhance their educational background in large-scale vegetation and wildfire modeling while gaining knowledge directly related to the agency's mission.

Requirements

• Hold or be pursuing a doctoral degree in Geography, Earth Science, Remote Sensing, Computer Science, Forestry, Ecology, or a related discipline.
• Strong foundation in geospatial analysis or computational modeling.
• Experience exploring machine learning and deep learning techniques for geospatial applications.
• Technical proficiency in scientific programming (Python or R) and deep learning frameworks (PyTorch or TensorFlow).
• Experience processing large spatial datasets using cloud or high-performance computing environments.
• A foundational understanding of fire ecology, forest dynamics, or aboveground biomass estimation.

Qualifications

• Candidates should possess academic research experience with remote sensing data, specifically LiDAR (e.g., GEDI), Synthetic Aperture Radar (SAR), and multispectral optical time-series.
• Desirable experience exploring machine learning and deep learning techniques for geospatial applications.
• Technical proficiency in scientific programming (Python or R) and deep learning frameworks (PyTorch or TensorFlow).
• Experience processing large spatial datasets using cloud or high-performance computing environments.
• A foundational understanding of fire ecology, forest dynamics, or aboveground biomass estimation.

Skills

• Geospatial analysis
• Remote sensing data
• Machine learning and deep learning techniques
• Scientific programming (Python or R)
• Deep learning frameworks (PyTorch or TensorFlow)
• Fire ecology
• Forest dynamics
• Aboveground biomass estimation

Benefits

• Opportunity to work with leading experts in the field.
• Competitive salary and benefits package.
• Flexible schedule and remote work options.
• Access to state-of-the-art facilities and equipment.

Pay

Salary range: $70,000 - $90,000 per year.

Schedule

Full-time, one- to three-year appointment.