Postdoctoral Research Associate - Plant Ecophysiology & AI

Requisition Id 16704 

Overview:

We are seeking a Postdoctoral Research Associate who will focus on AI-enabled plant ecophysiology to improve mechanistic understanding and predictions of ecosystem responses to environmental change. This position resides in the Ecosystem Processes Group in the Environmental Sciences Division at Oak Ridge National Laboratory (ORNL). The selected candidate will work with Dr. Jeffrey Warren and Dr. Lianhong Gu and collaborate with researchers in the ORNL Terrestrial Ecosystem Science (TES) Scientific Focus Area (SFA) to integrate experimental measurements and trait databases to assess ecosystem response to environmental forcing.

 

The primary research focus is AI-forward, experiment-driven. This position encourages leveraging AI/ML methods to assess plant physiological responses to current or imposed environmental conditions. Research may leverage:

• Laboratory, growth chamber and field experimental data, and/or new measurements to quantify molecular to ecosystem scale responses to warming, drought, and elevated CO2 (e.g., gas exchange, fluorescence, hydraulics, respiration, water potential, thermal tolerance)
• Trait synthesis at scale (e.g., using trait databases TRY, FRED, LeafWeb, Sapfluxnet, PSInet) to translate trait variation into model parameter priors and functional constraints, and to explore parameter relationships with environmental conditions
• Hybrid modeling that combines mechanistic ecophysiology with AI, such as:
  • Physics-informed machine learning and neutral networks to investigate plant physiological / abiotic relationships
  • Bayesian statistics and neural and Gaussian-process emulators for accelerating parameter estimation and uncertainty propagation
  • Selective cross-scale evaluation using complementary ecosystem observations (e.g., experiments) to test how AI-informed analyses can contribute to ecosystem-scale simulations.

 

Major Duties/Responsibilities:

• Conduct observational and manipulative ecophysiological research to quantify plant and ecosystem responses to abiotic stressors (e.g., heat and drought) and identify mechanistic resilience thresholds across the soil–plant–atmosphere continuum
• Lead soil-plant-atmosphere hydraulics measurements at the Missouri flux tower site (MOFLUX), including plant hydraulics, rooting depth, canopy temperature and other parameters for tree species that vary in sensitivity to drought. Scale water flux measurements to the site level for comparison with carbon/water exchange based on eddy flux measurements
• Use AI/ML data integration, modeling and trait databases to scale up ecophysiological mechanisms of ecosystem water and carbon flux from MOFLUX to broader region/ecotone/biome response to changes in seasonality of precipitation, temperature, and atmospheric constituents
• Contribute to other AI/ML synthesis activities - e.g., neutron imaging, SPRUCE hydraulic/thermal thresholds and scaling
• Produce and publish AI-ready datasets to the ESS-DIVE data archive and BER data lakehouse
• Develop AI pipelines for experimental ecophysiology, including automated QC and uncertainty-aware learning from sparse/noisy measurements
• Build hybrid mechanistic–AI models linking traits to photosynthesis, stomata, hydraulics, and respiration across experimental gradients
• Benchmark and stress-test model improvements against experimental datasets (e.g., SPRUCE, MOFLUX and related lab/field measurements), and publish open reproducible code and results
• Deliver ORNL’s mission by aligning behaviors, priorities, and interactions with our core values of Impact, Integrity, Teamwork, Safety, and Service. Promote equal opportunity by fostering a respectful workplace – in how we treat one another, work together, and measure success.

 

Basic Qualifications:

• PhD (completed by start date) in plant ecophysiology, plant biology, ecology, Earth system science, or related field 
• Strong understanding of plant physiological processes (photosynthesis, stomata, hydraulics, respiration, plant–water relations) 
• Demonstrated strength in quantitative methods and programming (e.g., Python or R; reproducible workflows; version control)
• Experience or interest in AI/ML application to ecophysiological research

 

Preferred Qualifications:

• H