Postdoctoral Research Fellow in Active Learning for Arctic observing systems (ref 303807)
Core
Developing actively learning observing systems for carbon, water, and energy exchange in Arctic environments using Bayesian inference, probabilistic modeling, and machine learning.
Role type
Postdoctoral Research Fellow in Active Learning for Arctic Observing Systems
Builds
Intelligent observing frameworks that adapt and learn from data to guide where, when, and how to observe next
Domain
Geosciences / Climate Science / Arctic Environmental Monitoring
Deliverable
production ML models
Required skills
Bayesian inference, probabilistic modeling, machine learning, data assimilation, land-surface modeling, boundary-layer modeling, field campaign execution, drone platform operation, satellite data integration
Preferred skills
Experience with eddy flux towers, expertise in actively learning experimental designs
Technologies
Bayesian inference frameworks, probabilistic modeling tools, machine learning libraries, data assimilation frameworks, satellite data processing tools
Responsibilities
Develop frameworks allowing environmental observing systems to adapt and learn from data; Integrate field observations (ground- and drone-based) and satellite data into land-surface and boundary-layer models; Participate in field campaigns in mainland Norway, Svalbard, and international Arctic sites; Engage in conference attendances and research visits with external collaborators
Seniority
Postdoctoral Researcher