**Job Description**
This research position focuses on developing theoretically grounded methods for inference and spatiotemporal prediction using opportunistic samples, particularly for environmental monitoring and mapping. The role addresses the challenges posed by irregularly spread and potentially unrepresentative environmental observation data, which can lead to poor model performance and untrustworthy maps. The aim is to synthesize and evaluate novel approaches to quantify uncertainty and correct for spatial and sampling biases inherent in such data, with applications to properties like forest biomass and soil organic carbon.
**Skills & Abilities**
• Strong methodological background covering spatial sampling, design-based estimation, model-based prediction (geostatistics, machine learning) and uncertainty assessment.
• Proficiency in high-level programming languages such as Python or R.
• Excellent scientific writing skills in English.
• Strong interest in environmental characterization.
• Proactive, inquisitive, enthusiastic, and creative mind-set.
• Command of the English language at C1 level.
**Qualifications**
Required Degree(s) in:
• Geo-Information Science
• Physical Geography
• Remote Sensing
• Applied Mathematics
• Statistics
• Closely related field
**Experience**
Other:
• Strong methodological background in spatial sampling, design-based estimation, model-based prediction (geostatistics, machine learning) and uncertainty assessment.
Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!
