Postdoc: Geospatial AI Modelling & Uncertainty Quantification of Carbon

Are you a data scientist interested in designing and implementing process-informed machine learning and uncertainties quantification methods? Join us as a postdoc and work on carbon turnover models and the fusion of data science forecasting methods with process-based models (hybrid modelling) to map soil and biomass carbon fluxes across Europe at high resolution.

Your job
This position is embedded in a multi-institutional EU-funded project Intergenerational Open Geospatial Carbon Registry (OGCR). The project is aimed at quantifying and mapping carbon storage potential and future carbon removal and carbon farming policy scenarios. It integrates process-based knowledge with machine learning and especially aims to spatially quantify uncertainties.

You will work closely with the Utrecht University team and OpenGeoHub together with other project partners, to develop surrogate and hybrid modelling frameworks combining process-based models with data science methods. A second focus will be to establish methods for geospatial uncertainty quantification of such models for aggregated units to support pan-European mapping of carbon storage potential and contribute to interactive uncertainty visualisations and dissemination of results tailored to stakeholder needs.

Your key responsibilities include:

• designing and implementing process-informed machine learning and data augmentation for soil and biomass carbon forecasts and scenario modelling across Europe;
• developing and benchmarking uncertainty quantification methods for space-time predictions and for spatial blocks;
• developing visualisation prototypes to communicate uncertainty to end-users;
• contributing to a computational framework for data production in cooperation with Research Software Engineers;
• working closely with the workpackage team and collaborating with partners across Europe: data sharing, code exchange, joint publications.

• You hold a PhD (or near completion) in statistics, applied mathematics, data science, environmental modelling, geosciences, or related field with strong quantitative focus.
• You have a deep understanding of statistical uncertainty quantification methods, sampling strategies, and error propagation techniques.
• You have experience in spatial-temporal statistics, kriging methods, and handling autocorrelation.
• You are interested in environmental biomass and soil mapping and modelling.
• You have good programming skills in Python and/or R; you are familiar with reproducible coding and automated (geospatial) data analysis.
• You have excellent scientific writing and communication skills in English.
• You show willingness to collaborate in multidisciplinary teams and to mentor students.

The following qualities are assets, but not required:

• You have prior experience in hybrid modelling (process-informed machine learning) and integrating uncertainty quantification into these workflows.
• You are familiar with environmental or soil science applications (e.g., carbon, nitrogen, biomass modelling).
• You have experience with interactive visualisation of uncertainty (e.g., dashboards, uncertainty mapping).
• You have experience with HPC or parallel computing for computationally intensive tasks.

• A position of 1.0 FTE for 30 months or 0.8 FTE for 37 months;
• access to computational resources (HPC), GIS/data infrastructure, and datasets via collaborative networks;
• a supportive, interdisciplinary research environment within the Faculty of Geosciences, national research institutes, and EU consortia;
• Opportunities to lead subprojects, co-supervise MSc students, and build your academic profile.
• a gross monthly salary between €3,546 and €5,538 in the case of full-time employment (salary scale 10 under the Collective Labour Agreement for Dutch Universities (CAO NU));
• 8% holiday pay and 8.3% year-end bonus;
• a pension scheme, partially paid parental leave and flexible terms of employment based on the CAO NU.

In addition to the terms of employmentlaid down in the CAO NU, Utrecht University has a number of schemes and facilities of its own for employees. This includes schemes facilitating professional development, leave schemes and schemes for sports and cultural activities, as well as discounts on software and other IT products. We also offer access to additional employee benefits through our Terms of Employment Options Model. In this way, we encourage our employees to continue to invest in their growth. For more information, please visit Working at Utrecht University.

A better future for everyone. This ambition motivates our scientists in executing their leading research and inspiring teaching. At Utrecht University, the various disciplines collaborate intensively towards major strategic themes. Our focus is on Dynamics of Youth, Institutions for Open Societies, Life Sciences and Pathways to Sustainability. Sharing science, shaping tomorrow.

Utrecht University’s Faculty of Geosciences studies the Earth: from the Earth’s core to its surface, including man’s spatial and material utilisation of the Earth – always with a focus on sustainability and innovation. With 3,400 students (BSc and MSc) and 720 staff, the faculty is a strong and challenging organisation. The Faculty of Geosciences is organised in four departments: Earth Sciences, Human Geography & Spatial Planning, Physical Geography, and Sustainable Development.