Postdoctoral Researcher in Forest CO₂ and Water Flux Partitioning using Machine Learning at ETH Zürich ETH Zürich in Switzerland

The Grassland Sciences Group at ETH Zürich is seeking a Postdoctoral Researcher to join the INETFLUX project, focusing on innovative technologies to partition carbon dioxide and evapotranspiration fluxes in forests. This international collaboration involves ETH Zürich, WSL (Switzerland), and CzechGlobe (Czech Republic), and aims to advance understanding of how forests respond to climate variability and extreme events through their carbon and water fluxes.

The research will develop and validate new machine learning approaches (including XGBoost and SHAP) to partition net ecosystem exchange (NEE) into gross primary production (GPP) and ecosystem respiration, as well as evapotranspiration (ET) into transpiration and evaporation. The project leverages eddy covariance flux observations, tree dendrometer and sap flow measurements, stable isotope data, and multi-site European forest datasets.

Key responsibilities include developing ML-based flux partitioning methods, identifying environmental drivers and forest responses to climate extremes, contributing to Swiss FluxNet measurements (with responsibility for one EC site), collaborating with international partners (including a 3-month research stay at CzechGlobe), and publishing scientific results. The position is based at ETH Zürich, Switzerland, with a start date of July 2026 (or by agreement) and a deadline for applications on 1 April 2026.

Applicants should have a PhD in micrometeorology, greenhouse gas exchange, tree or ecosystem physiology, or related fields, with strong skills in large data analyses and English. Experience in knowledge exchange and student supervision is a plus. The position is funded for up to three years, with salary and benefits according to ETH Zürich rules, including public transport, sports, childcare, and pension benefits.

To apply, submit your application online via the ETH Zürich portal, including a motivation letter, CV with publication list, transcripts, and contact information for two referees. For more information, contact Prof. Dr. Nina Buchmann ([email protected]). This is an excellent opportunity for researchers interested in combining environmental science, machine learning, and ecosystem research at a leading European institution.