Postdoc In Machine Learning And Urban Water Scarcity Modelling 80 100 Fmd

Laplace Apply; Birmensdorf (ZH); A distancia; CHF 75.000 - 110.000; Jornada completa

Descripción de la vacante

Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) in Birmensdorf seeks a two-year Postdoc in Machine Learning and Urban Water Scarcity Modelling. The role links hydrological models with subseasonal climate predictions and develops ML tools for city-scale forecasts.

The position emphasizes Python/R programming, uncertainty-aware forecasts, and collaboration with ETH-domain partners. English fluency and published research are expected for this data-intensive role.

Formación

• Experience with machine learning methods for time-series forecasting.
• Proficiency in Python or R for data analysis and modelling.
• Familiarity with graph neural networks and LSTM architectures.

Responsabilidades

• Develop and validate ML models to forecast urban water scarcity.
• Integrate hydrological and climate data with subseasonal predictions.
• Publish results and contribute to interdisciplinary collaborations.

Conocimientos

LSTM

Graph Neural Networks

Probabilistic forecasting

Python

R

Herramientas

Python

R

Descripción del empleo

Postdoc In Machine Learning And Urban Water Scarcity Modelling 80 100 Fmd

Swiss Federal Institute For Forest Snow And Landscape Research Wsl

15 November 2026; no exact cutoff time confirmed on the listing

About This Opportunity

The Swiss Federal Institute for Forest, Snow and Landscape Research WSL is recruiting a two-year postdoc in Birmensdorf for its WaterScarCity project in the NOVA-City research programme.

The Swiss Federal Institute for Forest, Snow and Landscape Research WSL is recruiting a two-year postdoc in Birmensdorf for its WaterScarCity project in the NOVA-City research programme. The project develops probabilistic subseasonal forecasts of urban water scarcity under more frequent heat and drought. The scientist connects hydrological models at WSL and collaborating ETH-domain institutions with subseasonal climate predictions, implements machine-learning approaches such as long short-term memory networks and graph neural networks, and works towards usable forecast tools for Swiss cities. The research integrates stakeholder-facing forecast applications, hydrometeorological data analysis, publications and interdisciplinary teamwork. Application date: 15 November 2026 (date only unless an exact time is independently specified).Who This Opportunity Is Best Suited For: Based on the advertised research and qualification requirements, the position may particularly suit doctoral graduates in environmental science, hydrology, climate science or related data-intensive disciplines who use Python or R, spatiotemporal modelling, machine learning and uncertainty-aware forecasts.Potential Challenges / Who May Find It Less Suitable: Applicants need experience interpreting weather or climate-model output and advanced programming; the role is 80–100% employment and requires published scholarship and English fluency.Overall Opportunity Assessment: The distinguishing research activities and working conditions described above determine the main applicant trade-offs; applicants should compare the documented duties with their professional research goals.

Level Postdoc

Duration 2 years

Field Machine Learning And Urban Water Scarcity Modelling 80 100 Fmd

Requirements

Education

Experience

Technical Skills LSTM Graph Neural Networks Python R Probabilistic forecasting