Two Funded Masters Internships at UNIL’s Expertise Center for Climate Extremes

Scroll Down

Applications should be sent to tom.beucler@unil.ch and will be considered on a rolling basis starting on December 8th, 2025 (see below for guidelines on how to apply).  The preferred start date is anytime starting in March 2026, with a start in June 2026 at the latest to ensure the internship concludes by the end of the academic year. For eligibility reasons, applicants must either be enrolled in a Master’s program at a university based in the EU or EFTA area, or hold citizenship from one of these countries.

Internship 1: Joint Downscaling and Parameterization of Observed Cloud Cover via 3D Conditional Diffusion

Collaborators: Emiliano Dìaz (UVEG), Fangfei Lan (UNIL) 

Clouds remain at the center of uncertainty in climate projections: limited horizontal resolution in climate models means that cloud systems such as storms are only crudely represented, leading to persistent biases in cloud cover and radiative fluxes. At the same time, this coarse resolution makes it impossible to use raw model output directly for local-scale impact studies, motivating statistical downscaling, usually done in a post-hoc fashion. In this internship, you will tackle these two issues jointly by using generative models to both downscale 3D cloud fields and extract physically meaningful cloud-cover profiles for use in subgrid parameterizations.

You will work with a new observational dataset that reconstructs 3D cloud fields and use it as a target to train 3D diffusion models. The project will first focus on learning to generate realistic 3D cloud scenes from observations, and then on conditioning these scenes on coarse environmental profiles (e.g. temperature, humidity, and condensates amount). From these generated fields, you will compute vertical profiles of cloud area and volume fraction at coarse resolution, yielding a cloud-cover parameterization that is directly trained on observations. This provides a unified, data-driven framework for both downscaling and parameterizing cloud cover, with improved cloud representation for radiation and microphysics schemes in climate models.

You will gain experience handling large geophysical datasets, designing and training conditional generative models, and analyzing their impact on cloud statistics relevant for climate modeling. If time allows, the learned cloud-cover parameterization may be coupled back into the ICON climate model, building on recent work showing that machine-learned cloud schemes can systematically reduce cloud-cover biases and improve simulated radiative fluxes.

Some references:

Internship 2: Symbolic Discovery of a Scale-Aware Equation for Tropical Precipitation

Collaborators: David Neelin, Fiaz Ahmed (UCLA), Frederick Iat-Hin Tam (UNIL)

Understanding and accurately representing precipitation processes in tropical regions is vital for improving data-driven forecasting tools in the Tropics and global Earth system models. However, because of computational constraints, most Earth system models run at horizontal resolutions of ~25-50 km or coarser, so the subgrid processes that drive precipitation must be parameterized rather than explicitly resolved. Subgrid parameterizations often introduce significant biases in surface rainfall. Recent machine-learning-based parameterizations trained on high-resolution simulations can improve performance, but often lack interpretability and flexibility. It is also challenging to link ML parameterizations to known atmospheric processes, which undermines trust.

You will participate in a collaborative effort to discover simple, interpretable tropical rainfall equations with novel data-driven equation-discovery approaches (e.g., Grundner et al. (2024)). Previous ∂3AWN work has already shown that simple equations with only two vertically integrated predictors and one surface predictor can already outperform analytic baselines used to model precipitation in idealized studies. You will take a step further toward learning useful precipitation equations jointly from satellite images and meteorological reanalysis data. Satellite images provide rich information on different spatial patterns of rainfall organization, which potentially have implications for precipitation intensity (Bao et al. 2024). However, such information is still underutilized in parameterizations for weather and climate models.

You will work with the ERA5 reanalysis data and a tagged IMERG dataset of co-occurring atmospheric features and precipitation extremes, which spans diverse regimes such as tropical cyclones, large-scale organized convection, monsoon rainbands, and localized convective storms. The tagged dataset contains labels for different precipitating regimes, enabling the discovery of universal equations that can potentially work across cloud types. To build upon previous work, you will use novel data-driven techniques to find an analytic equation linking the vertical profile of thermodynamic variables and surface properties (e.g. land-sea fraction, statistical moments of orography) to satellite-observed surface precipitation. These equations encapsulate the primary mechanisms by which local environmental characteristics control surface rainfall. You will validate equations by evaluating to what extent these equations can generalize across cloud types, allowing us to test whether a single physical law can describe how the thermodynamic environment controls precipitation intensity across widely different cloud regimes. The ultimate goal of this project is to make these equations scale-aware, transitioning smoothly from a local (column-wise) relationship between the thermodynamic environment and precipitation at coarse resolution to a non-local-in-space relationship as spatial resolution increases. 

You will gain experience in handling satellite data and handling large geophysical dataset. You will also have the opportunity to run novel data-driven methodologies that are more suitable for scientific discovery than usual ML approaches, including sparse neural operators, symbolic regression, and integrating kernels. From the regular meetings with local and external collaborators, you will obtain valuable insights into what makes an equation interpretable, and trustworthy for the atmospheric sciences community. The unique collaboration between applied machine learning practitioners and theoretical meteorologists will place you in the frontier in ML-assisted scientific discovery in atmospheric sciences.

Some references:

Your Responsibilities

  • Conduct independent, innovative, and responsible research
  • Disseminate results through a publicly-available report at the end of the project, which may be your Masters thesis
  • Ensure clear communication and productive interactions with project collaborators through regular in-person or Zoom meetings
  • Openly discuss research obstacles and seek advice/help in the lab 
  • Make your research/code open and reproducible (e.g. through Github/Gitlab/arXiv)
  • Informally share research progress at the weekly ∂3AWN lab meeting
  • Actively participate in creating a collaborative and inclusive culture in the ∂3AWN lab and ECCE
  • Actively participate in the various ECCE events and activities (e.g., research seminars, informal seminars for early-career scientists, social events)

Your Qualifications

  • Bachelor degree in atmospheric/climate science, computer science or electrical engineering, physics, fluid mechanics or mechanical engineering, statistics, applied mathematics, or a closely related discipline
  • Strong background in physics and applied mathematics (preferentially including calculus, differential equations, statistics, mechanics, and thermodynamics) 
  • Experience reading, writing, and manipulating scientific datasets
  • Excellent skills in written and spoken English
  • Enthusiasm for atmospheric/climate science, scientific machine learning, and statistics
  • (Preferred but not required) Background in environmental science
  • (Preferred but not required) Experience in high-performance computing

Note that proficiency in French is not required and free French courses are available at UNIL during the academic semester.

Position perks

  • Monthly salary of CHF 1’820.90 for the duration of the internship (4-6 months)
  • Fully-funded personal research equipment (desktop computer, monitor, etc.)
  • Fully-funded open-access publication costs
  • Access to UNIL’s high-computing facilities (Millions of CPU/GPU hours, 1PB of storage, etc.), additional CPU hours available for computationally-intensive atmospheric simulations through collaborations
  • International collaboration network
  • A friendly and cohesive culture at the Institute of Earth Surface Dynamics including 1-day Summer and Winter retreats, usually in the Alps
  • A very interdisciplinary environment provided by the Expertise Center for Climate Extremes, including social events
  • Access to UNIL Campus facilities (Sports center with 100+ recreational options, campus-grown food, etc.)
  • (If applicable) Fully-funded research-related travel (conferences, collaborations, etc.)

Application Documents

  • Curriculum Vitae
  • Copy of all university degree certificates and transcripts
  • Name, affiliation, and email address of 1 reference (e.g. Bachelor thesis advisor(s), previous teachers, previous employers)
  • Copy of one first-author research report (can be a manuscript, a thesis, or a class paper) 
  • Personal Statement (no more than 1 page excluding bibliography), including:

– A ~200-word description of which project(s) you are interested in and your strategies to tackle it/them within a 4-6 months timeframe

– Your professional goals, and how this position might further them

– Your strategies to collaborate with colleagues of diverse backgrounds and experience

Applications should be sent to tom.beucler@unil.ch and are accepted on a rolling basis. The preferred start date is anytime starting in March 2026, with a start in June 2026 at the latest to ensure the internship concludes by the end of the academic year.

What is ECCE?

The recently established Expertise Center for Climate Extremes (ECCE) fosters collaboration between the Faculty of Business and Economics (HEC) and the Faculty of Geosciences and Environment (FGSE). Its focus is on researching the prediction of climate extremes and their impacts, along with assessing risks associated with these extremes in current and future climates. “Climate extremes” encompass weather extremes, climate anomalies, water extremes, and weather-related natural hazards. ECCE, grounded in interdisciplinarity, aims to leverage the faculties’ expertise in meteorology, climatology, natural processes, statistics (especially extreme-value theory), machine learning, insurance risk, and finance to create synergies. For more details, visit https://www.unil.ch/ecce/home.html. These internships will be hosted at the Data-Driven Atmospheric & Water Dynamics (∂3AWN) lab (https://wp.unil.ch/dawn/) of the FGSE, one of the research groups affiliated with ECCE.

Additional Information

  • The University of Lausanne is committed to equal opportunity and stands firm against all forms of discrimination.
  • The Faculty of Geosciences and Environment of the University of Lausanne adheres to the DORA agreement and follows its guidelines in the evaluation of applications (in short, quality over quantity)