Introduction

UNIL is a leading international teaching and research institution, with over 5,000 employees and 17,000 students split between its Dorigny campus, CHUV and Epalinges. As an employer, UNIL encourages excellence, individual recognition and responsibility.

Presentation

Recent progress in computer vision has accelerated the development of statistical downscaling, which uses statistical models to improve the spatiotemporal resolution of impactful climate variables, such as extreme temperatures, wind gusts, and precipitation. Machine learning (ML)-based super-resolution algorithms, which learn from data how to best generate high-resolution images from their low-resolution version, are gaining traction because of their improved accuracy and low  omputational cost once trained. However, they are rarely designed to perform well on extremes, and their robustness is usually only tested in the present climate, where training data are available. These limitations prevent the widespread adoption of modern ML to better constrain uncertainties in the forecasting of local extremes and in the high-resolution projections of climate change.
To address these limitations, our project leverages recent developments in deep learning and geostatistics1 to design hybrid statistical-physical methods helping ML frameworks generalize to climate change and extreme events. We will test these methods for two applications that combine downscaling with prediction over Switzerland: future climate projections and medium-range forecasting.

For that purpose, we propose two synergistic PhD projects on Machine Learning for Weather/Climate Super-Resolution :

The first project generates spatially-resolved Swiss climate change scenarios that ensure physical consistency and preserve long-term trend.

The second project downscales medium-range forecasts over Switzerland, including small-scale features ignored by the original forecast.

In both projects, we will explore the added value of state-of-the-art ML for atmospheric science, which remains challenging to understand.

Both PhD positions will be hosted within UNIL’s recently established Expertise Center for Climate Extremes, and will include collaboration opportunities with research groups from the institutions listed below:
● MeteoSwiss
● LSCE-IPSL
● University of California, Irvine
● NVIDIA (Climate Simulation Team)

Job information

Expected start date in position : 01.10.2024 / to be agreed

Contract length : 1 year, renewable to a maximum of 4 years.

Activity rate : 100%

Workplace : Lausanne Mouline (Géopolis)

Your responsibilities

Technical Responsibilities:
Specific to the climate projection project:
● Develop and apply multivariate bias-correction methods suitable for the Swiss climate scenarios, focusing on enforcing physical consistency, maintaining inter-variable consistency, and evaluating spatial properties across downscaled outputs.
● Integrate and test new algorithms for trend preservation in the downscaled variables, ensuring that long-term climatic changes are accurately reflected in the projections.
● Collaborate with MeteoSwiss to ensure that the downscaled models align with the ongoing updates to Swiss climate change scenarios and are informed by the latest observational data.

Specific to the weather forecasting project:
● Design and implement machine learning models for medium-range weather forecasting that can handle initial conditions significantly different from those seen in the training data, especially under extreme weather conditions.
● Ensure the calibration of downscaled outputs for longer lead times as predicted distributions shift towards climatology.
● Develop and test feature transformation techniques that enhance the generalizability and accuracy of forecasts across complex topography, such as the Alpine region.
● Collaborate with MeteoSwiss to ensure that the downscaled forecasts align with ongoing forecasting and post-processing needs.

For both projects:
● Establish the broad applicability of new machine learning frameworks (new architectures, techniques to improve extrapolation/explainability, improved conditioning of the predicted distributions, etc.) for climate applications. You will receive support from the project’s team and have the opportunity to co-supervise Master's interns.
● Over the course of 4 years, complete 3-4 semesters of teaching assistantship in geoinformatics, scientific programming, or machine learning for Earth and environmental science courses (no more than approximately 5 hours/week).
● Given that the collaboration with MeteoSwiss offers the opportunity to root your research in practice, we encourage flexibility between Lausanne and the MeteoSwiss offices (Zürich, Geneva, Locarno).
 

Your qualifications

• Master’s degree in a quantitative field closely related to machine learning and/or climate science


• Strong background in scientific programming and data science


• Experience in manipulating scientific datasets, ideally including proficiency in Python.


• A solid foundation in applied mathematics and physics. We appreciate a range of competencies, including but not limited to calculus, differential equations, statistics, mechanics, and thermodynamics


• Strong communication skills in English


• Enthusiasm for both atmospheric/climate science and scientific machine learning


• (Preferred but not required) Experience in high-performance computing


• (Preferred but not required) Background in numerical weather prediction and/or climate change science


• (Preferred but not required) Teaching experience


• Note that proficiency in French and German is not required and free French and (Swiss) German courses are available at UNIL

What the position offers you

• We offer a nice working place in a multicultural, diverse and dynamic academic environment. Opportunities for professional training, a lot of activities and other benefits to discover.


• Annual salary of approximately CHF 45k-50k for up to 4 years, contingent upon satisfactory yearly reviews.


• Fully funded personal research equipment, including a laptop, desktop computer, monitor, etc.


• Fully funded research-related travel, including conferences, collaborations, etc.


• Fully funded open-access publication costs.


• 5 weeks of paid holidays, in addition to national holidays.


• Paid parental leave.


• Access to UNIL's high-performance computing facilities, offering millions of CPU/GPU hours, 1 PB of storage, etc., with additional CPU hours available for computationally intensive atmospheric simulations through collaborations.


• An international collaboration network.


• A friendly and cohesive culture at the Institute of Earth Surface Dynamics, including 1-2 day summer and winter retreats, usually in the Alps.


• Access to UNIL campus facilities, including a sports center with over 100 recreational options, campus-grown food, etc.

Contact for further information

Prof. Tom Beucler

tom.beucler@unil.ch

Your application

Deadline : 31.05.2024

Please, send your full application with all the following in PDF.

• Curriculum Vitae


• Copy of all university degree certificates and transcripts


• Names, affiliations, and email addresses of 2 references (e.g. Masters thesis advisor(s), academic staff members who have read your work, previous employers)


• Copy of one first-author research report (can be a manuscript, a thesis, or a class paper)


• Personal Statement (no more than 2 pages excluding bibliography), including:
  
  
  
  • A ~250-word description of a possible PhD project related to the position’s topic
  
  
  • A short description of what has been your favorite research experience so far and why
  
  
  • Your professional goals, and how this position might further them 
  
  
  • Your teaching methods (if you have no teaching experience: which teaching methods do you find most efficient?)
  
  
  • Your strategies to collaborate with colleagues of diverse backgrounds and experience
  
  
  
  

Only applications through this website will be taken into account.

We thank you for your understanding.

Additional information

We are dedicated to fostering a diverse, equitable, and inclusive environment where all individuals are encouraged to apply, regardless of their background. UNIL is committed to equal opportunities and diversity.
www.unil.ch/egalite

UNIL supports early career researchers.
www.unil.ch/graduatecampus

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)