Welcome to my professional portfolio! I’m a software developer with a Ph.D. in artificial intelligence applied to meteorology.

During my doctoral studies, I developed the DEVINE wind downscaling model and supplemented this model with an innovative corrective corrective strategy based on gradient descent. This work made it possible to perform high-resolution wind simulations over areas as large as mountain ranges and for periods as long as years – a feat that was not common before! With this developments, it’s now possible to simulate snow in mountain terrain at high resolution, including what happens to the snowpack during drifting snow episodes.

Before my Ph.D., I worked on Antarctic meteorology, spending countless hours studying outputs of the atmospheric model MAR. My focus was on the development of snow clouds during storms. These drifting-snow clouds, sufficiently thick and significant, can modify the structure of the lower atmosphere, making their study crucial for understanding the continent’s unique weather patterns.

But that’s not all! During my engeneering studies, I took a gap year and spent six months in the world’s northernmost city (Longyearbyen, Svalbard), where I studied Arctic geophysics. From boat trips in the icy oceans to snowmobile rides on glaciers, I embraced the harsh yet captivating Arctic terrain.

Fast forward to the present, I’m now a software developer at ACRI-ST, in Grasse, south of France. Here, I work on the reprocessing of the SLSTR instrument (level 1) from the satellite mission Sentinel 3. From high-res mountains to space, my perspective has skyrocketed! In my current and past experiences, I have primarily used Python, and I’ve grown quite fond of Xarray, TensorFlow and Dask librairies.

When I’m not coding up a storm, I’m out seeking one! Whether it’s running in the mountains, biking, playing soccer, or randonnée skiing.

Cheers,

CV:

Full CV here

  • BSc - 2012/2015 - Lycée Masséna/Centre international de Valbonne - Nice, Valbonne, France
  • Msc - 2015/2019 - Ecole Centrale de Lyon (2015 - 2019) - Lyon, France
    • Business developer intern - 2017 (6 months) - Ooshot - Paris, France
    • Spring semester - Jan. 2018 - July 2018 - UNIS - Svalbard, Norway
    • Research intern - 2019 (6 months) - IGE - Grenoble, France
  • PhD - 2020/2023 (ongoing) - Snow research center (CEN) / Météo-France / CNRM / CNRS - Grenoble, France
  • Software developer - ACRI-ST (in mission from Eekem consulting firm) - Grasse, France

Publications:

  • Le Toumelin, L., Gouttevin, I., Galiez, C., & Helbig, N. (2024). A two-fold deep-learning strategy to correct and downscale winds over mountains. Nonlinear Processes in Geophysics, 31(1), 75-97.
  • Haddjeri, A., Baron, M., Lafaysse, M., Le Toumelin, L., Deschamp-Berger, C., Vionnet, V., … & Dumont, M. (2023). Exploring the sensitivity to precipitation, blowing snow, and horizontal resolution of the spatial distribution of simulated snow cover. EGUsphere, 2023, 1-44.
  • Baron, M., Haddjeri, A., Lafaysse, M., Le Toumelin, L., Vionnet, V., & Fructus, M. (2024). SnowPappus v1. 0, a blowing-snow model for large-scale applications of the Crocus snow scheme. Geoscientific Model Development, 17(3), 1297-1326.
  • Helbig, N., Mott, R., Bühler, Y., Le Toumelin, L., & Lehning, M. (2024). Snowfall deposition in mountainous terrain: a statistical downscaling scheme from high-resolution model data on simulated topographies. Frontiers in Earth Science, 11, 1308269.
  • Le Toumelin, L., Gouttevin, I., Helbig, N., Galiez, C., Roux, M., & Karbou, F. (2023). Emulating the Adaptation of Wind Fields to Complex Terrain with Deep Learning. Artificial Intelligence for the Earth Systems, 2(1), e220034.
  • Kittel, C., Amory, C., Hofer, S., Agosta, C., Jourdain, N. C., Gilbert, E., Le Toumelin, L., Vignon, É., Gallée, H., and Fettweis, X.: Clouds drive differences in future surface melt over the Antarctic ice shelves, The Cryosphere, 16, 2655–2669, https://doi.org/10.5194/tc-16-2655-2022, 2022.
  • Hofer, S., Amory, C., Kittel, C., Carlsen, T., Le Toumelin, L., & Storelvmo, T. (2021). The contribution of drifting snow to cloud properties and the atmospheric radiative budget over Antarctica. Geophysical Research Letters, 48(22), e2021GL094967.
  • Le Toumelin, L., Amory, C., Favier, V., Kittel, C., Hofer, S., Fettweis, X., … & Kayetha, V. (2021). Sensitivity of the surface energy budget to drifting snow as simulated by MAR in coastal Adelie Land, Antarctica. The Cryosphere, 15(8), 3595-3614.
  • Amory, C., Kittel, C., Le Toumelin, L., Agosta, C., Delhasse, A., Favier, V., & Fettweis, X. (2021). Performance of MAR (v3. 11) in simulating the drifting-snow climate and surface mass balance of Adélie Land, East Antarctica. Geoscientific Model Development, 14(6), 3487-3510.

Talks and conferences:

  • 2023-12-27 - PhD Defense - Grenoble, France
  • 2022-12-15 - Downscaling and Post-processing Wind Fields in Complex Terrain with Deep Learning - Fall Meeting 2022. AGU
  • 2022-02-02 - Emulating an atmospheric model with deep learning to downscale winds fields in complex terrain - 3rd International Conference on Snow Hydrology
  • 2021-09-29 - Downscaling wind fields in complex terrain with deep learning: application to nivology - ERC RhEoVOLUTION - Valence, France
  • 2021-06-24 - Estimating drifting snow intensity with machine learning: preliminary results - INRAE - Grenoble, France
  • 2020-02-06 - Modelling drifting snow improves near-surface relative humidity and incoming longwave radiation simulations in Adélie Land with MAR - Laboratoire des Sciences et du Climat (LSCE) - Saclay, France