Florian Pinault

ORCID: 0000-0002-3003-3888
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Meteorological Phenomena and Simulations
  • Computational Physics and Python Applications
  • Scientific Computing and Data Management
  • Forecasting Techniques and Applications
  • Oceanographic and Atmospheric Processes
  • Climate variability and models

European Centre for Medium-Range Weather Forecasts
2022

Abstract There is a high demand and expectation for subseasonal to seasonal (S2S) prediction, which provides forecasts beyond 2 weeks, but less than 3 months ahead. To assess the potential benefit of artificial intelligence (AI) methods S2S prediction through better postprocessing ensemble system outputs, World Meteorological Organization (WMO) coordinated prize challenge in 2021 improve prediction. The goal this competition was produce most skillful precipitation 2-m temperature globally...

10.1175/bams-d-22-0046.1 article EN Bulletin of the American Meteorological Society 2022-09-30

Machine learning models have emerged as powerful tools for simulating Earth system processes. Following their successful application in capturing atmospheric evolution medium-range weather forecasts, attention has increasingly shifted towards other components of the system, such marine and land environments. This interest is further driven by potential to enhance forecasting capabilities beyond medium range. frameworks offer remarkable flexibility integrating these model achieve a coherent...

10.5194/egusphere-egu25-4499 preprint EN 2025-03-14

In just two years, the idea of an operational data-driven system for medium-range weather forecasting has been transformed from dream to very real possibility. This occurred through a series publications innovators, which have rapidly improved deterministic forecast skill. Our own evaluation confirms that these forecasts comparable skill NWP models across range variables. However, on timescales probabilistic forecasting, typically achieved ensembles, is key providing actionable insights...

10.5194/egusphere-egu24-17158 preprint EN 2024-03-11

<p>As machine learning algorithms are being used more and prominently in the meteorology climate domains, need for reference datasets has been identified as a priority. Moreover, boilerplate code data handling is ubiquitous scientific experiments. In order to focus on science, climate/meteorology/data scientists generic reusable domain-specific tools. To achieve these goals, we plugin based CliMetLab python package along with many packages listed by Pangeo....

10.5194/egusphere-egu22-13193 preprint EN 2022-03-28
Coming Soon ...