arXiv subjects

Zied Ben-Bouallegue

Publications and source records attributed to Zied Ben-Bouallegue.

4 recordsLinked to original sources

arXiv2024

Prévisions météorologiques basées sur l'intelligence artificielle : une révolution peut en cacher une autre

Artificial intelligence (AI), based on deep-learning algorithm using high-quality reanalysis datasets, is showing enormous potential for weather forecasting. In this context, the European Centre for Medium-Range Weather Forecasts (ECMWF) is developing a new forecasting system based on AI. Verification results of deterministic forecast for now are promising. However, the realism of weather forecasts based on AI is often questioned. Here, different types of realism are identified and we discuss, in particular, the relationship between structural realism and predictability of weather events. Furthermore, a statistical analysis of deterministic forecasts based on AI points to a realism/performance dilemma that a probabilistic approach should help to solve. -- L'intelligence artificielle (IA) bouleverse aujourd'hui le monde de la prévision météorologique avec l'utilisation d'algorithmes d'apprentissage profond nourris par des champs de réanalyses. Dans ce contexte, le Centre Européen pour les Prévisions Météorologiques à Moyen Terme (CEPMMT) a décidé de développer un nouveau système de prévisions resposant sur l'IA. Ces prévisions, pour le moment de type déterministe, montrent des résultats prometteurs. Toutefois, le réalisme de ce type de prévisions reposant sur l'IA est souvent questionné. Ici, nous identifions différents types de réalisme et interrogeons notamment le rapport entre réalisme structurel et prévisibilité des évênements météorologiques. Une analyse statistique de prévisions déterministes reposant sur l'IA laisse apparaitre un dilemme réalisme/performance qu'une approche probabiliste devrait aider à résoudre.

physics.ao-ph↗

arXiv2023

Seamless prediction of high-impact weather events: a comparison of actionable forecasts

A new index for high-impact weather forecasting is introduced and assessed in comparison with the well-established extreme forecast index (EFI). Two other ensemble summary statistics are also included in this comparison study: the shift-of-tail and a standardised ensemble mean anomaly. All these forecasts are based on the same ingredients: the ensemble forecast run at the European Centre for Medium-Range Weather Forecasts and the corresponding model climatology derived from a set of reforecasts. The new index emerges from recent developments in forecast verification of extreme events: it is derived as a consistent forecast with the diagonal score, a weighted version of the continuous ranked probability score targetting high-impact events. In this study, we emphasise the importance of forecast discretisation for communication purposes and decision-making. A forecast is actionable in the situation where a user can decide to take action when a threshold is exceeded by the forecast. Forecast verification is performed to assess both the potential skill of the different indices as well as their specific skill as actionable forecasts. Among the investigated actionable forecasts, the new proposed index demonstrates the strongest discrimination power, in particular at longer lead times, paving the way for seamless predictions of high-impact weather across time ranges.

stat.AP↗

arXiv2023

The rise of data-driven weather forecasting

Data-driven modeling based on machine learning (ML) is showing enormous potential for weather forecasting. Rapid progress has been made with impressive results for some applications. The uptake of ML methods could be a game-changer for the incremental progress in traditional numerical weather prediction (NWP) known as the 'quiet revolution' of weather forecasting. The computational cost of running a forecast with standard NWP systems greatly hinders the improvements that can be made from increasing model resolution and ensemble sizes. An emerging new generation of ML models, developed using high-quality reanalysis datasets like ERA5 for training, allow forecasts that require much lower computational costs and that are highly-competitive in terms of accuracy. Here, we compare for the first time ML-generated forecasts with standard NWP-based forecasts in an operational-like context, initialized from the same initial conditions. Focusing on deterministic forecasts, we apply common forecast verification tools to assess to what extent a data-driven forecast produced with one of the recently developed ML models (PanguWeather) matches the quality and attributes of a forecast from one of the leading global NWP systems (the ECMWF IFS). The results are very promising, with comparable skill for both global metrics and extreme events, when verified against both the operational analysis and synoptic observations. Increasing forecast smoothness and bias drift with forecast lead time are identified as current drawbacks of ML-based forecasts. A new NWP paradigm is emerging relying on inference from ML models and state-of-the-art analysis and reanalysis datasets for forecast initialization and model training.

physics.ao-ph↗

arXiv2023

Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers

Statistical post-processing of global ensemble weather forecasts is revisited by leveraging recent developments in machine learning. Verification of past forecasts is exploited to learn systematic deficiencies of numerical weather predictions in order to boost post-processed forecast performance. Here, we introduce PoET, a post-processing approach based on hierarchical transformers. PoET has 2 major characteristics: 1) the post-processing is applied directly to the ensemble members rather than to a predictive distribution or a functional of it, and 2) the method is ensemble-size agnostic in the sense that the number of ensemble members in training and inference mode can differ. The PoET output is a set of calibrated members that has the same size as the original ensemble but with improved reliability. Performance assessments show that PoET can bring up to 20% improvement in skill globally for 2m temperature and 2% for precipitation forecasts and outperforms the simpler statistical member-by-member method, used here as a competitive benchmark. PoET is also applied to the ENS10 benchmark dataset for ensemble post-processing and provides better results when compared to other deep learning solutions that are evaluated for most parameters. Furthermore, because each ensemble member is calibrated separately, downstream applications should directly benefit from the improvement made on the ensemble forecast with post-processing.

physics.ao-ph↗