arXiv subjects

Gabriele Messori

Publications and source records attributed to Gabriele Messori.

9 recordsLinked to original sources

arXiv2026

Assessing socio-economic climate impacts from text data

Recent advances in natural language processing (NLP) and large language models (LLMs) have enabled the systematic use of large-scale textual data from news, social media, and reports to create datasets with socio-economic impacts of climate hazards such as floods, droughts, storms, and multi-hazard events. As the field of text-as-data for impact assessment expands, so does its methodological complexity. Yet research remains fragmented, with no clear guidelines for defining what constitutes an impact, handling temporal and spatial biases, and selecting appropriate modeling and post-processing strategies. This lack of coherence limits transparency and comparability across studies. Here, we address this gap by synthesising common practices, describing key challenges specific to the use of text-as-data methods for analyzing socio-economic impact data, and proposing recommendations to address them. By providing guidance on best practices, we aim to support the construction of robust text-derived socio-economic impact datasets that can more accurately inform disaster risk management and attribution studies.

cs.CL↗

arXiv2025

Spatio-temporal Dynamical Indices for Complex Systems

Complex systems span multiple spatial and temporal scales, making their dynamics challenging to understand and predict. This challenge is especially daunting when one wants to study localized and/or rare events. Advances in dynamical systems theory, including the development of state-dependent dynamical indices, namely local dimension and persistence, have provided powerful tools for studying these phenomena. However, existing applications of such indices rely on a predefined and fixed spatial domain, that provides a single scalar quantity for the entire region of interest. This aspect prevents understanding the spatially localized dynamical behavior of the system. In this work, we introduce Spatio-temporal Dynamical Indices (SDIs), that leverage the existing framework of state-dependent local dimension and persistence. SDIs are obtained via a sliding window approach, enabling the exploration of space-dependent properties in spatio-temporal data. As an example, we show that, through this framework, we are able to reconcile previously different perspectives on European summertime heatwaves. This result showcases the importance of accounting for spatial scales when performing scale-dependent dynamical analyses.

physics.ao-ph↗

arXiv2025

Climate-Eval: A Comprehensive Benchmark for NLP Tasks Related to Climate Change

Climate-Eval is a comprehensive benchmark designed to evaluate natural language processing models across a broad range of tasks related to climate change. Climate-Eval aggregates existing datasets along with a newly developed news classification dataset, created specifically for this release. This results in a benchmark of 25 tasks based on 13 datasets, covering key aspects of climate discourse, including text classification, question answering, and information extraction. Our benchmark provides a standardized evaluation suite for systematically assessing the performance of large language models (LLMs) on these tasks. Additionally, we conduct an extensive evaluation of open-source LLMs (ranging from 2B to 70B parameters) in both zero-shot and few-shot settings, analyzing their strengths and limitations in the domain of climate change.

cs.CL↗

arXiv2024

A statistical physics and dynamical systems perspective on geophysical extreme events

Statistical physics and dynamical systems theory are key tools to study high-impact geophysical events such as temperature extremes, cyclones, thunderstorms, geomagnetic storms and many more. Despite the intrinsic differences between these events, they all originate as temporary deviations from the typical trajectories of a geophysical system, resulting in well-organised, coherent structures at characteristic spatial and temporal scales. While statistical extreme value analysis techniques are capable to provide return times and probabilities of occurrence of certain geophysical events, they are not apt to account for their underlying physics. Their focus is to compute the probability of occurrence of events that are large or small with respect to some specific observable (e.g. temperature, precipitation, solar wind), rather than to relate rare or extreme phenomena to the underlying anomalous geophysical regimes. This paper outlines this knowledge gap, presenting some related challenges, new formalisms and briefly commenting on how stochastic approaches tailored to the study of extreme geophysical events can help to advance their understanding.

physics.ao-ph↗

arXiv2023

Physics-inspired adaptions to low-parameter neural network weather forecasts systems

Recently, there has been a surge of research on data-driven weather forecasting systems, especially applications based on convolutional neural networks (CNNs). These are usually trained on atmospheric data represented on regular latitude-longitude grids, neglecting the curvature of the Earth. We assess the benefit of replacing the standard convolution operations with an adapted convolution operation which takes into account the geometry of the underlying data (Spherenet convolution), specifically near the poles. Additionally, we assess the effect of including the information that the two hemispheres of the Earth have "flipped" properties - for example cyclones circulating in opposite directions - into the structure of the network. Both approaches are examples of physics-informed machine learning. The methods are tested on the WeatherBench dataset, at a resolution of $\sim1.4^{\circ}$ which is higher than many previous studies on CNNs for weather forecasting. For most lead times up to day +10 for 500 hPa geopotential and 850 hPa temperature, we find that using Spherenet convolution or including hemisphere-specific information individually lead to improvement in forecast skill. Combining the two methods typically gives the highest forecast skill. Our version of Spherenet is implemented flexibly and scales well to high resolution datasets, but is still significantly more expensive than a standard convolution operation. Finally, we analyze cases with high forecast error. These occur mainly in winter, and are relatively consistent across different training realizations of the networks, pointing to flow-dependent atmospheric predictability.

physics.ao-ph↗

arXiv2022

Typicality of the 2021 Western North America Summer Heatwave

Elucidating the statistical properties of extreme meteo-climatic events and capturing the physical processes responsible for their occurrence are key steps for improving our understanding of climate variability and climate change and for better evaluating the associated hazards. It has recently become apparent that large deviation theory is very useful for investigating persistent extreme events, and specifically, for flexibly estimating long return periods and for introducing a notion of dynamical typicality. Using a methodological framework based on large deviation theory and taking advantage of long simulations by a state-of-the-art Earth System Model, we investigate the 2021 North America Heatwave. Indeed, our analysis shows that the 2021 event can be seen as an unlikely but possible manifestation of climate variability, whilst its probability of occurrence is greatly amplified by the ongoing climate change. We also clarify the properties of spatial coherence of the 2021 heatwave and elucidate the role played by the Rocky Mountains in modulating hot, dry, and persistent extreme events in the Western Pacific region of North America.

physics.ao-ph↗

arXiv2022

Meridional energy transport extremes and the general circulation of Northern Hemisphere mid-latitudes: dominant weather regimes and preferred zonal wavenumbers

The extratropical meridional energy transport in the atmosphere is fundamentally intermittent in nature, having extremes large enough to affect the net seasonal transport. Here, we investigate how these extreme transports are associated with the dynamics of the atmosphere at multiple spatial scales, from planetary to synoptic. We use the ERA5 reanalysis data to perform a wavenumber decomposition of meridional energy transport in the Northern Hemisphere mid-latitudes during winter and summer. We then relate extreme transport events to atmospheric circulation anomalies and dominant weather regimes, identified by clustering 500hPa geopotential height fields. In general, planetary-scale waves determine the strength and meridional position of the synoptic-scale baroclinic activity with their phase and amplitude, but important differences emerge between seasons. During winter, large wavenumbers ($k=2-3$) are key drivers of the meridional energy transport extremes, and planetary and synoptic-scale transport extremes virtually never co-occur. In summer, extremes are associated with higher wavenumbers ($k=4-6$), identified as synoptic-scale motions. We link these waves and the transport extremes to recent results on exceptionally strong and persistent co-occurring summertime heat waves across the Northern Hemisphere mid-latitudes. We show that the weather regime structures associated with these heat wave events are typical for extremely large poleward energy transport events.

physics.ao-ph↗

arXiv2021

Ensemble methods for neural network-based weather forecasts

Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast, by computing the ensemble's spread. However, generating an ensemble with a good spread-error relationship is far from trivial, and a wide range of approaches to achieve this have been explored -- chiefly in the context of numerical weather prediction models. Here, we aim to transform a deterministic neural network weather forecasting system into an ensemble forecasting system. We test four methods to generate the ensemble: random initial perturbations, retraining of the neural network, use of random dropout in the network, and the creation of initial perturbations with singular vector decomposition. The latter method is widely used in numerical weather prediction models, but is yet to be tested on neural networks. The ensemble mean forecasts obtained from these four approaches all beat the unperturbed neural network forecasts, with the retraining method yielding the highest improvement. However, the skill of the neural network forecasts is systematically lower than that of state-of-the-art numerical weather prediction models.

physics.ao-ph↗

arXiv2019

Spectral decomposition and extremes of atmospheric meridional energy transport in Northern Hemisphere midlatitudes

The atmospheric meridional energy transport in the Northern Hemisphere midlatitudes is mainly accomplished by planetary and synoptic waves. A decomposition into wave components highlights the strong seasonal dependence of the transport, with both the total transport and the contributions from planetary and synoptic waves peaking in winter. In both winter and summer months, poleward transport extremes primarily result from a constructive interference between planetary and synoptic motions. The contribution of the mean meridional circulation is close to climatology. Equatorward transport extremes feature a mean meridional equatorward transport in winter, while the planetary and synoptic modes mostly transport energy poleward. In summer, a systematic destructive interference occurs, with planetary modes mostly transporting energy equatorward and synoptic modes again poleward. This underscores that baroclinic conversion dominates regardless of season in the synoptic wave modes, whereas the planetary waves can be either free or forced, depending on the season.

physics.ao-ph↗