Timely and accurate situational reports are essential for humanitarian decision-making, yet current workflows remain largely manual, resource intensive, and inconsistent. We present a fully automated framework that uses large language models (LLMs) to transform heterogeneous humanitarian documents into structured and evidence-grounded reports. The system integrates semantic text clustering, automatic question generation, retrieval augmented answer extraction with citations, multi-level summarization, and executive summary generation, supported by internal evaluation metrics that emulate expert reasoning. We evaluated the framework across 13 humanitarian events, including natural disasters and conflicts, using more than 1100 documents from verified sources such as ReliefWeb. The generated questions achieved 84.7% relevance, 84.0% importance, and 76.4% urgency. The extracted answers reached 86.3% relevance, with citation precision and recall both exceeding 76%. Agreement between human and LLM based evaluations surpassed an F1 score of 0.80. Comparative analysis shows that the proposed framework produces reports that are more structured, interpretable, and actionable than existing baselines. By combining LLM reasoning with transparent citation linking and multi-level evaluation, this study shows that generative AI can substantially support the generation of humanitarian situation reports that domain experts judged more useful, better structured, and more transparently sourced than current approaches—marking a concrete step toward operational use, even as important challenges remain on the path to fully reliable autonomous deployment.
In 2023 the European Centre for Disease Prevention and Control (ECDC) launched RespiCast, the first European Respiratory Diseases Forecasting Hub, to provide probabilistic forecasts for influenza-like illness (ILI) and acute respiratory infection (ARI) incidence across 26 European countries. During the 2023/24 and 2024/25 winter seasons, RespiCast collected one- to four-week-ahead forecasts from multiple models contributed by different international teams and combined them into an ensemble. Our analysis shows that, when evaluated using the weighted interval score (WIS) and the absolute error (AE), the ensemble consistently outperformed the baseline model (defined as a persistence model that projects the last observed value forward) as well as individual models across most countries and forecasting rounds for both ILI and ARI incidence in the two seasons. Analysis of ensemble coverage (defined as the proportion of times observed values fall within the specified prediction intervals) indicated that forecast prediction intervals were reliable, although a general overconfidence trend (i.e., prediction intervals that are too narrow) was observed, particularly in specific countries. The relative performance of the ensemble declined in certain weeks, likely due to reduced participation from modelling teams, epidemic dynamics, higher data noise, and reporting delays. Forecast scores varied across countries, with some exhibiting consistently higher relative errors than others. Overall, the findings highlight the strengths of ensemble approaches in improving the accuracy and reliability of epidemiological forecasts while identifying areas for improvement, such as managing overconfidence and addressing variability in performance across countries and over time.
Over the last two decades, network science has greatly advanced our understanding of how the collective behaviors of a complex system emerge from the interactions among its basic units. Multiplex networks, i.e. networks with many layers, whose nodes are in one-to-one correspondence, provide a more realistic description for social, biological and ecological systems where multiple types of interactions coexist. After a brief introduction on how to model the architecture of multiplex networks, we present a complete overview of the different dynamics which can unfold over these structures. We present a unified framework to describe dynamical processes such as percolation, reaction-diffusion, synchronization, epidemic spreading, social dynamics and games on multiplex networks, as well as the coupled evolution of different dynamical processes, and the coevolution of a process with the network structure. Our focus is on truly-multiplex collective behaviors, i.e., all those phenomena which cannot emerge on the corresponding aggregated networks, or when the different layers of these systems are considered in isolation. We identify three main mechanisms leading to new collective behaviors: the existence of structural correlations across layers, the presence of dynamical correlations in the processes taking place at the different layers, and the dynamical interplay of inter- and intra-layer interactions. We conclude with a summary of the main takeaways from a decade of work in the field.
Segregation has long been recognized as a driver of environmental inequalities, with disadvantaged groups often living in neighborhoods where heat-related risks are highest. Yet, it remains unclear how daily mobility patterns, embedded within heterogeneous urban heat fields, shape heat exposure inequalities across sociodemographic groups. Using a mobile phone dataset of daily mobility flows and urban temperature fields across 23 Spanish cities, we develop a network-based framework to quantify how different sociodemographic groups experience heat through their daily movements. We find systematic income-related inequalities, with low-income groups consistently experiencing higher exposure than high-income groups, while age-related disparities are smaller in magnitude, with younger individuals slightly more exposed than elderly ones. These inequalities intensify during commuting trips, indicating that routine mobility amplifies spatial heat gradients more than non-routine movements. We further assess whether state-of-the-art population-based mobility models can capture these observed inequalities. The gravity model underestimates income- and age-related exposure differences, whereas the parameter-free radiation model captures most of the observed disparities. This indicates that heat exposure inequalities largely emerge from the interplay between the unequal organization of daily activities across sociodemographic groups and urban heat gradients, rather than from group-specific behavioral differences. Our findings provide a generalizable framework to characterize mobility-driven heat exposure inequalities and inform climate-resilient urban planning and public health strategies as cities face intensifying climate-related risks.
Households play a crucial role in the propagation of infectious diseases due to the frequent and prolonged interactions that typically occur between their members. Recent studies have emphasized the need to include socioeconomic variables in epidemic models to account for the heterogeneity induced by human behavior. While sub-Saharan Africa suffers the highest burden of infectious disease diffusion, few studies have investigated the mixing patterns in the countries and their relation with social indicators. This work analyzes household contact matrices measured with wearable proximity sensors in a rural and an urban village in South Africa. Leveraging a rich data collection describing additional individual and household attributes, we investigate how the household contact matrix varies according to the household type (whether it is composed only of a familiar nucleus or by a larger group), the gender of its head (the primary decision-maker), the rural or urban context, and the season in which it was measured. We show the household type and the gender of its head induce differences in the interaction patterns between household members, particularly regarding child caregiving, suggesting they are relevant attributes to include in epidemic modeling.
