LPLluís Palma

Lluís Palma

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lluís Palma has a total of 97 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Quantifying atmospheric and land drivers of hot temperature extremes through explainable Artificial Intelligence

    by Arnau Garcia Mesa, Lluís Palma, Markus Donat, Stefano Materia, Bruna Gràvalos Talló, Raül Marcos Matamoros

    Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an explainable machine‐learning framework to disentangle the respective influences of large‐scale atmospheric circulation, soil‐moisture anomalies, and rising CO 2 concentrations on boreal‐summer temperature extremes at six locations across Europe and North Africa with different characteristics of land–atmosphere coupling (Córdoba, Lyon, Hannover, Stockholm, Belgrade, and Marrakech). Using SHapley Additive exPlanation (SHAP) values, we find that the atmospheric circulation consistently dominates model explainability across all locations, contributing to 66 %–86 % of the total mean SHAP, with the geopotential at 500 hPa field contributing the most. Soil‐moisture influence exhibits a northward gradient: negligible at Marrakech (0.2 %), moderate at Córdoba (9.4 %), and substantial at Lyon (15.4 %). Additionally, the dominant shallow soil-moisture signal shows an inverse relationship between moisture anomalies and SHAP values, consistent with the amplifying effect of land drying on heat extremes, while attribution for deeper layers is weaker and less robust across locations. We demonstrate the robustness of these findings to a less stringent (80th percentile) extreme definition. Furthermore, the identified driver contributions are consistent when using alternative observational data for temperature extreme definition and for computing SPI/SPEI drought indices as proxies for soil moisture, with SPEI showing a closer alignment to the original ERA5-Land results. We also illustrate the methodology for case studies of two individual events, heatwaves occurring in Córdoba (Spain) 2021 and Hannover (Germany) 2018, which reveal a pronounced spatial pattern in the distribution of SHAP values for the circulation predictors. They also confirm the enhanced role of the land component in regions of Northern Europe and reveal a contribution of the anthropogenic factor through CO 2 concentrations, even for specific events. These results align with the established physical roles of atmospheric circulation and soil moisture modulation for temperature extremes, and demonstrate the methodological potential of explainable artificial intelligence to quantify the relative contributions of these drivers in a data-driven framework.

  • Open Access

    A Causal-based Analysis on the Role of Seasonal Climate Patterns in Aedes-borne Disease Transmission

    by Javier Corvillo Guerra, Verónica Torralba, Diego Campos, Lluís Palma, Ángel Garikoitz Muñoz

    Background: Vector-borne diseases transmitted by Aedes mosquitoes such as dengue, Zika, and chikungunya pose significant public health challenges worldwide in the wake of climate change. However, while their transmission is related to specific temperature, rainfall or humidity conditions, the overall role of large-scale climate drivers on the emergence of these diseases is not so well understood. Establishing the most important timeframes for Aedes-borne disease prediction and identifying specific climate patterns that drive its emergence can be key in the development of climate-based prediction systems for these arboviruses. Methods: The response of the climate component of Aedes-borne disease transmission to large-scale climate patterns is explored through their respective climate variability indices. A preliminary timescale decomposition analysis assesses the primary timescales over which climate processes condition disease transmissibility, while later correlation and causality analyses identify the most relevant climate drivers for Aedes-borne diseases. Findings: Year-to-year variations in temperature and precipitation have a significant impact on the environmental suitability for Aedes-borne diseases in the tropics, whereas seasonal fluctuations have a stronger impact in temperate regions instead. Overall, while some climate indices such as Niño 3.4, Tropical North Atlantic and the Indian Ocean Basin Mode stand out as modulators of climate-driven disease risk, it is the effect of multiple climate patterns, through compound interactions, that ultimately shape climate-based transmission dynamics. Interpretation: Aedes-borne disease transmission is susceptible to multiple climate factors, including long-term climate change and seasonal variability. The results of this study highlight the multi-faceted role of climate patterns in disease emergence, and their potential applicability in the development of climate-based early warning systems for Aedes-borne disease outbreaks. These findings can be integrated into an actionable disease prediction system using multiple climate patterns as predictors, which can ultimately better inform public health strategies to manage outbreaks.

  • Open Access

    Reply on RC1

    by Arnau Garcia Mesa, Lluís Palma, Markus Donat, Stefano Materia, Raül Marcos Matamoros

    Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an explainable machine‐learning framework to disentangle the respective influences of large‐scale atmospheric circulation, soil‐moisture anomalies, and rising CO2 concentrations on boreal‐summer temperature extremes at six locations across Europe and North Africa with different characteristics of land–atmosphere coupling (Córdoba, Lyon, Hannover, Stockholm, Belgrade, and Marrakech). Using SHapley Additive exPlanation (SHAP) values, we find that the atmospheric circulation consistently dominates model explainability across all locations, contributing to 67–90 % of the total mean SHAP, with the geopotential at 500 hPa field contributing the most. Soil‐moisture influence exhibits a northward gradient: negligible at Marrakech (0.5 %), moderate at Córdoba (7.7 %), and substantial at Lyon (15 %). Additionally, negative correlations between soil‐moisture standardized anomalies and SHAP values across three depth levels corroborate the amplifying effect of land drying on heat extremes. We demonstrate the robustness of these findings to a less stringent (80th percentile) extreme definition. Furthermore, the identified driver contributions are consistent when using alternative observational data for temperature extreme definition and for computing SPI/SPEI drought indices as proxies for soil moisture, with SPEI showing a closer alignment to the original ERA5-Land results. We also illustrate the methodology for case studies of two individual events, heatwaves occurring in Córdoba (Spain) 2021 and Hannover (Germany) 2018, which reveal a pronounced spatial pattern in the distribution of SHAP values for the circulation predictors. They also confirm the enhanced role of the land component in regions of Northern Europe and reveal a contribution of the anthropogenic factor through CO2 concentrations, even for specific events. These insights enhance our understanding of the physical mechanisms behind temperature extremes and demonstrate the potential of explainable artificial intelligence methods to quantify the contributions from different drivers of hot temperature extremes.

  • Open Access

    Reply on RC2

    by Arnau Garcia Mesa, Lluís Palma, Markus Donat, Stefano Materia, Raül Marcos Matamoros

    Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an explainable machine‐learning framework to disentangle the respective influences of large‐scale atmospheric circulation, soil‐moisture anomalies, and rising CO2 concentrations on boreal‐summer temperature extremes at six locations across Europe and North Africa with different characteristics of land–atmosphere coupling (Córdoba, Lyon, Hannover, Stockholm, Belgrade, and Marrakech). Using SHapley Additive exPlanation (SHAP) values, we find that the atmospheric circulation consistently dominates model explainability across all locations, contributing to 67–90 % of the total mean SHAP, with the geopotential at 500 hPa field contributing the most. Soil‐moisture influence exhibits a northward gradient: negligible at Marrakech (0.5 %), moderate at Córdoba (7.7 %), and substantial at Lyon (15 %). Additionally, negative correlations between soil‐moisture standardized anomalies and SHAP values across three depth levels corroborate the amplifying effect of land drying on heat extremes. We demonstrate the robustness of these findings to a less stringent (80th percentile) extreme definition. Furthermore, the identified driver contributions are consistent when using alternative observational data for temperature extreme definition and for computing SPI/SPEI drought indices as proxies for soil moisture, with SPEI showing a closer alignment to the original ERA5-Land results. We also illustrate the methodology for case studies of two individual events, heatwaves occurring in Córdoba (Spain) 2021 and Hannover (Germany) 2018, which reveal a pronounced spatial pattern in the distribution of SHAP values for the circulation predictors. They also confirm the enhanced role of the land component in regions of Northern Europe and reveal a contribution of the anthropogenic factor through CO2 concentrations, even for specific events. These insights enhance our understanding of the physical mechanisms behind temperature extremes and demonstrate the potential of explainable artificial intelligence methods to quantify the contributions from different drivers of hot temperature extremes.

  • Open Access

    The Rise of AI in Weather and Climate Information and Its Impact on Global Inequity

    by Amirpasha Mozaffari, Amanda Duarte, Lina Teckentrup, Stefano Materia, Gina E. C. Charnley, Lluís Palma, Eulalia Baulenas Serra, Dragana Bojovic, Paula Checchia, Aude Carreric, et al.

    The rapid integration of Artificial Intelligence (AI) into Earth system science promises a transformative revolution in predictive speed and fidelity, yet this technological prowess rests on a fragile and unequal foundation. We argue that the current trajectory of AI development risks automating and amplifying the historical North-South divide in the global climate information system. The systemic inequalities are manifested and compounded across the three primary stages of the AI modeling pipeline: input, process, and output.At the input level, we highlight the risks of relying on global datasets, such as ERA5, which inadvertently inherit and reinforce geographic biases and observational gaps in the Global South; most notably in the Amazon and Sub-Saharan Africa. At the process level, we detail a profound compute sovereignty gap, where the concentration of exascale High Performance Computing infrastructure in the Global North gatekeeps the development of foundation models. Finally, at the output level, we demonstrate that AI-powered forecasting improvements are unevenly distributed, with wealthy regions seeing significantly greater skill gains than the vulnerable populations most in need of accurate early warning systems. To steer this revolution toward just outcomes, we call for a move toward Climate Digital Public Infrastructure. By prioritizing data-centric AI, human-cost evaluation metrics, and knowledge co-production, we can ensure that the AI revolution fosters genuine systemic resilience rather than exacerbating global inequity.

  • Open Access

    Comment on egusphere-2025-5392

    by Arnau Garcia Mesa, Lluís Palma, Markus Donat, Stefano Materia, Raül Marcos Matamoros

    Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an explainable machine‐learning framework to disentangle the respective influences of large‐scale atmospheric circulation, soil‐moisture anomalies, and rising CO2 concentrations on boreal‐summer temperature extremes at six locations across Europe and North Africa with different characteristics of land–atmosphere coupling (Córdoba, Lyon, Hannover, Stockholm, Belgrade, and Marrakech). Using SHapley Additive exPlanation (SHAP) values, we find that the atmospheric circulation consistently dominates model explainability across all locations, contributing to 67–90 % of the total mean SHAP, with the geopotential at 500 hPa field contributing the most. Soil‐moisture influence exhibits a northward gradient: negligible at Marrakech (0.5 %), moderate at Córdoba (7.7 %), and substantial at Lyon (15 %). Additionally, negative correlations between soil‐moisture standardized anomalies and SHAP values across three depth levels corroborate the amplifying effect of land drying on heat extremes. We demonstrate the robustness of these findings to a less stringent (80th percentile) extreme definition. Furthermore, the identified driver contributions are consistent when using alternative observational data for temperature extreme definition and for computing SPI/SPEI drought indices as proxies for soil moisture, with SPEI showing a closer alignment to the original ERA5-Land results. We also illustrate the methodology for case studies of two individual events, heatwaves occurring in Córdoba (Spain) 2021 and Hannover (Germany) 2018, which reveal a pronounced spatial pattern in the distribution of SHAP values for the circulation predictors. They also confirm the enhanced role of the land component in regions of Northern Europe and reveal a contribution of the anthropogenic factor through CO2 concentrations, even for specific events. These insights enhance our understanding of the physical mechanisms behind temperature extremes and demonstrate the potential of explainable artificial intelligence methods to quantify the contributions from different drivers of hot temperature extremes.

  • Open Access

    Comment on egusphere-2025-5392

    by Arnau Garcia Mesa, Lluís Palma, Markus Donat, Stefano Materia, Raül Marcos Matamoros

    Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an explainable machine‐learning framework to disentangle the respective influences of large‐scale atmospheric circulation, soil‐moisture anomalies, and rising CO2 concentrations on boreal‐summer temperature extremes at six locations across Europe and North Africa with different characteristics of land–atmosphere coupling (Córdoba, Lyon, Hannover, Stockholm, Belgrade, and Marrakech). Using SHapley Additive exPlanation (SHAP) values, we find that the atmospheric circulation consistently dominates model explainability across all locations, contributing to 67–90 % of the total mean SHAP, with the geopotential at 500 hPa field contributing the most. Soil‐moisture influence exhibits a northward gradient: negligible at Marrakech (0.5 %), moderate at Córdoba (7.7 %), and substantial at Lyon (15 %). Additionally, negative correlations between soil‐moisture standardized anomalies and SHAP values across three depth levels corroborate the amplifying effect of land drying on heat extremes. We demonstrate the robustness of these findings to a less stringent (80th percentile) extreme definition. Furthermore, the identified driver contributions are consistent when using alternative observational data for temperature extreme definition and for computing SPI/SPEI drought indices as proxies for soil moisture, with SPEI showing a closer alignment to the original ERA5-Land results. We also illustrate the methodology for case studies of two individual events, heatwaves occurring in Córdoba (Spain) 2021 and Hannover (Germany) 2018, which reveal a pronounced spatial pattern in the distribution of SHAP values for the circulation predictors. They also confirm the enhanced role of the land component in regions of Northern Europe and reveal a contribution of the anthropogenic factor through CO2 concentrations, even for specific events. These insights enhance our understanding of the physical mechanisms behind temperature extremes and demonstrate the potential of explainable artificial intelligence methods to quantify the contributions from different drivers of hot temperature extremes.

  • Open Access

    From observation to action: the future of EO-driven multi-hazard risk assessment

    by Pedro Ribeiro, Jacopo Furlanetto, Chaonan Ji, Miguel Mahecha, Melanie Weynants, Fabian Gans, Marcin Kluczek, Jedrzej Bojanowski, Khalil Teber, Laia Romero, et al.

    This chapter explores recent advances in the use of Earth Observation (EO) for understanding and addressing climate extremes and multi-hazard risks, based on activities contributing to the European Space Agency's (ESA's) Extremes and Disaster Science Cluster. As climate-driven disasters such as floods, droughts, wildfires and compound events increase in frequency and severity, EO has emerged as a vital tool for monitoring, forecasting and assessing their impacts. The chapter highlights novel EO-based methodologies and data fusion techniques developed across six ESA-funded projects. These range from uncertainty-aware (UA) satellite precipitation datasets to deep learning (DL) models for compound heat and drought event forecasting. A key theme is the integration of EO data with in situ observations, modelling frameworks and artificial intelligence (AI) to better characterize cascading hazard interactions and system vulnerabilities. The chapter also identifies cross-cutting challenges, scientific gaps and emerging opportunities. Finally, it highlights the role of open science, interoperable data systems and collaborative platforms to foster transparency, usability and innovation, which together with scientific advancements constitute a foundational element in a new generation of science-informed, AI-enabled and impact-driven risk assessment tools – helping the move from observation to Earth Action in the face of accelerating climate risks.

  • Open Access

    Quantifying atmospheric and land drivers of hot temperature extremes through explainable Artificial Intelligence

    by Arnau Garcia Mesa, Lluís Palma, Markus Donat, Stefano Materia, Raül Marcos Matamoros

    Different drivers have been shown to play a central role in modulating the occurrence and intensity of summer temperature extremes, yet their individual contributions remain difficult to quantify. In this study, we develop an explainable machine‐learning framework to disentangle the respective influences of large‐scale atmospheric circulation, soil‐moisture anomalies, and rising CO2 concentrations on boreal‐summer temperature extremes at six locations across Europe and North Africa with different characteristics of land–atmosphere coupling (Córdoba, Lyon, Hannover, Stockholm, Belgrade, and Marrakech). Using SHapley Additive exPlanation (SHAP) values, we find that the atmospheric circulation consistently dominates model explainability across all locations, contributing to 67–90 % of the total mean SHAP, with the geopotential at 500 hPa field contributing the most. Soil‐moisture influence exhibits a northward gradient: negligible at Marrakech (0.5 %), moderate at Córdoba (7.7 %), and substantial at Lyon (15 %). Additionally, negative correlations between soil‐moisture standardized anomalies and SHAP values across three depth levels corroborate the amplifying effect of land drying on heat extremes. We demonstrate the robustness of these findings to a less stringent (80th percentile) extreme definition. Furthermore, the identified driver contributions are consistent when using alternative observational data for temperature extreme definition and for computing SPI/SPEI drought indices as proxies for soil moisture, with SPEI showing a closer alignment to the original ERA5-Land results. We also illustrate the methodology for case studies of two individual events, heatwaves occurring in Córdoba (Spain) 2021 and Hannover (Germany) 2018, which reveal a pronounced spatial pattern in the distribution of SHAP values for the circulation predictors. They also confirm the enhanced role of the land component in regions of Northern Europe and reveal a contribution of the anthropogenic factor through CO2 concentrations, even for specific events. These insights enhance our understanding of the physical mechanisms behind temperature extremes and demonstrate the potential of explainable artificial intelligence methods to quantify the contributions from different drivers of hot temperature extremes.

  • Open Access

    On the application of generative modelling for seasonal climate predictions

    by Lluís Palma, Amanda Duarte, Albert Soret, Markus Donat

    Reliable probabilistic predictions at the seasonal time scale are critical for key societal sectors such as agriculture, energy, and water management. Current operational approaches face significant challenges: General Circulation Models (GCMs) are computationally expensive and often limited by low spatial resolution and model deficiencies. At the same time, traditional statistical methods struggle due to significant modelling assumptions, such as linearity or homoscedasticity. Generative models emerge as a cost-effective, promising alternative, offering the potential to model complex nonlinear climate dynamics inherently probabilistically and at a reduced computational cost. Yet, training these algorithms on the short span of current reanalysis datasets results in almost certain overfitting due to the imbalance between trainable parameters and available training samples.In this context, the present study compares the effectiveness of different generative methodologies in predicting gridded fields of temperature and rainfall seasonal anomalies. The predictions cover all four seasons and are initialised one month before the start of the season, aligning with most climate services providers. We employ climate model output from CMIP6 and CEMS-lens2 during training and ERA5 reanalysis data during testing to circumvent the short span of current reanalysis and observational datasets. We analyse the method's performance in predicting interannual anomalies beyond the climate change-induced trend. We show that the model's ensemble generation capabilities allow it to provide diverse ensemble members, allowing the derivation of relevant probabilistic information and potentially reliable predictions. While climate change trends dominate the skill of temperature predictions, additional skill over the climatological forecast in regions influenced by known teleconnections is found. We reach similar conclusions based on the validation of precipitation predictions.This work further demonstrates the effectiveness of training generative models on climate model output for seasonal predictions, providing skilful seasonal climate predictions beyond the induced climate change trend at time scales and lead times relevant for user applications, motivating further research.