Esther Rodrigo Bonet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Esther Rodrigo Bonet has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Nikos Deligiannis
Vrije Universiteit Brussel
5 shared publications - Gustau Camps-Valls
Universitat de València
3 shared publications - Jelle Hofman
Air Quality & Industrial Emissions Team, Flemish Institute for Technological Research (VITO), Boeretang 200, 2400 Mol, Belgium
3 shared publications - Tien Huu Do
Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, Belgium
3 shared publications - Xuening Qin
Department of Telecommunications and Information Processing, Ghent University, Ghent, Belgium
3 shared publications - Jordi Cerdà-Bautista2 shared publications
Latest Publications
- 15 September 2026
- Published by Springer Nature
- p. 654-666
Mean-Field Variational Graph Autoencoders for Data Generation: An Application to Urban Environmental Exposure Data
- 15 September 2026
- Published by Springer Nature
- p. 654-666
Mean-Field Variational Graph Autoencoders for Data Generation: An Application to Urban Environmental Exposure Data
- Open Access
- 18 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 8578
Bridging the weather and climate divide with artificial intelligence
Weather and climate shape every aspect of our lives, yet for decades they have been studied as separate worlds—one concerned with what happens tomorrow, the other with what awaits us over the coming decades. This long-standing divide has slowed progress in both fields. Here, we argue that artificial intelligence (AI) is helping to dissolve the boundary between them. By learning directly from vast streams of Earth observations, AI is starting to predict both tomorrow’s storm and next century’s climate within a single, unified framework. We show how this convergence is already underway, why weather and climate science have much to gain from each other, and what still stands in the way—from trust, transparency, and fairness to the energy cost of computation and the risk of widening global inequalities. Realizing this vision will demand not only better algorithms but a new culture of collaboration across scientific communities, operational centers, fields and disciplines. Done well, a unified, AI-driven Earth science could deliver faster, more reliable, and more actionable predictions—helping societies anticipate and adapt to a rapidly warming planet.
- 18 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 8578
Open AccessBridging the weather and climate divide with artificial intelligence
Weather and climate shape every aspect of our lives, yet for decades they have been studied as separate worlds—one concerned with what happens tomorrow, the other with what awaits us over the coming decades. This long-standing divide has slowed progress in both fields. Here, we argue that artificial intelligence (AI) is helping to dissolve the boundary between them. By learning directly from vast streams of Earth observations, AI is starting to predict both tomorrow’s storm and next century’s climate within a single, unified framework. We show how this convergence is already underway, why weather and climate science have much to gain from each other, and what still stands in the way—from trust, transparency, and fairness to the energy cost of computation and the risk of widening global inequalities. Realizing this vision will demand not only better algorithms but a new culture of collaboration across scientific communities, operational centers, fields and disciplines. Done well, a unified, AI-driven Earth science could deliver faster, more reliable, and more actionable predictions—helping societies anticipate and adapt to a rapidly warming planet.
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Operational and actionable Acute Food Insecurity modelling
The growing complexity of global food security, exacerbated by climate change and socio-economic disparities, calls for a multi-hazard approach to risk evaluation and management. Recognizing the lack of a universally accepted measure for food insecurity covering all dimensions, we first review target variables and input features in existing ML modeling efforts, providing an assessment of current data availability, accessibility, and fragmentation, and improving the understanding of possibilities and limitations of ML for the food security community. We further consolidate a comprehensive dataset, with an operational design for continuous enrichment, that includes various indicators and precursors, updated monthly on a subnational level across over one hundred countries. We apply innovative explainable artificial intelligence (XAI) methods to unravel the intricate relationships between food insecurity, drought, and conflict-related fatalities. Our models forecast food crises with different lead times, revealing the nuanced patterns recognized by machine learning algorithms over various time frames. Our analysis also shows that the relative importance of drivers can shift depending on the food security metric used, indicating that distinct processes are at play in its many dimensions. This study not only exposes the complex drivers of food security but also provides policymakers with an operational multi-risk forecasting tool, improving the ability to foresee and strategically manage food crises.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessOperational and actionable Acute Food Insecurity modelling
The growing complexity of global food security, exacerbated by climate change and socio-economic disparities, calls for a multi-hazard approach to risk evaluation and management. Recognizing the lack of a universally accepted measure for food insecurity covering all dimensions, we first review target variables and input features in existing ML modeling efforts, providing an assessment of current data availability, accessibility, and fragmentation, and improving the understanding of possibilities and limitations of ML for the food security community. We further consolidate a comprehensive dataset, with an operational design for continuous enrichment, that includes various indicators and precursors, updated monthly on a subnational level across over one hundred countries. We apply innovative explainable artificial intelligence (XAI) methods to unravel the intricate relationships between food insecurity, drought, and conflict-related fatalities. Our models forecast food crises with different lead times, revealing the nuanced patterns recognized by machine learning algorithms over various time frames. Our analysis also shows that the relative importance of drivers can shift depending on the food security metric used, indicating that distinct processes are at play in its many dimensions. This study not only exposes the complex drivers of food security but also provides policymakers with an operational multi-risk forecasting tool, improving the ability to foresee and strategically manage food crises.
- Open Access
- 15 March 2025
- Published by Copernicus GmbH
Hierarchical Causal Graph-Based Methods for Imputing Food Insecurity
Food insecurity is typically modelled using inter-regional data comprising economical, geophysical and social variables. Such datasets are often of varying granularity, with each variable corresponding to a certain granularity level (e.g., GDP is a national variable, while disaster displacement can be local or regional). Additionally, each level shows a specific causal relation of its variables. Since countries affected by food insecurity are usually underdeveloped, collecting such variables is a challenging task, leading to highly-incomplete datasets. To deal with the multi-level complexity and incomplete nature of the data, we propose to build a hierarchical causal graph (HCG) structure of the variables, that can then be injected in different imputation methods. Specifically, we propose to classify the variables at different granularity levels, and use causal graph discovery to learn a causal graph at each level. We test the proposed approach for imputing food insecurity using a dataset of 300+ economical, geophysical and social variables for more than 70 countries.
- 15 March 2025
- Published by Copernicus GmbH
Open AccessHierarchical Causal Graph-Based Methods for Imputing Food Insecurity
Food insecurity is typically modelled using inter-regional data comprising economical, geophysical and social variables. Such datasets are often of varying granularity, with each variable corresponding to a certain granularity level (e.g., GDP is a national variable, while disaster displacement can be local or regional). Additionally, each level shows a specific causal relation of its variables. Since countries affected by food insecurity are usually underdeveloped, collecting such variables is a challenging task, leading to highly-incomplete datasets. To deal with the multi-level complexity and incomplete nature of the data, we propose to build a hierarchical causal graph (HCG) structure of the variables, that can then be injected in different imputation methods. Specifically, we propose to classify the variables at different granularity levels, and use causal graph discovery to learn a causal graph at each level. We test the proposed approach for imputing food insecurity using a dataset of 300+ economical, geophysical and social variables for more than 70 countries.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (1) , 281-291
GF-LRP: A Method for Explaining Predictions Made by Variational Graph Auto-Encoders
Variational graph autoencoders (VGAEs) combine the best of graph convolutional networks (GCNs) and variational inference and have been used to address various tasks such as node classification or link prediction. However, the lack of explainability is a limiting factor when trustworthy decisions are required. In this paper, we present a novel post-hoc explainability framework for VGAEs that considers their encoder-decoder architecture. Specifically, we propose a layer-wise-relevance-propagation-based (LRP-based) explanation technique coined GF-LRP which, to our knowledge, is the first explanation method for VGAEs. GF-LRP goes beyond existing LRP techniques for GCNs by taking into account, in addition to input features and the graph structure of the data, the VGAE branch-specific architecture. The explanations are branch-specific in the sense that we explain the mean and standard deviation branches of the Gaussian distribution learned by the model. For a node's prediction, GF-LRP infers the most relevant features, nodes and its edges. To prove the effectiveness of our explanation method, we compute fidelity, sparsity and contrastivity as well as commonly employed evaluation metrics. Extensive experiments and visualizations on two real-world datasets demonstrate the effectiveness of the proposed explanation method.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (1) , 281-291
GF-LRP: A Method for Explaining Predictions Made by Variational Graph Auto-Encoders
Variational graph autoencoders (VGAEs) combine the best of graph convolutional networks (GCNs) and variational inference and have been used to address various tasks such as node classification or link prediction. However, the lack of explainability is a limiting factor when trustworthy decisions are required. In this paper, we present a novel post-hoc explainability framework for VGAEs that considers their encoder-decoder architecture. Specifically, we propose a layer-wise-relevance-propagation-based (LRP-based) explanation technique coined GF-LRP which, to our knowledge, is the first explanation method for VGAEs. GF-LRP goes beyond existing LRP techniques for GCNs by taking into account, in addition to input features and the graph structure of the data, the VGAE branch-specific architecture. The explanations are branch-specific in the sense that we explain the mean and standard deviation branches of the Gaussian distribution learned by the model. For a node's prediction, GF-LRP infers the most relevant features, nodes and its edges. To prove the effectiveness of our explanation method, we compute fidelity, sparsity and contrastivity as well as commonly employed evaluation metrics. Extensive experiments and visualizations on two real-world datasets demonstrate the effectiveness of the proposed explanation method.
- 20 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 8, 499-513
Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference
Graph neural networks (GNNs) have proven their ability in modelling graph-structured data in diverse domains, including natural language processing and computer vision. However, like other deep learning models, the lack of explainability is becoming a major drawback for GNNs, especially in health-related applications such as air pollution estimation, where a model’s predictions might directly affect humans’ health and habits. In this paper, we present a novel post-hoc explainability framework for GNN-based models. More concretely, we propose a novel topology-aware kernelised node selection method, which we apply over the graph structural and air pollution information. Thanks to the proposed model, we are able to effectively capture the graph topology and, for a certain graph node, infer its most relevant nodes. Additionally, we propose a novel topological node embedding for each node, capturing in a vector-shape the graph walks with respect to every other graph node. To prove the effectiveness of our explanation method, we include commonly employed evaluation metrics as well as fidelity, sparsity and contrastivity, and adapt them to evaluate explainability on a regression task. Extensive experiments on two real-world air pollution data sets demonstrate and visually show the effectiveness of the proposed method.
- 20 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 8, 499-513
Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference
Graph neural networks (GNNs) have proven their ability in modelling graph-structured data in diverse domains, including natural language processing and computer vision. However, like other deep learning models, the lack of explainability is becoming a major drawback for GNNs, especially in health-related applications such as air pollution estimation, where a model’s predictions might directly affect humans’ health and habits. In this paper, we present a novel post-hoc explainability framework for GNN-based models. More concretely, we propose a novel topology-aware kernelised node selection method, which we apply over the graph structural and air pollution information. Thanks to the proposed model, we are able to effectively capture the graph topology and, for a certain graph node, infer its most relevant nodes. Additionally, we propose a novel topological node embedding for each node, capturing in a vector-shape the graph walks with respect to every other graph node. To prove the effectiveness of our explanation method, we include commonly employed evaluation metrics as well as fidelity, sparsity and contrastivity, and adapt them to evaluate explainability on a regression task. Extensive experiments on two real-world air pollution data sets demonstrate and visually show the effectiveness of the proposed method.
- Open Access
- 30 May 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (11) , 2613
Fine-Grained Urban Air Quality Mapping from Sparse Mobile Air Pollution Measurements and Dense Traffic Density
Urban air quality mapping has been widely applied in urban planning, air pollution control and personal air pollution exposure assessment. Urban air quality maps are traditionally derived using measurements from fixed monitoring stations. Due to high cost, these stations are generally sparsely deployed in a few representative locations, leading to a highly generalized air quality map. In addition, urban air quality varies rapidly over short distances (2 by 100 m and 1 h resolution for fine-grained air quality mapping. The CLADF model exploits deep forest to construct a local model for each cluster consisting of nearest neighbor measurements in contextual feature space, and considers traffic flow as an important contextual feature. Extensive validation experiments were conducted using mobile NO2 measurements collected by 17 postal vans equipped with low-cost sensors operating in Antwerp, Belgium. The experimental results demonstrate that the CLADF model achieves the lowest RMSE as well as advances in accuracy and correlation, compared with various benchmark models, including random forest, deep forest, extreme gradient boosting and support vector regression.
- 30 May 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (11) , 2613
Open AccessFine-Grained Urban Air Quality Mapping from Sparse Mobile Air Pollution Measurements and Dense Traffic Density
Urban air quality mapping has been widely applied in urban planning, air pollution control and personal air pollution exposure assessment. Urban air quality maps are traditionally derived using measurements from fixed monitoring stations. Due to high cost, these stations are generally sparsely deployed in a few representative locations, leading to a highly generalized air quality map. In addition, urban air quality varies rapidly over short distances (2 by 100 m and 1 h resolution for fine-grained air quality mapping. The CLADF model exploits deep forest to construct a local model for each cluster consisting of nearest neighbor measurements in contextual feature space, and considers traffic flow as an important contextual feature. Extensive validation experiments were conducted using mobile NO2 measurements collected by 17 postal vans equipped with low-cost sensors operating in Antwerp, Belgium. The experimental results demonstrate that the CLADF model achieves the lowest RMSE as well as advances in accuracy and correlation, compared with various benchmark models, including random forest, deep forest, extreme gradient boosting and support vector regression.
- 9 January 2022
- Published by Elsevier in Environmental Modelling & Software
- Vol. 149
Spatiotemporal air quality inference of low-cost sensor data: Evidence from multiple sensor testbeds
- 9 January 2022
- Published by Elsevier in Environmental Modelling & Software
- Vol. 149
Spatiotemporal air quality inference of low-cost sensor data: Evidence from multiple sensor testbeds