Victor Xing
Research Subjects
Victor Xing has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Adrien Burq
Laboratoire des Sciences du Climat et de l’Environnement, UMR 8212 CEA-CNRS-UVSQ, Université Paris-Saclay, IPSL, 91191 Gif-sur-Yvette, France
10 shared publications - Davide Faranda
Laboratoire des Sciences du Climat et de l'Environnement, UMR 8212 CEA-CNRS-UVSQ, Université Paris-Saclay & IPSL, CE Saclay l'Orme des Merisiers, 91191, Gif-sur-Yvette, France
10 shared publications - Mathieu Vrac
Laboratoire des Sciences du Climat et de l’Environnement, UMR 8212 CEA-CNRS-UVSQ, Université Paris-Saclay, IPSL, 91191 Gif-sur-Yvette, France
10 shared publications Jean Jouhaud
Descartes Underwriting, 148 rue de Courcelles, 75017 Paris, France
9 shared publications- Mateusz Taszarek
Department of Meteorology and Climatology, Adam Mickiewicz University, Pozna´n, Poland
8 shared publications Victor Bouvier
Descartes Underwriting, 148 rue de Courcelles, 75017 Paris, France
8 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Reply on RC3
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 6 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Open AccessReply on RC3
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 6 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Reply on RC2
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 6 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Open AccessReply on RC2
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 6 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Reply on RC1
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 6 November 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Open AccessReply on RC1
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 9 October 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Comment on egusphere-2026-4363
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 9 October 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Open AccessComment on egusphere-2026-4363
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 19 September 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Comment on egusphere-2026-4363
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 19 September 2026
- Published by Copernicus GmbH
- Vol. 2026, 1-35
Open AccessComment on egusphere-2026-4363
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 3 September 2026
- Published by Copernicus GmbH
- p. 1-35
Comment on egusphere-2026-4363
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 3 September 2026
- Published by Copernicus GmbH
- p. 1-35
Open AccessComment on egusphere-2026-4363
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 17 August 2026
- Published by Copernicus GmbH
Supplementary material to "From logistic regression to deep learning: machine learning modeling of lightning in ERA5 reanalysis data"
- 17 August 2026
- Published by Copernicus GmbH
Open AccessSupplementary material to "From logistic regression to deep learning: machine learning modeling of lightning in ERA5 reanalysis data"
- Open Access
- 17 August 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-35
From logistic regression to deep learning: machine learning modeling of lightning in ERA5 reanalysis data
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- 17 August 2026
- Published by Copernicus GmbH in EGUsphere
- Vol. 2026, 1-35
Open AccessFrom logistic regression to deep learning: machine learning modeling of lightning in ERA5 reanalysis data
Most lightning parameterization schemes rely on local approaches where the predictors are the atmospheric variables in the same grid cell as the output. To validate the hypothesis that large-scale thunderstorm clusters – such as mesoscale convective systems – are driven by broad spatial predictor patterns, we model lightning occurrence using architectures capable of processing surrounding grid-cell data rather than relying solely on local point-based inputs. This study develops a deep convolutional neural network (U-Net) to model lightning occurrence across Europe using ERA5 reanalysis data. The model is trained on 13 years of data and evaluated with a leave-one-year-out cross-validation strategy. We compare the performance of the U-Net to several local machine learning models of increasing complexity, including logistic regression, generalized additive model, extreme gradient boosting, and multi-layer perceptron. We find that the U-Net outperforms all single grid cell models in overall performance and on the most extreme events. Through a feature importance study, we find that the most important predictors depend on the model type. Finally we show with a spatial sensitivity study that the U-Net captures mesoscale patterns driving lightning occurrence.
- Open Access
- 8 August 2025
- Published by Copernicus GmbH
A novel Deep Learning framework for lightning probabilistic prediction based on ERA5 reanalysis data and lightning observations.
Traditional methods for studying thunderstorm climatology and associated hazards often rely on analyzing long-term trends of key environmental variables. These variables are derived from low-resolution reanalysis datasets like ERA5 and are aggregated over extended time periods (Taszarek et al., 2021). The methods also derive probability of occurrence of convective events, providing useful insights into large-scale climatological trends (Battaglioli et al., 2023). However, they struggle to capture the fine-scale characteristics of individual events. Their representations tend to suffer from probabilistic smoothing effects—such as overestimating hazard occurrence in regions without activity and underestimating it in areas of high activity—leading to unrealistic distributions of hazards in space, time, and intensity.Machine learning approaches, including random forests, gradient boosting and more recently deep learning models, have improved short-term lightning nowcasting (McGovern et al., 2023). However, they rely on high-resolution inputs such as radar and satellite data which constrains their usage because of the spatio-temporal limitation of such data. To address this limitation, we develop a deep learning model tailored for reanalysis data which enables us to apply the model on a global scale and over a much larger period of time to study the evolution of thunderstorm activity.Given a state of the atmosphere, we generate an ensemble forecast of lightnings at an hourly time resolution and 0.25° spatial resolution. Compared to previous models (Battaglioli et al., 2023, Saha et al., 2025), we use 3D inputs in our model to directly output a map of lightning with statistically coherent spatial structures. Additionally, we make ensemble predictions to capture a wide range of possible realistic scenarios for a given set of thermodynamic and dynamic variables.Technically, we develop a guided diffusion model that learns to generate lightning maps at an hourly timestep over western Europe. Given 3 maps of environmental conditions (representing instability, humidity and wind-shear) derived from the ERA5 reanalysis and an ensemble of 2D noise data, we generate an ensemble of possible lightning maps.Because of the large temporal availability of ERA5 data, our model will enable us to detect changes in past thunderstorm activity.
- 8 August 2025
- Published by Copernicus GmbH
Open AccessA novel Deep Learning framework for lightning probabilistic prediction based on ERA5 reanalysis data and lightning observations.
Traditional methods for studying thunderstorm climatology and associated hazards often rely on analyzing long-term trends of key environmental variables. These variables are derived from low-resolution reanalysis datasets like ERA5 and are aggregated over extended time periods (Taszarek et al., 2021). The methods also derive probability of occurrence of convective events, providing useful insights into large-scale climatological trends (Battaglioli et al., 2023). However, they struggle to capture the fine-scale characteristics of individual events. Their representations tend to suffer from probabilistic smoothing effects—such as overestimating hazard occurrence in regions without activity and underestimating it in areas of high activity—leading to unrealistic distributions of hazards in space, time, and intensity.Machine learning approaches, including random forests, gradient boosting and more recently deep learning models, have improved short-term lightning nowcasting (McGovern et al., 2023). However, they rely on high-resolution inputs such as radar and satellite data which constrains their usage because of the spatio-temporal limitation of such data. To address this limitation, we develop a deep learning model tailored for reanalysis data which enables us to apply the model on a global scale and over a much larger period of time to study the evolution of thunderstorm activity.Given a state of the atmosphere, we generate an ensemble forecast of lightnings at an hourly time resolution and 0.25° spatial resolution. Compared to previous models (Battaglioli et al., 2023, Saha et al., 2025), we use 3D inputs in our model to directly output a map of lightning with statistically coherent spatial structures. Additionally, we make ensemble predictions to capture a wide range of possible realistic scenarios for a given set of thermodynamic and dynamic variables.Technically, we develop a guided diffusion model that learns to generate lightning maps at an hourly timestep over western Europe. Given 3 maps of environmental conditions (representing instability, humidity and wind-shear) derived from the ERA5 reanalysis and an ensemble of 2D noise data, we generate an ensemble of possible lightning maps.Because of the large temporal availability of ERA5 data, our model will enable us to detect changes in past thunderstorm activity.
- Open Access
- 30 June 2025
- Published by Copernicus GmbH
A novel Deep Learning framework for lightning probabilistic prediction based on ERA5 reanalysis data and lightning observations.
Thunderstorms are associated with several hazards such as lightning, hail, wind gusts, tornadoes and heavy rain. Because of their small scale spatio-temporal processes, studying convective events associated with thunderstorms is challenging and requires high resolution observations and models.Traditional methods for studying thunderstorm climatology and associated hazards often rely on analyzing long-term trends of key environmental variables. These variables are derived from low-resolution reanalysis datasets like ERA5 and are aggregated over extended time periods (Taszarek et al., 2021). The methods also derive probability of occurrence of convective events, providing useful insights into large-scale climatological trends (Battaglioli et al., 2023). However, they struggle to capture the fine-scale characteristics of individual events. Their representations tend to suffer from probabilistic smoothing effects—such as overestimating hazard occurrence in regions without activity and underestimating it in areas of high activity—leading to unrealistic distributions of hazards in space, time, and intensity.Machine learning approaches, including random forests, gradient boosting and more recently deep learning models, have improved short-term lightning nowcasting (McGovern et al., 2023). However, they use high-resolution inputs such as radar and satellite data which constrains their usage because of the spatio-temporal limitation of such data. To address this limitation, we develop a deep learning model tailored for reanalysis data which enables us to apply the model on a global scale and over a much larger period of time.Given a thermodynamic state of the atmosphere, we generate an ensemble forecast of lightnings at an hourly time resolution and 0.25° spatial resolution. Compared to previous models (Battaglioli et al., 2023), we use 3D inputs in our model to directly output a map of lightning with statistically coherent spatial structures. Additionally, we make ensemble predictions to capture a wide range of possible realistic scenarios for a given set of thermodynamic variables. Finally, we add more variables as input to our model to leverage deep learning's ability to automatically capture complex dependencies between input variables.Because of the large temporal availability of ERA5 data, our model will later enable us to perform attribution studies for specific events and create a stochastic catalogue of lightning events.
- 30 June 2025
- Published by Copernicus GmbH
Open AccessA novel Deep Learning framework for lightning probabilistic prediction based on ERA5 reanalysis data and lightning observations.
Thunderstorms are associated with several hazards such as lightning, hail, wind gusts, tornadoes and heavy rain. Because of their small scale spatio-temporal processes, studying convective events associated with thunderstorms is challenging and requires high resolution observations and models.Traditional methods for studying thunderstorm climatology and associated hazards often rely on analyzing long-term trends of key environmental variables. These variables are derived from low-resolution reanalysis datasets like ERA5 and are aggregated over extended time periods (Taszarek et al., 2021). The methods also derive probability of occurrence of convective events, providing useful insights into large-scale climatological trends (Battaglioli et al., 2023). However, they struggle to capture the fine-scale characteristics of individual events. Their representations tend to suffer from probabilistic smoothing effects—such as overestimating hazard occurrence in regions without activity and underestimating it in areas of high activity—leading to unrealistic distributions of hazards in space, time, and intensity.Machine learning approaches, including random forests, gradient boosting and more recently deep learning models, have improved short-term lightning nowcasting (McGovern et al., 2023). However, they use high-resolution inputs such as radar and satellite data which constrains their usage because of the spatio-temporal limitation of such data. To address this limitation, we develop a deep learning model tailored for reanalysis data which enables us to apply the model on a global scale and over a much larger period of time.Given a thermodynamic state of the atmosphere, we generate an ensemble forecast of lightnings at an hourly time resolution and 0.25° spatial resolution. Compared to previous models (Battaglioli et al., 2023), we use 3D inputs in our model to directly output a map of lightning with statistically coherent spatial structures. Additionally, we make ensemble predictions to capture a wide range of possible realistic scenarios for a given set of thermodynamic variables. Finally, we add more variables as input to our model to leverage deep learning's ability to automatically capture complex dependencies between input variables.Because of the large temporal availability of ERA5 data, our model will later enable us to perform attribution studies for specific events and create a stochastic catalogue of lightning events.