arXiv subjects

Jean-Baptiste Filippi

Publications and source records attributed to Jean-Baptiste Filippi.

6 recordsLinked to original sources

arXiv2026

Leveraging MTG-FCI fire observations for event-based fire behavior monitoring from near-real-time operation to seasonal analysis

Wildfire monitoring and suppression require timely information on fire behavior, including fire energy release and rate of spread, to support operational decision-making and resource allocation. Active fire products from the Flexible Combined Imager (FCI) aboard the geostationary Meteosat Third Generation (MTG) satellites provide 10-min observations over Europe and Africa. Deriving fire behavior information from these observations requires associating individual hotspot detections into coherent fire events. We present a Fire Event Tracker (FET) algorithm that performs spatio-temporal clustering of hotspot detections from the LSA-SAF FCI active fire product. The algorithm assigns persistent identifiers to fire events and updates their geometry, fire radiative power, and rate of spread at each 10-min interval. The same parameterization is used for both near-real-time and retrospective processing. FET was applied retrospectively to the Mediterranean FCI hotspot archive of 2025 and operationally in two near-real-time contexts: wildfire monitoring in Portugal and support of the 2025 SILEX airborne campaign within the EUBURN project, where besides fire monitoring, FET products were also used to initialize coupled FOREFIRE-MesoNH simulations for plume forecasting. Results show that event-based clustering of FCI active fire detections provides a consistent description of fire evolution, enabling both tactical wildfire management and high-frequency seasonal fire analyses.

physics.ao-ph↗

arXiv2025

Local wind speed forecasting at short time horizons based on Numerical Weather Prediction and observations from surrounding stations

This study presents a hybrid neural network model for short-term (1-6 hours ahead) surface wind speed forecasting, combining Numerical Weather Prediction (NWP) with observational data from ground weather stations. It relies on the MeteoNet dataset, which includes data from global (ARPEGE) and regional (AROME) NWP models of the French weather service and meteorological observations from ground stations in the French Mediterranean. The proposed neural network architecture integrates recent past station observations (over last few hours) and AROME and ARPEGE predictions on a small subgrid around the target location. The model is designed to provide both deterministic and probabilistic forecasts, with the latter predicting the parameters of a suitable probability distribution that notably allows us to capture extreme wind events. Our results demonstrate that the hybrid model significantly outperforms baseline methods, including raw NWP predictions, persistence models, and linear regression, across all forecast horizons. For instance, the model reduces RMSE by up 30\% compared to AROME predictions. Probabilistic forecasting further enhances performance, particularly for extreme quantiles, by estimating conditional quantiles rather than relying solely on the conditional mean. Fine-tuning the model for specific stations, such as those in the Mediterranean island of Corsica, further improves forecasting accuracy. Our study highlights the importance of integrating multiple data sources and probabilistic approaches to improve short-term wind speed forecasting. It defines an effective approach, even in a complex terrain like Corsica where localized wind variations are significant

physics.ao-ph↗

arXiv2025

Improving prediction of heavy rainfall in the Mediterranean with Neural Networks using both observation and Numerical Weather Prediction data

Forecasting Heavy Precipitation Events (HPE) in the Mediterranean is crucial but challenging due to the complexity of the processes involved. In this context, Artificial Intelligence methods have recently proven to be competitive with state-of-the-art Numerical Weather Prediction (NWP). This work focuses on improving the prediction of the occurrence of HPE over periods from 1 h to 24 h based on Neural Network (NN) models. The proposed method uses both ground-station observations and data from Météo France's Arome and Arpege NWP models, on two regions with oceanic and Mediterranean climates for the period 2016-2018. The verification metric is the Peirce Skill Score. Results show that the NN model using only observations or NWP data performs better for shorter and longer rainfall accumulation period respectively. In contrast, a hybrid method combining both observations and NWP data offers the best performance and remains stable with the rainfall accumulation period. The hybrid method also improves the performance in predicting increasingly intense rainfall, from the 5% to the 0.1% rarest events. The choice of the loss function is found to be an important aspect of this work, where only balanced loss functions provide results insensitive to rare event frequency. Finally, the hybrid method is particularly well suited for the prediction of HPE in the Mediterranean climate, especially during the fall season, period during which most HPE occur.

physics.ao-ph↗

arXiv2023

Modelling pyro-convection phenomenon during a mega-fire event in Portugal

The present study contributes to an increased understanding of pyro-convection phenomena by using a fire-atmosphere coupled simulation, and investigates in detail the large-scale meteorological conditions affecting Portugal during the occurrence of multiple mega-fires events on 15 October 2017. Two numerical simulations were performed using the MesoNH atmospheric model. The first simulation, was run for a large single domain (300 x 250 grid points) with a 15 km resolution. In the second one, the MesoNH was coupled to a fire propagation model (ForeFire) to study in detail the Quiaios's fire. To optimize both high resolution in the proximity of the fire region and computational efficiency, the simulation is set up using 3 nested domains (300 x 300 grid points) with horizontal resolution of 2000 m, 400 m, and 80 m respectively. The emission into the atmosphere of the heat and the water vapour fluxes caused by the evolving fire is managed by the ForeFire code. The fire spatio-temporal evolution is based on an assigned map, which follows what reported by public authorities. At the large scale, the simulation shows the evolution of the hurricane Ophelia, pointing out the influence of south/southwest winds on the rapid spread of active fires, as well as the subtropical moisture transport toward mainland Portugal in the early evening, when violent pyro-convective activity was observed in Central Portugal. The coupled simulation allowed to reproduce the formation of a PyroCu cloud inside the smoke plume. The convective updraughts caused by the fire led to the vertical transport of water vapour to higher levels and enhanced the development of a high-based cloud over a dry atmospheric layer within the smoke plume.

physics.ao-ph↗

arXiv2021

EscapeWildFire: Assisting People to Escape Wildfires in Real-Time

Over the past couple of decades, the number of wildfires and area of land burned around the world has been steadily increasing, partly due to climatic changes and global warming. Therefore, there is a high probability that more people will be exposed to and endangered by forest fires. Hence there is an urgent need to design pervasive systems that effectively assist people and guide them to safety during wildfires. This paper presents EscapeWildFire, a mobile application connected to a backend system which models and predicts wildfire geographical progression, assisting citizens to escape wildfires in real-time. A small pilot indicates the correctness of the system. The code is open-source; fire authorities around the world are encouraged to adopt this approach.

cs.CY↗

arXiv2016

Turbulence and fire-spotting effects into wild-land fire simulators

This paper presents a mathematical approach to model the effects of phenomena with random nature such as turbulence and fire-spotting into the existing wildfire simulators. The formulation proposes that the propagation of the fire-front is the sum of a drifting component (obtained from an existing wildfire simulator without turbulence and fire-spotting) and a random fluctuating component. The modelling of the random effects is embodied in a probability density function accounting for the fluctuations around the fire perimeter which is given by the drifting component. In past, this formulation has been applied to include these random effects into a wildfire simulator based on an Eulerian moving interface method, namely the Level Set Method (LSM), but in this paper the same formulation is adapted for a wildfire simulator based on a Lagrangian front tracking technique, namely the Discrete Event System Specification (DEVS). The main highlight of the present study is the comparison of the performance of a Lagrangian and an Eulerian moving interface method when applied to wild-land fire propagation. Simple idealised numerical experiments are used to investigate the potential applicability of the proposed formulation to DEVS and to compare its behaviour with respect to the LSM. The results show that DEVS based wildfire propagation model qualitatively improves its performance (e.g., reproducing flank and back fire, increase in fire spread due to pre-heating of the fuel by hot air and firebrands, fire propagation across no fuel zones, secondary fire generation, \dots). Though the results presented here are devoid of any validation exercise and provide only a proof of concept, they show a strong inclination towards an intended operational use. The existing LSM or DEVS based operational simulators like WRF-SFIRE and ForeFire respectively can serve as an ideal basis for the same.

physics.ao-ph↗