Flood prediction challenge
Type de document :
Pré-publication ou Document de travail
URL permanente :
Titre :
Flood prediction challenge
Auteur(s) :
Medernach, David [Auteur]
Capgemini
Lemaire, Cyril [Auteur]
Girousse, Eva [Auteur]
EDF R&D [EDF R&D]
Keisler, Julie [Auteur]
EDF R&D [EDF R&D]
Optimisation, Simulation, Risque et Statistiques pour les Marchés de l’Energie [EDF R&D OSIRIS]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Richon, Julie [Auteur]
Capgemini
Brunel, Nicolas [Auteur]
Laboratoire de Mathématiques et Modélisation d'Evry [LaMME]
Capgemini
Capgemini
Lemaire, Cyril [Auteur]
Girousse, Eva [Auteur]
EDF R&D [EDF R&D]
Keisler, Julie [Auteur]
EDF R&D [EDF R&D]
Optimisation, Simulation, Risque et Statistiques pour les Marchés de l’Energie [EDF R&D OSIRIS]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Richon, Julie [Auteur]
Capgemini
Brunel, Nicolas [Auteur]
Laboratoire de Mathématiques et Modélisation d'Evry [LaMME]
Capgemini
Mot(s)-clé(s) en anglais :
Machine learing
CNN
Hackathon
Flood prediction
CNN
Hackathon
Flood prediction
Discipline(s) HAL :
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [en]
<div><p>Flooding poses significant risks across various sectors in France. This paper presents the outcomes of a machine learning hackathon focused on predicting the extent of various types of floods by leveraging a ...
Lire la suite ><div><p>Flooding poses significant risks across various sectors in France. This paper presents the outcomes of a machine learning hackathon focused on predicting the extent of various types of floods by leveraging a combination of geospatial and climate data. A Convolutional Neural Network (CNN) emerged as the most effective model, achieving strong performance in predicting the temporal evolution of flood risk maps. The evaluation not only includes prediction accuracy but also incorporates robustness, frugality, and explainability, in line with the principles of trustworthy AI principles. A key feature of this challenge was the absence of streamflow data, allowing the models to predict floods in regions where such data is unavailable. This highlights the potential of machine learning to improve flood forecasting in data-scarce environments.</p><p>2 Hackathon setup 2.1 Geospatial Data Labels: Flood maps were extracted from the Sen1Floods11 dataset [2] which can be visualized on the Global Flood Database. Sen1Floods11 provides surface water data, including raw Sentinel-1 WIP paper.</p></div>Lire moins >
Lire la suite ><div><p>Flooding poses significant risks across various sectors in France. This paper presents the outcomes of a machine learning hackathon focused on predicting the extent of various types of floods by leveraging a combination of geospatial and climate data. A Convolutional Neural Network (CNN) emerged as the most effective model, achieving strong performance in predicting the temporal evolution of flood risk maps. The evaluation not only includes prediction accuracy but also incorporates robustness, frugality, and explainability, in line with the principles of trustworthy AI principles. A key feature of this challenge was the absence of streamflow data, allowing the models to predict floods in regions where such data is unavailable. This highlights the potential of machine learning to improve flood forecasting in data-scarce environments.</p><p>2 Hackathon setup 2.1 Geospatial Data Labels: Flood maps were extracted from the Sen1Floods11 dataset [2] which can be visualized on the Global Flood Database. Sen1Floods11 provides surface water data, including raw Sentinel-1 WIP paper.</p></div>Lire moins >
Langue :
Anglais
Collections :
Source :
Date de dépôt :
2025-01-22T05:24:33Z
Fichiers
- document
- Accès libre
- Accéder au document
- ScientificDesign_Hackathon_Flooding%20%281%29.pdf
- Accès libre
- Accéder au document