Titre :

Automatic geomorphological mapping using ground truth data with coverage sampling and random forest algorithms

Auteur(s) :

Faye, Paul Aimé Latsouck [Auteur correspondant]
Institut Montpelliérain Alexander Grothendieck [IMAG]
Brunel, Elodie [Auteur]
Institut Montpelliérain Alexander Grothendieck [IMAG]
Claverie, Thomas [Auteur]
Université de Mayotte (UMay) [UMay]
Ecologie marine tropicale dans les Océans Pacifique et Indien [ENTROPIE [Réunion]]
Manou-Abi, Solym [Auteur]
Université de Mayotte (UMay) [UMay]
Laboratoire de mathématiques et applications [UMR 7348] [LMA [Poitiers]]
Institut Montpelliérain Alexander Grothendieck [IMAG]
Dabo-Niang, Sophie [Auteur]
MOdel for Data Analysis and Learning [MODAL]
Laboratoire Paul Painlevé - UMR 8524 [LPP]

Titre de la revue :

Earth Science Informatics

Pagination :

3715–3732

Éditeur :

Springer Link

Date de publication :

2024

ISSN :

1865-0473

Mot(s)-clé(s) en anglais :

geomorphological maps
spatial modeling
random forest classification
digital bathymetric model
terrain attributes
lidar data

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]
Planète et Univers [physics]/Sciences de la Terre/Géomorphologie
Statistiques [stat]/Applications [stat.AP]

Résumé en anglais : [en]

Marine geomorphological maps are useful to understand seafloor structure for example in the context of ecological studies, resources management or conservation planning. Although techniques to build such maps are increasingly ...
Lire la suite >Marine geomorphological maps are useful to understand seafloor structure for example in the context of ecological studies, resources management or conservation planning. Although techniques to build such maps are increasingly sophisticated, manual techniques are still largely used. Automated approaches are needed to get reproducible maps in a reasonable time. This work provides statistical learning approaches based framework to build automatically geomorphological maps. We used bathymetric data to build Digital Bathymetric Model (DBM) and compute terrain attributes characteristic of seafloor geomorphology. Then, we used clustering based algorithms to select automatically ground truth locations from a reference geomorphological map manually made. Finally a supervised classification model random forest based was used to build predictive models for seafloor geomorphology typologies. Subsequently we studied the effect of DBM resolution, sample size and sampling method of the ground truth locations, in the quality of map production via a series of simulations. Results showed that the proposed framework allowed to build efficiently relevant seafloor geomorphological maps. The best compromise between the sampling effort and the quality of the resulting maps was obtained with 100 m DBM resolution, 200 data points sample size and using a complexity-dependent sampling method and led to a map matching at 90% the reference one.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL