Enter Note Done
Go to previous page in this tab
Session
  • Presentation | IN51C: Advancing Artificial Intelligence for Remote Sensing: Overcoming Data Scarcity and Domain Shift III Poster
  • Poster
  • Share Icon
    Bookmark Icon
  • IN51C-0195: Characterization of Strike-Slip Fault Offsets Using Deep Learning and Simulated Topographic Data
    • Schedule
    Notes
  • Board 0195‚ Hall EFG (Poster Hall)
    NOLA CC
    Set Timezone

Generic 'disconnected' Message
Author(s):
Jules Bourcier, Institut des Sciences de la Terre (First Author, Presenting Author)
Sarah Visage, Sapienza University of Rome
Sofia Goncalves, Institut des Sciences de la Terre
Sarah Perrinel, Institut des Sciences de la Terre
Margaux Mouchené, Institut des Sciences de la Terre
Léa Pousse Beltran, Institut des Sciences de la Terre
Sophie Giffard-Roisin, Institut des Sciences de la Terre


We present a deep learning approach for automatically quantifying strike-slip fault offsets from high-resolution topographic data. Traditional offset measurements require extensive manual or semi-automatic analyses, which can be time-consuming and inconsistent. To address data scarcity, we generate a semi-synthetic dataset by simulating faulting and landscape evolution, enabling effective pretraining of our neural network. A simulated-to-real transfer learning strategy improves offset prediction accuracy and more closely matches semi-automatic measurements compared to models trained only on real data. These findings show promise for efficient, automated fault characterization.



Scientific Discipline
Suggested Itineraries
Neighborhood
Type
Main Session
Discussion