@article{fdi:010084555,
  title = {{C}oastal bathymetry estimation from {S}entinel-2 satellite imagery : comparing deep learning and physics-based approaches},
  author = {{A}l {N}ajar, {M}. and {B}enshila, {R}. and {E}l {B}ennioui, {Y}. and {T}houmyre, {G}r{\'e}goire and {A}lmar, {R}afa{\¨e}l and {B}ergsma, {E}. {W}. {J}. and {D}elvit, {J}. {M}. and {W}ilson, {D}. {G}.},
  editor = {},
  language = {{ENG}},
  abstract = {{T}he ability to monitor the evolution of the coastal zone over time is an important factor in coastal knowledge, development, planning, risk mitigation, and overall coastal zone management. {W}hile traditional bathymetry surveys using echo-sounding techniques are expensive and time consuming, remote sensing tools have recently emerged as reliable and inexpensive data sources that can be used to estimate bathymetry using depth inversion models. {D}eep learning is a growing field of artificial intelligence that allows for the automatic construction of models from data and has been successfully used for various {E}arth observation and model inversion applications. {I}n this work, we make use of publicly available {S}entinel-2 satellite imagery and multiple bathymetry surveys to train a deep learning-based bathymetry estimation model. {W}e explore for the first time two complementary approaches, based on color information but also wave kinematics, as inputs to the deep learning model. {T}his offers the possibility to derive bathymetry not only in clear waters as previously done with deep learning models but also at common turbid coastal zones. {W}e show competitive results with a state-of-the-art physical inversion method for satellite-derived bathymetry, {S}atellite to {S}hores ({S}2{S}hores), demonstrating a promising direction for worldwide applicability of deep learning models to inverse bathymetry from satellite imagery and a novel use of deep learning models in {E}arth observation.},
  keywords = {deep learning ; convolutional neural networks ; bathymetry ; {S}entinel-2 ; wave kinematics ; coastal physics},
  booktitle = {},
  journal = {{R}emote {S}ensing},
  volume = {14},
  numero = {5},
  pages = {1196 [21 p.]},
  year = {2022},
  DOI = {10.3390/rs14051196},
  URL = {https://www.documentation.ird.fr/hor/fdi:010084555},
}