@article{fdi:010093335,
  title = {{U}nveiling urban flood vulnerability : a machine learning approach for mapping high risk zones in {T}etouan {C}ity, {N}orthern {M}orocco},
  author = {{M}ekkaoui, {O}. and {M}orarech, {M}. and {B}ouramtane, {T}. and {B}arbi{\'e}ro, {L}aurent and {H}amidi, {M}. and {A}kka, {H}. and {R}engasamy, {R}. {P}. {M}.},
  editor = {},
  language = {{ENG}},
  abstract = {{T}his study examines urban flood vulnerability in {T}etouan city, {N}orthern {M}orocco, using four machine learning models-{C}lassification and {R}egression {T}ree ({CART}), {S}upport {V}ector {M}achine ({SVM}), {L}ogistic {R}egression ({LR}), and {F}actorial {D}iscriminant {A}nalysis ({FDA})-to identify and map flood-prone areas. {T}he primary goal is to enhance flood prevention efforts and minimize losses by determining the most vulnerable zones. {T}he analysis highlights consistent flood risk along the {M}artil {R}iver and eastern plains, areas characterized by low-lying topography, dense drainage, proximity to canals, and recent urban development. {D}espite some spatial variation among the models, all consistently indicate low and very high vulnerability zones, with {FDA} identifying the highest proportion of very high risk areas (58%), followed by {CART}, {SVM}, and {LR} (39%, 38%, and 37%, respectively). {I}n terms of model accuracy, {SVM} and {LR} outperform others, demonstrating their effectiveness in flood risk delineation. {T}he findings offer valuable insights for urban planners and decision-makers in flood risk management, contributing to more informed resource allocation in {T}etouan-{M}artil and potentially guiding similar strategies in comparable regions globally.},
  keywords = {flood vulnerability ; machine learning models ; urban planning ; risk ; management ; {T}etouan ; {MAROC} ; {TETOUAN}},
  booktitle = {},
  journal = {{U}rban {S}cience},
  volume = {9},
  numero = {3},
  pages = {70 [18 p.]},
  year = {2025},
  DOI = {10.3390/urbansci9030070},
  URL = {https://www.documentation.ird.fr/hor/fdi:010093335},
}