@article{fdi:010097137,
  title = {{I}ntercomparison of regional flood frequency estimation procedures in {W}est {A}frica},
  author = {{D}iop, {S}. {B}. and {T}ramblay, {Y}ves and {B}odian, {A}. and {D}ieppois, {B}. and {O}uarda, {T}bmj},
  editor = {},
  language = {{ENG}},
  abstract = {{W}est {A}frica faces devastating flood hazards that affect more than 400 million people. {Y}et flood risk assessment is hindered by sparse and often unreliable hydrological data. {R}egional flood frequency analysis ({RFFA}) is widely used to estimate design values at ungauged catchments and there is a need for a systematic intercomparison of {RFFA} approaches in this region. {W}ith an unprecedented dataset of 211 near-natural catchments, we compared a {D}irect {R}egression {A}pproach ({DRA}) and three homogeneous region delineation methods using the index-flood methods based on spatial proximity, {P}rincipal {C}omponent {A}nalysis ({PCA}), and {C}anonical {C}orrelation {A}nalysis ({CCA}) with catchment attributes. {E}ach regional approach was paired with two regression models: (i) {S}tepwise {R}egression and (ii) {L}east {A}bsolute {S}hrinkage and {S}election {O}perator ({LASSO}), and four machine learning algorithms: (i) {R}andom {F}orest ({RF}), (ii) e{X}treme {G}radient {B}oosting ({XGB}), (iii) {S}upport {V}ector {R}egression ({SVR}), and (iv) a hybrid linear-tree ensemble ({L}in{RF}). {R}esults show that index-flood methods consistently outperformed {DRA}, with the {CCA}-based framework achieving the highest accuracy. {CCA}-{SVR} combination is the best-performing regional model, yielding the lowest estimation errors (mean absolute relative error = 0.21 and relative bias = -0.03) for 20- or 50-year flood quantiles. {F}eature importance analysis revealed that subsurface properties, catchment area, and topographic attributes have stronger influence on regional flood estimation than surface features or land use patterns. {T}he methodology and findings of this study offer practical tools for infrastructure design and climate adaptation, supporting more resilient flood risk management across vulnerable {W}est {A}frican communities.},
  keywords = {{W}est {A}frica ; {F}loods ; {I}ndex-flood ; {GEV} ; {CCA} ; {R}egionalization ; {AFRQIE} {DE} {L}'{OUEST}},
  booktitle = {},
  journal = {{S}tochastic {E}nvironmental {R}esearch and {R}isk {A}ssessment},
  volume = {40},
  numero = {6},
  pages = {124 [22 p.]},
  ISSN = {1436-3240},
  year = {2026},
  DOI = {10.1007/s00477-026-03258-3},
  URL = {https://www.documentation.ird.fr/hor/fdi:010097137},
}