@article{fdi:010092840,
  title = {{C}omparison of machine learning algorithms for daily runoff forecasting with global rainfall products in {A}lgeria},
  author = {{B}ounab, {R}. and {B}outaghane, {H}. and {B}oulmaiz, {T}. and {T}ramblay, {Y}ves},
  editor = {},
  language = {{ENG}},
  abstract = {{R}ainfall-runoff models are crucial tools for managing water resources. {T}he absence of reliable rainfall data in many regions of the world is a major limitation for these models, notably in many {A}frican countries, although some recent global rainfall products can effectively monitor rainfall from space. {I}n {A}lgeria, to identify a relevant modeling approach using this new source of rainfall information, the present research aims to (i) compare a conceptual model ({GR}4{J}) and seven machine learning algorithms ({FFNN}, {ELM}, {LSTM}, {LSTM}2, {GRU}, {SVM}, and {GPR}) and (ii) compare different types of precipitation inputs, including four satellite products ({CHIRPS}, {SM}2{RAIN}, {GPM}, and {PERSIANN}), one reanalysis product ({ERA}5), and observed precipitation, to assess which combination of models and precipitation data provides the optimal performance for river discharge simulation. {T}he results show that the {ELM}, {FFNN}, and {LSTM} algorithms give the best performance ({NSE} > 0.6) for river runoff simulation and provide reliable alternatives compared to a conceptual hydrological model. {T}he {SM}2{RAIN}-{ASCAT} and {ERA}5 rainfall products are as efficient as observed precipitation in this data-scarce context. {C}onsequently, this work is the first step towards the implementation of these tools for the operational monitoring of surface water resources in {A}lgeria.},
  keywords = {{A}lgeria ; machine learning ; hydrologic models ; rainfall-runoff ; simulation ; satellite rainfall ; {ALGERIE}},
  booktitle = {},
  journal = {{A}tmosphere},
  volume = {16},
  numero = {2},
  pages = {213 [24 p.]},
  year = {2025},
  DOI = {10.3390/atmos16020213},
  URL = {https://www.documentation.ird.fr/hor/fdi:010092840},
}