@article{fdi:010086735,
  title = {{P}redicting crop yields in {S}enegal using machine learning methods},
  author = {{S}arr, {A}lioune {B}adara and {S}ultan, {B}enjamin},
  editor = {},
  language = {{ENG}},
  abstract = {{A}griculture plays an important role in {S}enegalese economy and annual early warning predictions of crop yields are highly relevant in the context of climate change. {I}n this study, we used three main machine learning methods (support vector machine, random forest, neural network) and one multiple linear regression method, namely {L}east {A}bsolute {S}hrinkage and {S}election {O}perator ({LASSO}), to predict yields of the main food staple crops (peanut, maize, millet and sorghum) in 24 departments of {S}enegal. {T}hree combination of predictors (climate data, vegetation data or a combination of both) are used to compare the respective contribution of statistical methods and inputs in the predictive skill. {O}ur results showed that the combination of climate and vegetation with the machine learning methods gives the best performance. {T}he best prediction skill is obtained for peanut yield likely due to its high sensitivity to interannual climate variability. {A}lthough more research is needed to integrate the results of this study into an operational framework, this paper provides evidence of the promising performance machine learning methods. {T}he development and operationalization of such prediction and their integration into operational early warning systems could increase resilience of {S}enegal to climate change and contribute to food security.},
  keywords = {climate change scenario ; crop yield prediction ; machine learning ; {S}enegal ; {SENEGAL}},
  booktitle = {},
  journal = {{I}nternational {J}ournal of {C}limatology},
  volume = {43},
  numero = {4},
  pages = {1817--1838},
  ISSN = {0899-8418},
  year = {2023},
  DOI = {10.1002/joc.7947},
  URL = {https://www.documentation.ird.fr/hor/fdi:010086735},
}