@article{fdi:010092869,
  title = {{A} forecasting model for desert locust presence during recession period, using real-time satellite imagery},
  author = {{M}arescot, {L}. and {F}ernandez, {E}lodie and {D}ridi, {H}. and {B}enahi, {A}. {S}. and {H}amouny, {M}. {L}. and {M}aeno, {K}. {O}. and {P}aolini, {G}. and {P}iou, {C}.},
  editor = {},
  language = {{ENG}},
  abstract = {{D}esert locust ({S}chistocerca gregaria) is a major agricultural pest that poses significant socioeconomic challenges to food security. {T}his study aims to enhance preventive management of desert locusts in {W}estern and {N}orthern {A}frica by improving an operational model developed by {P}iou et al. (2019). {T}he model employs satellite remote sensing data and machine learning to forecast locust occurrence at a 1 km2 resolution every ten days. {O}bjectives include identifying environmental risk factors, training random forest models with high-predictive power and providing updated forecasts via a web interface. {I}t is the first implementation of a statistical forecasting model for this species within an automated system, delivering updated locust presence probabilities every ten days. {V}alidated through field surveys with a positive error rate of 23%, the forecasting tool shows a strong correlation between predicted probabilities and observed locust densities. {T}his operational tool can guide survey teams, optimize resource allocation, and mitigate environmental impacts efficiently. {W}e believe continuous evaluation and integration of the forecast system will enhance its effectiveness in preventing locust outbreaks, thereby safeguarding food security in the region.},
  keywords = {{A}utomatic forecast system ; {L}ocust outbreak ; {M}achine learning ; {R}emote sensing ; {S}chistocerca gregaria ; {AFRIQUE} {DE} {L}'{OUEST} ; {AFRIQUE} {DU} {NORD}},
  booktitle = {},
  journal = {{R}emote {S}ensing {A}pplications : {S}ociety and {E}nvironment},
  volume = {37},
  numero = {},
  pages = {101497 [15 p.]},
  ISSN = {2352-9385},
  year = {2025},
  DOI = {10.1016/j.rsase.2025.101497},
  URL = {https://www.documentation.ird.fr/hor/fdi:010092869},
}