Cannet A. auteur aut IRD Simon-Chane C. auteur aut IRD Histace A. auteur aut IRD Akhoundi M. auteur aut IRD Romain O. auteur aut IRD Souchaud M. auteur aut IRD Jacob P. auteur aut IRD Sereno D. auteur aut IRD Volf P. auteur aut IRD Dvorak V. auteur aut IRD Sereno Denis auteur aut IRD text journalArticle eng text/pdf reformatted digital access Sandflies (Diptera; Psychodidae) are medical and veterinary vectors that transmit diverse parasitic, viral, and bacterial pathogens. Their identification has always been challenging, particularly at the specific and sub-specific levels, because it relies on examining minute and mostly internal structures. Here, to circumvent such limitations, we have evaluated the accuracy and reliability of Wing Interferential Patterns (WIPs) generated on the surface of sandfly wings in conjunction with deep learning (DL) procedures to assign specimens at various taxonomic levels. Our dataset proves that the method can accurately identify sandflies over other dipteran insects at the family, genus, subgenus, and species level with an accuracy higher than 77.0%, regardless of the taxonomic level challenged. This approach does not require inspection of internal organs to address identification, does not rely on identification keys, and can be implemented under field or near-field conditions, showing promise for sandfly pro-active and passive entomological surveys in an era of scarcity in medical entomologists. specialized 052 020 13 1 21389 [9 ] 2023 2045-2322 https://www.documentation.ird.fr/hor/fdi:010089714 10.1038/s41598-023-48685-2 2045-2322 [F B010089714] https://www.documentation.ird.fr/hor/fdi:010089714 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2024-05/010089714.pdf IRD - Base Horizon / Pleins textes 2024-05-22 2026-06-12 fdi:010089714 fre