A Swin Transformer-based model for mosquito species identification

• Published in: Scientific reports 2022-11, Vol.12 (1), p.18664-13, Article 18664
• Main Authors: Zhao, De-zhong, Wang, Xin-kai, Zhao, Teng, Li, Hu, Xing, Dan, Gao, He-ting, Song, Fan, Chen, Guo-hua, Li, Chun-xiao
• Format: Article
• Language: English
• Subjects: 631/114/1305; 631/114/1386; 631/601/1466; 704/158/2178; Animals; Aquatic insects; Culex; Deep learning; Humanities and Social Sciences; Humans; Morphology; Mosquito Vectors; Mosquitoes; multidisciplinary; Neural networks; Neural Networks, Computer; Parasites; Science; Science (multidisciplinary); Species; Vector-borne diseases
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-022-21017-6

Mosquito transmit numbers of parasites and pathogens resulting in fatal diseases. Species identification is a prerequisite for effective mosquito control. Existing morphological and molecular classification methods have evitable disadvantages. Here we introduced Deep learning techniques for mosquito species identification. A balanced, high-definition mosquito dataset with 9900 original images covering 17 species was constructed. After three rounds of screening and adjustment-testing (first round among 3 convolutional neural networks and 3 Transformer models, second round among 3 Swin Transformer variants, and third round between 2 images sizes), we proposed the first Swin Transformer-based mosquito species identification model (Swin MSI) with 99.04% accuracy and 99.16% F1-score. By visualizing the identification process, the morphological keys used in Swin MSI were similar but not the same as those used by humans. Swin MSI realized 100% subspecies-level identification in Culex pipiens Complex and 96.26% accuracy for novel species categorization. It presents a promising approach for mosquito identification and mosquito borne diseases control.