Deep Learning Approach for Species Identification of Forensically Important Sarcophagid flies (Diptera: Sarcophagidae) in China
Insects · 01.04.2026 · 17 (4) · 374
DOI: 10.3390/insects17040374 ↗Kurz gefasst
Fachartikel in der Zeitschrift Insects, online erschienen am 01.04.2026. Verfasst von Sen Hou und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Forensic Medicine, Jining Medical University, Jining 272067, China. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Special Foundation of Taishan Scholars Program, Natural Science Foundation of Hunan Province, Shanghai Key Lab of Forensic Medicine, Key Lab of Forensic Science, Ministry of Justice, China (Academy of Forensic Science).
Abstract (Originalsprache)
Accurate species identification of necrophagous flies is fundamental to forensic entomology, particularly for postmortem interval (PMI) estimation in decomposed remains. Here, we conducted a targeted carrion-baited survey along the Shandong Peninsula and documented 15 Sarcophaga species, including the first regional records of S. cinerea, S. pingi, and S. pterygota. We established an expert-validated image dataset for automated identification. We then developed a parameter-efficient identification framework by fine-tuning a pretrained Vision Transformer with Low-Rank Adaptation (ViT-LoRA) on this custom dataset. Compared with conventional CNN-based models, ViT-LoRA achieved 98.50% species-level accuracy while updating only ~0.16 M trainable parameters, and it converged rapidly and stably within ~10 epochs, demonstrating efficient adaptation under limited training data. This study provides faunistic and distributional data on carrion-associated Sarcophaga species in the coastal Shandong Peninsula, characterizes their regional distribution patterns, and offers a scalable image-based identification approach for forensically important sarcophagid flies.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Forensic Medicine, Jining Medical University, Jining 272067, China.
- College of Computer Science, Nankai University, Tianjin 300350, China.
- Department of Forensic Science, School of Basic Medical Sciences, Central South University, Changsha 410083, China.
- Department of Forensic Science, School of Basic Medical Sciences, Inner Mongolia Medical University, Hohhot 010110, China.
- Shanghai Key Lab of Forensic Medicine, Key Lab of Forensic Science of Ministry of Justice, Shanghai 570100, China.
Förderung
- Special Foundation of Taishan Scholars Program
- Natural Science Foundation of Hunan Province
- Shanghai Key Lab of Forensic Medicine, Key Lab of Forensic Science, Ministry of Justice, China (Academy of Forensic Science)
- Natural Science Foundation of Inner Mongolia Autonomous Region
Zitieren
APA
Hou, S., Su, J., Yao, X., Li, X., Du, J., Li, J., Jiang, F., Xia, Y., Zhang, S., Cui, W., Wang, Y., & Ren, L. (2026). Deep Learning Approach for Species Identification of Forensically Important Sarcophagid flies (Diptera: Sarcophagidae) in China. Insects, 17(4), 374. https://doi.org/10.3390/insects17040374
Vancouver
Hou S, Su J, Yao X, Li X, Du J, Li J, et al. Deep Learning Approach for Species Identification of Forensically Important Sarcophagid flies (Diptera: Sarcophagidae) in China. Insects. 2026;17(4):374. doi:10.3390/insects17040374
BibTeX
@article{Hou2026,
author = {Hou, Sen and Su, Jiali and Yao, Xinyi and Li, Xinglin and Du, Jinliang and Li, Jianxia and Jiang, Futeng and Xia, Yang and Zhang, Shuguang and Cui, Wen and Wang, Yequan and Ren, Lipin},
title = {Deep Learning Approach for Species Identification of Forensically Important Sarcophagid flies (Diptera: Sarcophagidae) in China},
journal = {Insects},
year = {2026},
volume = {17},
number = {4},
pages = {374},
doi = {10.3390/insects17040374}
}
EUVIMED