Automated detection and classification of morphologically similar weevil species using AI for precision pest monitoring
Year: 2026
Type: preprint
Abstract: Accurate identification of morphologically similar insects is important for agricultural surveillance but remains challenging when large and balanced image datasets are limited. We developed Rostrum Recognition: A Weevil Identification Tool (RRWIT), a lightweight object-detection framework for distinguishing 14 weevil taxa, including two economically important weevil species, the boll weevil and pecan weevil, using more than 16,000 expert-verified annotated images. RRWIT was developed by transfer learning from a pretrained YOLO11n detector using a stratified data partition with the test set withheld from model and threshold selection. We evaluated this design with matched random-initialization and transfer-learning experiments, quantitative EigenGradCAM attribution analysis, targeted architectural modifications, and a frozen eight-framework benchmark across three independent training seeds. In the cross-framework benchmark, RRWIT achieved a mean average precision at an intersection-over-union threshold of 0.50 (mAP50) of 0.938 ± 0.005 on held-out test partitions subset, whereas the newer lightweight YOLO26n achieved the highest value, 0.976 ± 0.010, with a similarly compact computational footprint. Post-training 8-bit integer (INT8) quantization reduced the serialized RRWIT model from 10.09 to 2.91 MiB (71.2%) with a small validation mAP50 change from 0.978 to 0.971 but did not accelerate end-to-end inference under the tested central processing unit configuration. RRWIT therefore provides an extensible foundation for automated weevil identification while highlighting the importance of representative biological data, independent external validation, evolving lightweight architectures, and hardware-specific deployment optimization in future development. A publicly accessible RRWIT web application supporting image upload and live image capture for automated weevil detection and classification is available at https://huggingface.co/spaces/adamartukuli/RRWIT .
Institution: Southern Plains Agricultural Research Center
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7236691351
