Automated detection and classification of morphologically similar weevil species using AI for precision pest monitoring

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.

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-11-19
DOI
https://doi.org/10.64898/2026.11.17.767224
Primary Topic
Smart Agriculture and AI
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Automated detection and classification of morphologically similar weevil species using AI for precision pest monitoring

Xanthe A. Shirley, Charles P.‐C. Suh, Zachary Cohen, Lindsey Perkin et al.
bioRxiv (Cold Spring Harbor Laboratory)
Smart Agriculture and AI
preprint

Automated detection and classification of morphologically similar weevil species using AI for precision pest monitoring

Xanthe A. Shirley, Charles P.‐C. Suh, Zachary Cohen, Lindsey Perkin, Adama R. Tukuli, Tyler Jay Raszick
preprint en

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.

bioRxiv (Cold Spring Harbor Laboratory)
Animal and Plant Health Inspection Service (US), Agricultural Research Service (US), United States Department of Agriculture (US)
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon