Smart insect trap: insect identification and classification using iNaturalist and ChatGPT
- 1Department of Electrical and Computer Engineering, Cornell University 1 , Ithaca, NY, USA
- 2Department of Biological and Environmental Engineering, Cornell University 2 , Ithaca, NY, USA
- 3Department of Computer Science, Cornell University 3 , Ithaca, NY, USA
Abstract
Insect identification is crucial for sustainable agriculture and pest control, as it helps determine the pest type, reduces human labour, and decreases reliance on pesticides. However, there are a number of challenges associated with AI-based insect identification and classification, such as the lack of reliable data sources, imbalanced datasets and difficulty of annotation. Our paper offers a practical solution to these challenges using online platforms. Specifically, we coordinate multiple AI tools in an agentic-AI-style workflow: iNaturalist's computer vision model identifies the insect, ChatGPT determines whether it is a pest and the result drives a low-cost robotic trap. This approach is particularly accessible for non-experts, as it does not require extensive knowledge of machine learning or computer vision, and each component can be upgraded as better AI tools emerge. The system was further validated through field testing using images collected under real agricultural conditions. The results show our method is able to identify and differentiate insect species with sufficient accuracy. Our approach would be more accessible, reliable and efficient than traditional methods and can be used to identify a wider range of insect species.
Related
- Identification by MALDI-TOF MS of Coleopteran insect pests collected in the field
- IoT-enabled smart home activity classification using BiLSTM and attention mechanisms
- iNaturalist records reveal shifts in phenology of caterpillar (Lepidoptera) activity in response to warmer spring temperatures
- Hyperparameter-Tuned K-Nearest Neighbor for Herbal Leaf Classification Using Shape, Color, and Texture Feature Fusion in Smart Agriculture
- A coarse-to-fine modulation classification scheme utilizing Transformers and Liquid Neural Networks for Smart Grids
BibTeX
@article{wu2026smart,
title = {{Smart insect trap: insect identification and classification using iNaturalist and ChatGPT}},
author = {Yuhan Wu and Anthony Nicolaides and Anthony Coffin-Schmitt and Sunghwan Jung},
journal = {Royal Society Open Science},
year = {2026},
month = oct,
doi = {10.1098/rsos.251212},
url = {https://royalsocietypublishing.org/rsos/article/13/10/251212/483912/Smart-insect-trap-insect-identification-and},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Smart insect trap: insect identification and classification using iNaturalist and ChatGPT
AU - Yuhan Wu
AU - Anthony Nicolaides
AU - Anthony Coffin-Schmitt
AU - Sunghwan Jung
PY - 2026
DA - 2026/10/07
JO - Royal Society Open Science
DO - 10.1098/rsos.251212
UR - https://royalsocietypublishing.org/rsos/article/13/10/251212/483912/Smart-insect-trap-insect-identification-and
AB - Insect identification is crucial for sustainable agriculture and pest control, as it helps determine the pest type, reduces human labour, and decreases reliance on pesticides. However, there are a number of challenges associated with AI-based insect identification and classification, such as the lack of reliable data sources, imbalanced datasets and difficulty of annotation. Our paper offers a practical solution to these challenges using online platforms. Specifically, we coordinate multiple AI tools in an agentic-AI-style workflow: iNaturalist's computer vision model identifies the insect, ChatGPT determines whether it is a pest and the result drives a low-cost robotic trap. This approach is particularly accessible for non-experts, as it does not require extensive knowledge of machine learning or computer vision, and each component can be upgraded as better AI tools emerge. The system was further validated through field testing using images collected under real agricultural conditions. The results show our method is able to identify and differentiate insect species with sufficient accuracy. Our approach would be more accessible, reliable and efficient than traditional methods and can be used to identify a wider range of insect species.
SN - 2054-5703
ER -