InsectNet: Real-time identification of insects using an end-to-end machine learning pipeline
PNAS Nexus · 23.12.2024 · 4 (1)
DOI: 10.1093/pnasnexus/pgae575 ↗Kurz gefasst
Fachartikel in der Zeitschrift PNAS Nexus, online erschienen am 27.12.2024. Verfasst von Shivani Chiranjeevi und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Iowa State University, Ames, IA 50011, USA. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: USDA-NIFA, NSF, CPS.
Abstract (Originalsprache)
Insect pests significantly impact global agricultural productivity and crop quality. Effective integrated pest management strategies require the identification of insects, including beneficial and harmful insects. Automated identification of insects under real-world conditions presents several challenges, including the need to handle intraspecies dissimilarity and interspecies similarity, life-cycle stages, camouflage, diverse imaging conditions, and variability in insect orientation. An end-to-end approach for training deep-learning models, InsectNet, is proposed to address these challenges. Our approach has the following key features: (i) uses a large dataset of insect images collected through citizen science along with label-free self-supervised learning to train a global model, (ii) fine-tuning this global model using smaller, expert-verified regional datasets to create a local insect identification model, (iii) which provides high prediction accuracy even for species with small sample sizes, (iv) is designed to enhance model trustworthiness, and (v) democratizes access through streamlined machine learning operations. This global-to-local model strategy offers a more scalable and economically viable solution for implementing advanced insect identification systems across diverse agricultural ecosystems. We report accurate identification (>96% accuracy) of numerous agriculturally and ecologically relevant insect species, including pollinators, parasitoids, predators, and harmful insects. InsectNet provides fine-grained insect species identification, works effectively in challenging backgrounds, and avoids making predictions when uncertain, increasing its utility and trustworthiness. The model and associated workflows are available through a web-based portal accessible through a computer or mobile device. We envision InsectNet to complement existing approaches, and be part of a growing suite of AI technologies for addressing agricultural challenges.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical Engineering, Iowa State University, Ames, IA 50011, USA.
- Department of Computer Science, Iowa State University, Ames, IA 50011, USA.
- Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ 85721, USA.
- Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
- Department of Plant Pathology, Entomology and Microbiology, Iowa State University, Ames, IA 50011, USA.
- Data Science Institute, University of Arizona, Tucson, AZ 85721, USA.
ORCID-Profile: Mojdeh Saadati, Talukder Z Jubery, Daren S Mueller, Nirav Merchant, Asheesh K Singh, Soumik Sarkar, Baskar Ganapathysubramanian
Förderung
- USDA-NIFA
- NSF
- CPS
- Smart Integrated Farm Network for Rural Agricultural Communities
- USDA
- Plant Sciences Institute
Zitieren
APA
Chiranjeevi, S., Saadati, M., Deng, Z. K., Koushik, J., Jubery, T. Z., Mueller, D. S., O'Neal, M., Merchant, N., Singh, A., Singh, A. K., Sarkar, S., Singh, A., & Ganapathysubramanian, B. (2024). InsectNet: Real-time identification of insects using an end-to-end machine learning pipeline. PNAS Nexus, 4(1). https://doi.org/10.1093/pnasnexus/pgae575
Vancouver
Chiranjeevi S, Saadati M, Deng ZK, Koushik J, Jubery TZ, Mueller DS, et al. InsectNet: Real-time identification of insects using an end-to-end machine learning pipeline. PNAS Nexus. 2024;4(1). doi:10.1093/pnasnexus/pgae575
BibTeX
@article{Chiranjeevi2024,
author = {Chiranjeevi, Shivani and Saadati, Mojdeh and Deng, Zi K and Koushik, Jayanth and Jubery, Talukder Z and Mueller, Daren S and O'Neal, Matthew and Merchant, Nirav and Singh, Aarti and Singh, Asheesh K and Sarkar, Soumik and Singh, Arti and Ganapathysubramanian, Baskar},
title = {InsectNet: Real-time identification of insects using an end-to-end machine learning pipeline},
journal = {PNAS Nexus},
year = {2024},
volume = {4},
number = {1},
doi = {10.1093/pnasnexus/pgae575}
}
EUVIMED