InsectNet: Real-time identification of insects using an end-to-end machine learning pipeline
Open Access
- 23 December 2024
- journal article
- Published by Oxford University Press (OUP) in PNAS Nexus
- Vol. 4 (1) , pgae575
Abstract
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.Keywords
Funding Information
- USDA-NIFA (#2021-67021-35329)
- NSF
- CPS (#1954556)
- Smart Integrated Farm Network for Rural Agricultural Communities (#1952045)
- USDA (IOW04714)
- Plant Sciences Institute
This publication has 47 references indexed in Scilit:
- Survey on crop pest detection using deep learning and machine learning approachesMultimedia Tools and Applications, 2023
- Plant phenotyping with limited annotation: Doing more with lessThe Plant Phenome Journal, 2022
- Real‐time insect tracking and monitoring with computer vision and deep learningRemote Sensing in Ecology and Conservation, 2021
- Citrus pests classification using an ensemble of deep learning modelsComputers and Electronics in Agriculture, 2021
- Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf diseaseComputers and Electronics in Agriculture, 2020
- Occurrence prediction of cotton pests and diseases by bidirectional long short-term memory networks with climate and atmosphere circulationComputers and Electronics in Agriculture, 2020
- Species‐level image classification with convolutional neural network enables insect identification from habitus imagesEcology and Evolution, 2019
- ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases2018
- Automatic classification for field crop insects via multiple-task sparse representation and multiple-kernel learningComputers and Electronics in Agriculture, 2015
- Microsoft COCO: Common Objects in Context2014