Deep learning powered real-time identification of insects using citizen science data

by   Shivani Chiranjeevi, et al.

Insect-pests significantly impact global agricultural productivity and quality. Effective management involves identifying the full insect community, including beneficial insects and harmful pests, to develop and implement integrated pest management strategies. Automated identification of insects under real-world conditions presents several challenges, including differentiating similar-looking species, intra-species dissimilarity and inter-species similarity, several life cycle stages, camouflage, diverse imaging conditions, and variability in insect orientation. A deep-learning model, InsectNet, is proposed to address these challenges. InsectNet is endowed with five key features: (a) utilization of a large dataset of insect images collected through citizen science; (b) label-free self-supervised learning for large models; (c) improving prediction accuracy for species with a small sample size; (d) enhancing model trustworthiness; and (e) democratizing access through streamlined MLOps. This approach allows accurate identification (>96 of over 2500 insect species, including pollinator (e.g., butterflies, bees), parasitoid (e.g., some wasps and flies), predator species (e.g., lady beetles, mantises, dragonflies) and harmful pest species (e.g., armyworms, cutworms, grasshoppers, stink bugs). InsectNet can identify invasive species, provide fine-grained insect species identification, and work effectively in challenging backgrounds. It also can abstain from making predictions when uncertain, facilitating seamless human intervention and making it a practical and trustworthy tool. InsectNet can guide citizen science data collection, especially for invasive species where early detection is crucial. Similar approaches may transform other agricultural challenges like disease detection and underscore the importance of data collection, particularly through citizen science efforts..


page 4

page 10

page 13

page 15

page 18

page 39

page 40


A Computer Vision Approach to Combat Lyme Disease

Lyme disease is an infectious disease transmitted to humans by a bite fr...

Identifying 3 moss species by deep learning, using the "chopped picture" method

In general, object identification tends not to work well on ambiguous, a...

CWD30: A Comprehensive and Holistic Dataset for Crop Weed Recognition in Precision Agriculture

The growing demand for precision agriculture necessitates efficient and ...

Experiential-Informed Data Reconstruction for Fishery Sustainability and Policies in the Azores

Fishery analysis is critical in maintaining the long-term sustainability...

Hawkes Processes for Invasive Species Modeling and Management

The spread of invasive species to new areas threatens the stability of e...

A Semantic Cross-Species Derived Data Management Application

Managing dynamic information in large multi-site, multi-species, and mul...

Comparative study on supervised learning methods for identifying phytoplankton species

Phytoplankton plays an important role in marine ecosystem. It is defined...

Please sign up or login with your details

Forgot password? Click here to reset