EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using deep learning to assess the toxicological effects of sublethal exposure of a novel green pesticide in a stored‐product beetle

Anita Casadei iD, Maria C Boukouvala, Gianluca Manduca iD, Nickolas G Kavallieratos iD, Filippo Maggi iD, Marta Ferrati iD, Eleonora Spinozzi, Cesare Stefanini, Antonio DeSimone iD, Donato Romano

Pest Management Science · 2026

DOI: 10.1002/ps.70545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pest Management Science, 2026. Verfasst von Anita Casadei und 9 weiteren Autor:innen. Beteiligte Einrichtung: The BioRobotics Institute, Sant'Anna School of Advanced Studies, Pisa, Italy. Hauptthemen laut MEDLINE: Coleoptera, Behavior, Animal, Plant Extracts, Insect Control. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: COST Action 20132 - Urban Tree Guard - Safeguarding European urban trees and forests through improved biosecurity, Italian Space Agency (ASI) DC-DSR-UVS-2022-375 Project "pRomoting pEdogenesis throuGh lunar sOil-terrestriaL organIsms interaction For moon FErtilization - REG…, HORIZON-EIC-2023-PATHFINDEROPEN-01, SENSORBEES "Sensorbees are ENhanced Self-ORganizing Bio-hybrids for Ecological and Environmental Surveillance".

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND Managing stored‐grain pests requires new strategies to limit economic and health risks. This study analyses the sublethal effects of the natural compound carlina oxide on Prostephanus truncatus , providing new behavioural insights through a multidisciplinary approach. A fully automatic computer vision approach was developed to label two specific insect body parts, enabling the generation of an annotated dataset without manual intervention. This dataset was used to train a convolutional neural network (CNN) for pose estimation. A second dedicated CNN focused on the antennae to investigate neuroethological and sensory variations. RESULTS CNN for body parts detection achieved an average precision of 0.78, recall of 0.90, and F1 score of 0.84 on the test dataset. An additional CNN tracked key points for antennal pose estimation. Motor analysis showed that the LC 30 of carlina oxide reduced average speed and distance, induced altered exploratory behaviour, and affected thigmotaxis. Statistically significant features were evaluated using machine learning classifiers: random forest, support vector machine, and K‐nearest neighbours. The analysis comparing control and treated groups distinguishes LC 30 and LC 10 from the control group, while SHapley Additive exPlanation (SHAP) analysis explained the features contribution to predictions. CONCLUSIONS Metrics poorly distinguish individuals in the LC 10 and LC 30 classes, supporting the employment of lower sublethal concentration for the control of P. truncatus . However, our findings indicate possible neuroethological effects of green pesticides on sensory systems, highlighting the need for an accurate risk assessment to minimize ecosystem impacts and supporting integrated pest management within One‐Health and Eco‐Health frameworks. © 2026 The Author(s). Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ColeopteraBehavior, AnimalPlant ExtractsInsect ControlDeep LearningMaleFemaleAnimalsConvolutional Neural NetworksAsteraceaeInsecticidesToxicity TestsAlkynesFurans

Stichwörter der Autor:innen

Prostephanus truncatuscarlina oxidemachine learningmotor behaviournatural control

Substanzen

carlina oxidePlant ExtractsInsecticidesAlkynesFurans

Autor:innen und Institutionen

  • The BioRobotics Institute, Sant'Anna School of Advanced Studies, Pisa, Italy.
  • Department of Excellence in Robotics and AI, Sant'Anna School of Advanced Studies, Pisa, Italy.
  • Laboratory of Agricultural Zoology and Entomology, Department of Crop Science, Agricultural University of Athens, Attica, Greece.
  • ChIP-Chemistry Interdisciplinary Project Research Center, School of Pharmacy, University of Camerino, Camerino, Italy.
  • Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence, Masdar, UAE.

ORCID-Profile: Anita Casadei, Gianluca Manduca, Nickolas G Kavallieratos, Filippo Maggi, Marta Ferrati, Antonio DeSimone

Förderung

  • COST Action 20132 - Urban Tree Guard - Safeguarding European urban trees and forests through improved biosecurity
  • Italian Space Agency (ASI) DC-DSR-UVS-2022-375 Project "pRomoting pEdogenesis throuGh lunar sOil-terrestriaL organIsms interaction For moon FErtilization - REG…
  • HORIZON-EIC-2023-PATHFINDEROPEN-01, SENSORBEES "Sensorbees are ENhanced Self-ORganizing Bio-hybrids for Ecological and Environmental Surveillance"
  • Italian Space Agency (ASI) DC-DSR-U.S.hyphen;2022-375 Project "pRomoting pEdogenesis throuGh lunar sOil-terrestriaL organIsms interaction For moon FErtilizatio…

Zitieren

APA

Casadei, A., Boukouvala, M. C., Manduca, G., Kavallieratos, N. G., Maggi, F., Ferrati, M., Spinozzi, E., Stefanini, C., DeSimone, A., & Romano, D. (2026). Using deep learning to assess the toxicological effects of sublethal exposure of a novel green pesticide in a stored‐product beetle. Pest Management Science. https://doi.org/10.1002/ps.70545

Vancouver

Casadei A, Boukouvala MC, Manduca G, Kavallieratos NG, Maggi F, Ferrati M, et al. Using deep learning to assess the toxicological effects of sublethal exposure of a novel green pesticide in a stored‐product beetle. Pest Management Science. 2026. doi:10.1002/ps.70545

BibTeX
@article{Casadei2026,
  author = {Casadei, Anita and Boukouvala, Maria C and Manduca, Gianluca and Kavallieratos, Nickolas G and Maggi, Filippo and Ferrati, Marta and Spinozzi, Eleonora and Stefanini, Cesare and DeSimone, Antonio and Romano, Donato},
  title = {Using deep learning to assess the toxicological effects of sublethal exposure of a novel green pesticide in a stored‐product beetle},
  journal = {Pest Management Science},
  year = {2026},
  doi = {10.1002/ps.70545}
}
Kostenlos starten →