Automated machine learning for identification of pest aphid species (Hemiptera: Aphididae)

  • Masayuki HayashiEmail author
  • Kazuhiko Tamai
  • Yuta Owashi
  • Kazuki Miura
Technical Note


Effective crop protection requires accurate and rapid detection and identification of pest species. However, identification usually requires the involvement of experts. It would be useful to develop means to support pest identification. Although machine learning techniques have been applied to multiple fields including pest identification, expert knowledge for modeling was required to construct a high-accuracy model. In recent years, machine learning platforms that automatically construct a model are offered by IT firms. We tested whether automated machine learning using Google Cloud AutoML Vision was useful for identifying pest species. We trained machine learning models to identify aphids of three species—Aphis craccivora Koch, Acyrthosiphon pisum Harris, and Megoura crassicauda Mordivilko (Hemiptera: Aphididae)—sharing host plants and assessed accuracies. Models were constructed using 20, 50, 100, 200, and 400 images per species, with and without augmentation of training data volume by image inversion. The accuracy of identification increased with the number of training images and with the use of inverted images. Since the rates of correct identification were > 0.96 when the models were trained with 400 images per species with inversion, we consider automated machine learning to be useful for pest species identification.


Automated machine learning AutoML Pest identification Image analysis Aphid 



  1. Ataş M, Yardimci Y, Temizel A (2012) A new approach to aflatoxin detection in chili pepper by machine vision. Comput Electron Agric 87:129–141CrossRefGoogle Scholar
  2. Behmann J, Mahlein AK, Rumpf T, Römer C, Plümer L (2015) A review of advanced machine learning methods for the detection of biotic stress in precision crop protection. Precis Agric 16:239–260CrossRefGoogle Scholar
  3. Bishop CM (2006) Pattern recognition and machine learning. Springer, BerlinGoogle Scholar
  4. Chlingaryan A, Sukkarieh S, Whelan B (2018) Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: a review. Comput Electron Agric 151:61–69CrossRefGoogle Scholar
  5. Cruz A, Ampatzidis Y, Pierro R, Materazzi A, Panattoni A, De Bellis L, Luvisi A (2019) Detection of grapevine yellows symptoms in Vitis vinifera L. with artificial intelligence. Comput Electron Agric 157:63–76CrossRefGoogle Scholar
  6. Ding W, Taylor G (2016) Automatic moth detection from trap images for pest management. Comput Electron Agric 123:17–28CrossRefGoogle Scholar
  7. Feng P, Wang B, Li Liu D, Yu Q (2019) Machine learning-based integration of remotely-sensed drought factors can improve the estimation of agricultural drought in South-Eastern Australia. Agric Syst 173:303–316CrossRefGoogle Scholar
  8. Feurer M, Klein A, Eggensperger K, Springenberg J, Blum M, Hutter F (2015) Efficient and robust automated machine learning. Adv Neural Inf Process Syst 28:2962–2970Google Scholar
  9. Gaston KJ, O’Neill MA (2004) Automated species identification: why not? Philos Trans R Soc B 359:655–667CrossRefGoogle Scholar
  10. Google (2019) AutoML Vision Beginner’s Guide: Accessed 7 Sept 2019
  11. Hayashi M, Nakamuta K, Nomura M (2015) Ants learn aphid species as mutualistic partners: is the learning behavior species-specific? J Chem Ecol 41:1148–1154CrossRefGoogle Scholar
  12. Katayama N, Suzuki N (2003) Changes in the use of extrafloral nectaries of Vicia faba (Leguminosae) and honeydew of aphids by ants with increasing aphid density. Ann Entomol Soc Am 96:579–584CrossRefGoogle Scholar
  13. Kotthoff L, Thornton C, Hoos HH, Hutter F, Leyton-Brown K (2017) Auto-WEKA 2.0: automatic model selection and hyperparameter optimization in WEKA. J Mach Learn Res 18:826–830Google Scholar
  14. Lee M, Xing SA (2018) Study of tangerine pest recognition using advanced deep learning methods. Preprints. Google Scholar
  15. Li F, Xiong Y (2018) Automatic identification of butterfly species based on HoMSC and GLCMoIB. Visual Comput 34:1525–1533CrossRefGoogle Scholar
  16. R Development Core Team (2018) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria Accessed 7 Sept 2019
  17. Rehman TU, Mahmud MS, Chang YK, Jin J, Shin J (2019) Current and future applications of statistical machine learning algorithms for agricultural machine vision systems. Comput Electron Agric 156:585–605CrossRefGoogle Scholar
  18. US EPA (2019) Integrated Pest Management (IPM) Principles. United States Environmental Protection Agency: Accessed 7 Sept 2019
  19. Weeks PJD, O’Neill MA, Gaston KJ, Gauld ID (1999) Automating insect identification: exploring the limitations of a prototype system. J Appl Entomol 123:1–8CrossRefGoogle Scholar
  20. Wu R, Yan S, Shan Y, Dang Q, Sun G (2015) Deep image: Scaling up image recognition. arXiv:1501.02876. Accessed 7 Sept 2019

Copyright information

© The Japanese Society of Applied Entomology and Zoology 2019

Authors and Affiliations

  1. 1.Western Region Agricultural Research CenterNational Agriculture and Food Research OrganizationFukuyamaJapan
  2. 2.Faculty of HorticultureChiba UniversityMatsudoJapan
  3. 3.Earth CorporationAkoJapan

Personalised recommendations