Investigation of Deep Learning Approaches for Identification of Important Wheat Pests in Central Anatolia

Abstract

Artificial intelligence-based systems play a crucial role in Integrated Pest Management studies. It is important to develop and support such systems for controlling wheat pests, which cause significant losses in wheat production which is strategic importance, particularly in Turkey. This study employed various pre-trained deep learning approaches to identify key wheat pests in the Central Anatolia Region, namely Aelia spp., Anisoplia spp., Eurygaster spp., Pachytychius hordei, and Zabrus spp. The models' classification success was determined using open and original datasets. Among the models, the ResNet-18 model outperformed others, achieving a classification success rate of 99%. Furthermore, each model was tested with original images collected during field studies to assess their effectiveness. The results demonstrate that pre-trained deep learning models can be utilized for the identification of important wheat pests in Central Anatolia as part of Integrated Pest Management.

Keywords

• Important Wheat Pests
• Insect Classification
• Deep Learning
• CNN
• Transfer Learning
• ResNet-18

Supporting Institution

Science Fellowships and Grant Programmes Department (TUBİTAK BİDEB)

Project Number

1919B012107851

Thanks

This study was supported by the project 1919B012107851 no. within the scope of the 2209-A University Students Research Projects Support Program carried out by Science Fellowships and Grant Programmes Department (TUBİTAK BİDEB). We also thank Directorate of Plant Protection Central Research Institute, Republic of Türkiye Ministry of Agriculture and Forestry for support in generating the original data set.

References

1. 1. Maslow AH. A theory of human motivation. Psychol Rev. 1943 50(4):370-396.
2. 2. Agrios NG. Plant pathology. San Diego (USA): Elsevier Academic Press; 2005.
3. 3. Polat K. Tarım Ürünleri Piyasaları [Internet]. Turkey (SGB): Tarımsal Ekonomi ve Politika Geliştirme Enstitüsü; 2021 [reviewed 2022 Dec 15; cited 2022 Dec 20]. Available from: https://arastirma. tarimorman.gov.tr/tepge/Belgeler/PDF%20Tar%C4%B1m%20 %C3%9Cr%C3%BCnleri%20Piyasalar%C4%B1/2021-Ocak%20 Ta r%C4%B1m%20%C3%9Cr%C3%BCnler i%20Raporu/ Bu%C4%9Fday,%20Ocak%202021,%20Tar%C4%B1m%20 %C3%9Cr%C3%BCnleri%20Piyasa%20Raporu.pdf
4. 4. FAO. World Food and Agriculture – Statistical Yearbook 2022. Rome: https://doi.org/10.4060/cc2211en; 2022.
5. 5. Babaroğlu NE, Akci E, Çulcu M, Yalçın F. Süne ve Mücadelesi. Ankara (TR): Tarım ve Orman Bakanlığı Gıda ve Kontrol Genel Müdürlüğü; 2020.
6. 6. Zirai Mücadele Teknik Talimatları Cilt 1. Ankara (TR): Gıda Tarım ve Hayvancılık Bakanlığı Tarımsal Araştırmalar ve Politikalar Genel Müdürlüğü Bitki Sağlığı Araştırmaları Daire Başkanlığı; 2008.
7. 7. Hububat Zararlıları [Internet]. [place unknown: publisher unknown]; [reviewed 2022 Dec 16; cited 2022 Dec 20]. Available from: https://arastirma.tarimorman.gov.tr/zmmae/Belgeler/ Sol%20Menu/Zirai%20M%C3%BCcadele%20Rehberi/Hububat/ Hububat-Zararl%C4%B1.pdf
8. 8. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-444.

9. 9. Hayit T, Erbay H, Varçın F, Hayit F, Akci N. Determination of the severity level of yellow rust disease in wheat by using convolutional neural networks. JPP. 2021;103(3):923-934.
10. 10. Hayıt T, Erbay H, Varçın F, Hayit F, Akci N. The classification of wheat yellow rust disease based on a combination of textural and deep features. Multimedia Tools and Applications. 2023:1-19.
11. 11. Zhu LQ, Ma MY, Zhang Z, et al. Hybrid deep learning for automated lepidopteran insect image classification. Oriental Insects. 2017;51(2):79-91.
12. 12. Lim S, Kim S, Kim D. Performance effect analysis for insect classification using convolutional neural network. In 2017 7th IEEE International Conference on Control System, Computing and Engineering. 2017; Penang, Malaysia; 2017. p. 210-215.
13. 13. Xia D, Chen P, Wang B, Zhang J, Xie C. Insect detection and classification based on an improved convolutional neural network. Sensors. 2018;18(12):4169.
14. 14. Marques ACR, Raimundo MM, Cavalheiro EMB, et al. Ant genera identification using an ensemble of convolutional neural networks. Plos One. 2018;13(1):e0192011.
15. 15. Lu CY, Rustia DJA, Lin TT. Generative adversarial network based image augmentation for insect pest classification enhancement. IFAC-PapersOnLine. 2019;52(30):1-5.
16. 16. Thenmozhi K, Reddy US. Crop pest classification based on deep convolutional neural network and transfer learning. Comput Electron Agric. 2019;164(104906).
17. 17. Hansen OL, Svenning JC, Olsen K, et al. Species‐level image classification with convolutional neural network enables insect identification from habitus images. Ecol Evol. 2020;10(2):737-747.
18. 18. Nanni L, Maguolo G, Pancino F. Insect pest image detection and recognition based on bio-inspired methods. Ecol Inform. 2020;57(101089).
19. 19. Ayan E, Erbay H, Varçın F. Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks. Comput Electron Agric. 2020;179(105809).
20. 20. Visalli F, Bonacci T, Borghese NA. Insects image classification through deep convolutional neural networks. Prog Artif Intell. 2021:217-228.
21. 21. Kasinathan T, Singaraju D, Uyyala SR. Insect classification and detection in field crops using modern machine learning techniques. Inf Process Agric. 2021;8(3):446-457.
22. 22. Zheng T, Yang X, Lv J, Li M, Wang S, Li W. An efficient mobile model for insect image classification in the field pest management. IJEST. 2023;39(101335).
23. 23. GBIF.org. What is GBIF? [Internet]. Copenhage (DK); 2022 [reviewed 2023 Jan 05; cited 2023 Jan 20]. Available from: https:// www.gbif.org/what-is-gbif
24. 24. GBIF.org. Aelia images. Copenhage (DK); 2023 [reviewed 2023 Jan 10; cited 2023 Jan 10]. Available from: https://doi.org/10.15468/ dl.x52gxq
25. 25. GBIF.org. Anisoplia images. Copenhage (DK); 2023 [reviewed 2023 Jan 08; cited 2023 Jan 08]. Available from: https://doi.org/10.15468/ dl.3k29je
26. 26. GBIF.org. Eurygaster images. Copenhage (DK); 2023 [reviewed 2023 Jan 08; cited 2023 Jan 08]. Available from: https://doi. org/10.15468/dl.7sz7cp
27. 27. GBIF.org, Pachytychius images. Copenhage (DK); 2023 [reviewed 2023 Jan 08; cited 2023 Jan 08]. Available from: https://doi. org/10.15468/dl.fh8q57
28. 28. GBIF.org. Zabrus images. Copenhage (DK); 2023 [reviewed 2023 Jan 05; cited 2023 Jan 05]. Available from: https://doi.org/10.15468/ dl.tpq3zy
29. 29. Moreno-Barea FJ, Jerez JM, Franco L. Improving classification accuracy using data augmentation on small data sets. Expert Syst Appl. 2020;161(113696).
30. 30. Tian X, Ding CH, Chen S, Luo B, Wang X. Regularization graph convolutional networks with data augmentation. Neurocomputing. 2021;436:92-102.
31. 31. Oyelade ON, Ezugwu AE. A deep learning model using data augmentation for detection of architectural distortion in whole and patches of images. Biomed Signal.2021;65(102366).
32. 32. Mohanty SP, Hughes DP, Salathé M. Using deep learning for imagebased plant disease detection. Front Plant Sci. 2016;7(1419).
33. 33. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Commun. 2017;60(6):84-90.
34. 34. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016; Las Vegas, NV, USA.
35. 35. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 2818-2826.
36. 36. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 1-9.
37. 37. Sultana F, Sufian A, Dutta P. Advancements in image classification using convolutional neural network. In 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN). 2018 Nov. p. 122-129.