Please wait a minute...
Journal of Integrative Agriculture  2023, Vol. 22 Issue (7): 2173-2187    DOI: 10.1016/j.jia.2022.12.003
Plant Protection Advanced Online Publication | Current Issue | Archive | Adv Search |
Accurate recognition of the reproductive development status and prediction of oviposition fecundity in Spodoptera frugiperda (Lepidoptera: Noctuidae) based on computer vision

LÜ Chun-yang1, 2, GE Shi-shuai2, 3, HE Wei2, 3, ZHANG Hao-wen1, 2, YANG Xian-ming2, CHU Bo2, 4, WU Kong-ming2#

1 State Key Laboratory of Agricultural Information Service Technology, Ministry of Agriculture and Rural Affairs, Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, P.R.China
2 State Key Laboratory for Biology of Plant Diseases and Insect Pests, Institute of Plant Protection, Chinese Academy of Agricultural Sciences, Beijing 100193, P.R.China
3 State Key Laboratory of Ecological Pest Control for Fujian and Taiwan Crops, Institute of Applied Ecology, Fujian Agriculture and Forestry University, Fuzhou 350002, P.R.China
4 College of Plant Protection, Henan Agricultural University, Zhengzhou 450002, P.R.China
Download:  PDF in ScienceDirect  
Export:  BibTeX | EndNote (RIS)      
摘要  

草地贪夜蛾(鳞翅目:夜蛾科)是世界范围内重要的迁飞性农业害虫,自2016年以来入侵非亚洲多个国家,目前对世界粮食安全构成严重威胁。当前,草地贪夜蛾的监测和预警策略主要集中在成虫种群密度,缺乏准确预测成虫繁殖动态的信息技术平台。于是在本研究中,为了识别成虫的发育状况,我们首先利用雌性卵巢图像提取和筛选出五个特征并结合支持向量机(SVM)分类器,以及利用雄性精巢图像获取精巢的圆形特征,对成虫发育时间进行判定。然后,利用实验室测试建立了产卵动态与成虫生殖器官发育时间之间关系的模型。结果表明,雌性卵巢发育等级判断的准确率达到91%,卵巢发育时间实际值与预测值的均方误差(MSE)为0.2431,日产卵量实际值与预测值的平均误差率为12.38%。精巢直径识别误差3.25%,雄性精巢发育时间预测值和实际值的均方误差为0.7734。综合上述研究成果,开发了草地贪夜蛾生殖发育状态识别及繁殖预测微信小程序,现已开放给植保人员使用。本研究开发了一种自动化方法,可以精准预测草地贪夜蛾种群繁殖动态,有助于建设种群监测预和警系统,供专业专家和当地群众使用。



Abstract  

Spodoptera frugiperda (Lepidoptera: Noctuidae) is an important migratory agricultural pest worldwide, which has invaded many countries in the Old World since 2016 and now poses a serious threat to world food security. The present monitoring and early warning strategies for the fall army worm (FAW) mainly focus on adult population density, but lack an information technology platform for precisely forecasting the reproductive dynamics of the adults. In this study, to identify the developmental status of the adults, we first utilized female ovarian images to extract and screen five features combined with the support vector machine (SVM) classifier and employed male testes images to obtain the testis circular features. Then, we established models for the relationship between oviposition dynamics and the developmental time of adult reproductive organs using laboratory tests. The results show that the accuracy of female ovary development stage determination reached 91%. The mean standard error (MSE) between the actual and predicted values of the ovarian developmental time was 0.2431, and the mean error rate between the actual and predicted values of the daily oviposition quantity was 12.38%. The error rate for the recognition of testis diameter was 3.25%, and the predicted and actual values of the testis developmental time in males had an MSE of 0.7734. A WeChat applet for identifying the reproductive developmental state and predicting reproduction of S. frugiperda was developed by integrating the above research results, and it is now available for use by anyone involved in plant protection. This study developed an automated method for accurately forecasting the reproductive dynamics of S. frugiperda populations, which can be helpful for the construction of a population monitoring and early warning system for use by both professional experts and local people at the county level.

Keywords:  Spodoptera frugiperda       computer vision        ovary        testis        WeChat applet  
Received: 29 July 2022   Accepted: 28 October 2022
Fund: This research was supported by the National Natural Science Foundation of China (31727901), the National Key R&D Program of China (2021YFD1400702) and the Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences.
About author:  LÜ Chun-yang, Mobile: +86-13718651161, E-mail: lcy8511@163.com; #Correspondence WU Kong-ming, E-mail: wukongming@caas.cn

Cite this article: 

LÜ Chun-yang, GE Shi-shuai, HE Wei, ZHANG Hao-wen, YANG Xian-ming, CHU Bo, WU Kong-ming. 2023. Accurate recognition of the reproductive development status and prediction of oviposition fecundity in Spodoptera frugiperda (Lepidoptera: Noctuidae) based on computer vision. Journal of Integrative Agriculture, 22(7): 2173-2187.

Bochkovskiy A, Wang C Y, Liao H Y M. 2020. YOLOv4: Optimal speed and accuracy of object detection. arXiv, doi: arxiv.org/abs/2004.10934.

Chen Q H, Zeng J, Zeng W, Li Q, Chen X J, Zhou Y. 2017. Application of the morphological indicators of the male internal reproductive system in forecasting the population dynamics of the rice leaf roller, Cnaphalocrocis medinalis (Lepidoptera: Pyralidae) by sex pheromone trapping. Acta Entomologica Sinica60, 927–935. (in Chinese)

Day R, Abrahams P, Bateman M, Beale T, Clottey V, Cock M, Witt A, Colmenarez Y, Corniani N, Early R, Godwin J, Gomez J, Moreno P G, Murphy S T, Oppong-Mensah B, Phiri N, Pratt C, Silvestri S, Witt A. 2017. Fall armyworm: Impacts and implications for Africa. Outlooks on Pest Management28, 196–201.

Dong Q J, Zhou J C, Zhu K H, Zhang Z T, Dong H. 2019. A simple method for identifying sexuality of Spodoptera frugiperda (J.E. Smith) pupae and adults. Plant Protection, 45, 96–98, 105. (in Chinese)

DPPMAM (Department of Plant Protection, Ministry of Agriculture, Myanmar). 2019. First detection report of the fall armyworm Spodoptera frugiperda (Lepidoptra: Noctuidae) on maize in Myanmar. [2019-01-14]. https://reliefweb.int/report/myanmar/first-detection-report-fall-armyworm-spodoptera-frugiperda-lepidoptra-noctuidae-maize

Duda R O, Hart P E. 1972. Use of the hough transformation to detect lines and curves in pictures. Communications of the ACM15, 11–15.

Early R, González-Moreno P, Murphy S T, Day R. 2018. Forecasting the global extent of invasion of the cereal pest Spodoptera frugiperda, the fall armyworm. NeoBiota40, 25–50.

FAO (Food and Agriculture Organization). 2018. First detection of fall army worm on the border of Thailand. [2018-12-19]. https://reliefweb.int/report/thailand/first-detection-fall-army-worm-border-thailand

Feng L, Tang S S, Liu F, Dai C G, Xing J C, Li H B. 2022. Toxicity and control efficacy of seven bio-insecticides against Spodoptera frugiperda and Mythimna separata larvae. Journal of Environmental Entomology44, 35–43. (in Chinese)

Gao Y. 2017. Maize pest identification based on SVM and DS image data fusion. MSc thesis, Anhui Agricultural University, China. (in Chinese)

Ge S S, He W, He, L M, Yan R, Zhang H W, Wu K M. 2021. Flight activity promotes reproductive processes in the fall armyworm, Spodoptera frugiperdaJournal of Integrative Agriculture20, 727–735.

Goergen G, Kumar P L, Sankung S B, Togola A, Tamò M. 2016. First report of outbreaks of the fall armyworm Spodoptera frugiperda (JE Smith) (Lepidoptera, Noctuidae), a new alien invasive pest in West and Central Africa. PLoS ONE11, e0165632.

Hansen O L P, Svenning J C, Olsen K, Dupont S, Garner B H, Iosifidis A, Price B W, Høye T T. 2020. Species-level image classification with convolutional neural network enables insect identification from habitus images. Ecology and Evolution10, 737–747.

Haralick R M, Shanmugam K, Dinstein I H. 1973. Textural features for image classification. IEEE Transactions on SystemsManand Cybernetics3, 610–621.

He L M, Ge S S, Zhang H W, He W, Yan R, Wu K M. 2021. Photoregime affects development, reproduction, and flight performance of the invasive fall armyworm (Lepidoptera: Noctuidae) in China. Environmental Entomology50, 367–381.

He W, Zhao S Y, Ge S S, Jiang Y Y, Zhao X C, Wu K M. 2019. Population prediction method using sexual trapping for Spodoptera frugiperdaPlant Protection45, 48–53, 115. (in Chinese)

He W, Zhao X C, Ali A, Ge S S, Zhang H W, He L M, Wu K M. 2021a. Population dynamics and reproductive developmental analysis of Helicoverpa armigera (Lepidoptera: Noctuidae) trapped using food attractants in the field. Journal of Economic Entomology114, 1533–1541.

He W, Zhao X C, Ge S S, Wu K M. 2021b. Food attractants for field population monitoring of Spodoptera exigua (Hübner). Crop Protection145, 105616.

Hu X, Liu Y, Zhao Z, Liu J, Yang X, Sun C, Chen S H, Li B, Zhou C. 2021. Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network. Computers and Electronics in Agriculture185, 106135.

Jiang X F, Zhang L, Cheng Y X, Song L L. 2019. Advances in migration and monitoring techniques of the fall armyworm, Spodoptera frugiperda (J. E. Smith). Plant Protection45, 12–18. (in Chinese)

Jiang Y Y, Liu J, Xie M C, Li Y H, Yang J J, Zhang M L, Qiu K. 2019. Observation on law of diffusion damage of Spodoptera frugiperda in China in 2019. Plant Protection45, 10–19. (in Chinese)

Jiang Y Y, Liu J, Yang J J, Zhao W X, Yi L, Liu Y, Ye S F, Qin B Q, Song L D. 2020. Trapping effect of searchlight-trap and light trap for the moth of Spodoptera frugiperda in 2019. Plant Protection46, 118–122, 156. (in Chinese)

Liang G M, Tan W J, Guo Y Y. 1999. Improvement of artificial raising of cotton bollworm. Plant Protection25, 3. (in Chinese)

Lin X Z, Zhang J Y, Zhu S H, Liu D Y. 2019. Sparse representation classification method of rice planthopper image based on K-SVD and orthogonal matching pursuit algorithm. Transactions of the Chinese Society of Agricultural Engineering35, 216–222. (in Chinese)

Liu J, Jiang Y Y, Liu W C, Li Y H, Zeng J, Yang Q B. 2019. Investigation and forecast techniques of Spodoptera frugiperdaChina Plant Protection39, 44–47. (in Chinese)

Maktabdar Oghaz M, Maarof M A, Rohani M F, Zainal A, Shaid S Z M. 2019. An optimized skin texture model using gray-level co-occurrence matrix. Neural Computing and Applications31, 1835–1853.

Mohammadi S, Mohammadi M, Dehlaghi V, Ahmadi A. 2019. Automatic segmentation, detection, and diagnosis of abdominal aortic aneurysm (AAA) using convolutional neural networks and hough circles algorithm. Cardiovascular Engineering and Technology10, 490–499.

Montezano D G, Specht A, Sosa-Gómez D R, Roque-Specht V F, Sousa-Silva J C, Paula-Moraes S V, Peterson J A, Hunt T E. 2018. Host plants of Spodoptera frugiperda (Lepidoptera: Noctuidae) in the Americas. African Entomology26, 286–300.

Nagoshi R N, Fleischer S, Meagher R L. 2009. Texas is the overwintering source of fall armyworm in Central Pennsylvania: implications for migration into the northeastern United States. Environmental Entomology38, 1546–1554.

Nagoshi R N, Murúa M G, Hay-Roe M, Juárez M L, Willink E, Meagher R L. 2012. Genetic characterization of fall armyworm (Lepidoptera: Noctuidae) host strains in Argentina. Journal of Economic Entomology105, 418–428.

Nakweya G. 2018. Global actions needed to combat fall armyworm. [2018-09-28]. https://www.scidev.net/sub-saharan-africa/news/global-actions-combat-fall-armyworm/

Otsu N. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on SystemsManand Cybernetics9, 62–66.

Redmon J, Divvala S, Girshick R, Farhadi A. 2016. You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vsion and Pattern Recognition (CVPR). IEEE Computer Society, USA. pp. 779–788.

Schaefer S, Yuksel C. 2007. Example-based skeleton extraction. In: Eurographics Symposium on Geometry Processing (2007). Eurographics Association and Wiley, Austria. pp. 153–162.

Sethy A, Patra P K, Nayak D R. 2019. Gray-level co-occurrence matrix and random forest based off-line Odia handwritten character recognition. Recent Patents on Engineering13, 136–141.

Shylesha A N, Jalali S K, Gupta A, Varshney R, Venkatesan T, Shetty P, Ojha R, C.Ganiger P, Navik O, Subaharan K, Bakthavatsalam N, Ballal C R. 2018. Studies on new invasive pest Spodoptera frugiperda (JE Smith) (Lepidoptera: Noctuidae) and its natural enemies. Journal of Biological Control32, 145–151.

Sisay B, Simiyu J, Malusi P, Likhayo P, Mendesil E, Elibariki N, Wakgari M, Ayalew G, Tefera T. 2018. First report of the fall armyworm, Spodoptera frugiperda (Lepidoptera: Noctuidae), natural enemies from Africa. Journal of Applied Entomology142, 800–804.

Sparks A N, Jackson R D, Carpenter J E, Muller R A. 1986. Insects captured in light traps in the Gulf of Mexico. Annals of the Entomological Society of America79, 132–139.

Stricker M A, Orengo M. 1995. Similarity of color images. In: Proceeding of Storage and Retrieval for Image and Video Databases III. The International Society for Optical Engine, California, America. pp. 381–392.

Sun X X, Hu C X, Jia H R, Wu Q L, Shen X J, Zhao S Y, Jiang Y Y, Wu K M. 2021. Case study on the first immigration of fall armyworm, Spodoptera frugiperda invading into China. Journal of Integrative Agriculture20, 664–672.

Tamez-Guerra P, Tamayo-Mejía F, Gomez-Flores R, Rodríguez-Padilla C, Damas G, Tamez-Guerra R. S, Ek-Ramos M, Williams T. 2017. Increased efficacy and extended shelf life of spinosad formulated in phagostimulant granules against Spodoptera frugiperdaPest Management Science74, 100–110.

Wang H X, Li Y F, Dang L M, Moon H. 2022. An efficient attention module for instance segmentation network in pest monitoring. Computers and Electronics in Agriculture195, 106853.

Wu K M. 2020. Management strategies of fall armyworm (Spodoptera frugiperda) in China. Plant Protection46, 1–5. (in Chinese)

Wu K S, Otoo E, Suzuki K. 2009. Optimizing two-pass connected-component labeling algorithms. Pattern Analysis and Applications12, 117–135.

Yang B H, Gao Z W, Gao Y, Zhu Y. 2021. Rapid detection and counting of wheat ears in the field using YOLOv4 with attention module. Agronomy11, 1202.

Yang X M, Zhao S Y, Jiang Y Y, Wu K M. 2020. Population occurrence and sampling technique of fall armyworm Spodoptera frugiperda in barley field. Plant Protection46, 18–23. (in Chinese)

Zhang W N, Xiao H J, Liang G M, Guo Y Y. 2013. Observation on ovarian morphology and oogenesis in the cotton bollworm, Helicoverpa armigera (Lepidoptera: Noctuidae). Acta Entomologica Sinica56, 358–364.

Zhang X G. 2000. Introduction to statistical learning theory and support vector machines. Acta Automatica Sinica26, 36–46. (in Chinese)

Zhao S Y, Yang X M, He W, Zhang H W, Jiang Y Y, Wu K M. 2019a. Ovarian development gradation and reproduction potential prediction in Spodoptera frugiperdaPlant Protection45, 28–34. (in Chinese)

Zhao S Y, Yang X M, Yang X L, Song Y F, Wu K M. 2019b. Field efficacy of eight insecticides on fall armyworm, Spodoptera frugiperdaPlant Protection45, 74–78. (in Chinese)

Zhu L Q, Ma M Y, Zhang Z, Zhang P Y, Wu W, Wang D D, Zhang D X, Wang X, Wang H Y. 2017. Hybrid deep learning for automated lepidopteran insect image classification. Oriental Insects51, 79–91.

No related articles found!
No Suggested Reading articles found!