KOREAN JOURNAL OF CROP SCIENCE (한국작물학회지)

The Korean Society of Crop Science (한국작물학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of the Lodging Area in Rice Using Deep Learning

딥러닝을 이용한 벼 도복 면적 추정

  • Ban, Ho-Young (Crop Cultivation & Physiology Research Division, National Institute of Crop Science, Rural Development Administration) ;
  • Baek, Jae-Kyeong (Crop Cultivation & Physiology Research Division, National Institute of Crop Science, Rural Development Administration) ;
  • Sang, Wan-Gyu (Crop Cultivation & Physiology Research Division, National Institute of Crop Science, Rural Development Administration) ;
  • Kim, Jun-Hwan (Crop Cultivation & Physiology Research Division, National Institute of Crop Science, Rural Development Administration) ;
  • Seo, Myung-Chul (Crop Cultivation & Physiology Research Division, National Institute of Crop Science, Rural Development Administration)
  • 반호영 (농촌진흥청 국립식량과학원) ;
  • 백재경 (농촌진흥청 국립식량과학원) ;
  • 상완규 (농촌진흥청 국립식량과학원) ;
  • 김준환 (농촌진흥청 국립식량과학원) ;
  • 서명철 (농촌진흥청 국립식량과학원)
  • Received : 2021.03.16
  • Accepted : 2021.05.01
  • Published : 2021.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Rice lodging is an annual occurrence caused by typhoons accompanied by strong winds and strong rainfall, resulting in damage relating to pre-harvest sprouting during the ripening period. Thus, rapid estimations of the area of lodged rice are necessary to enable timely responses to damage. To this end, we obtained images related to rice lodging using a drone in Gimje, Buan, and Gunsan, which were converted to 128 × 128 pixels images. A convolutional neural network (CNN) model, a deep learning model based on these images, was used to predict rice lodging, which was classified into two types (lodging and non-lodging), and the images were divided in a 8:2 ratio into a training set and a validation set. The CNN model was layered and trained using three optimizers (Adam, Rmsprop, and SGD). The area of rice lodging was evaluated for the three fields using the obtained data, with the exception of the training set and validation set. The images were combined to give composites images of the entire fields using Metashape, and these images were divided into 128 × 128 pixels. Lodging in the divided images was predicted using the trained CNN model, and the extent of lodging was calculated by multiplying the ratio of the total number of field images by the number of lodging images by the area of the entire field. The results for the training and validation sets showed that accuracy increased with a progression in learning and eventually reached a level greater than 0.919. The results obtained for each of the three fields showed high accuracy with respect to all optimizers, among which, Adam showed the highest accuracy (normalized root mean square error: 2.73%). On the basis of the findings of this study, it is anticipated that the area of lodged rice can be rapidly predicted using deep learning.

해마다, 강한 바람을 동반한 태풍 및 집중호우로 인해 벼도복이 발생하고 있으며, 이삭이 여무는 등숙기에 도복으로 인한 수발아와 관련된 피해를 발생시키고 있다. 따라서,신속한 피해 대응을 위해 신속한 벼 도복 피해 면적 산정은 필수적이다. 벼 도복과 관련된 이미지들은 도복이 발생된 김제, 부안, 군산일대에서 드론을 이용하여 수집하였고, 수집한 이미지들을 128 × 128 픽셀로 분할하였다. 벼 도복을 예측하기 위해 이미지 기반 딥 러닝 모델인 CNN을 이용하였다. 분할한 이미지들은 도복 이미지(lodging)와 정상 이미지(non-lodging) 2가지로 라벨로 분류하였고, 자료들은 학습을 위한 training-set과 검증을 위한 vali-se을 8:2의 비율로 구분하였다. CNN의 층을 간단하게 구성하여, 3개의 optimizer (Adam, Rmsprop, and SGD)로 모델을 학습하였다. 벼 도복 면적 평가는 training-set과 vali-set에 포함되지 않은 자료를 이용하였으며, 이미지들을 methshape 프로그램으로 전체 농지로 결합하여 총 3개의 농지를 평가하였다. 도복 면적 추정은 필지 전체의 이미지를 모델의 학습 입력 크기(128 × 128)로 분할하여 학습된 CNN 모델로 각각 예측한 후, 전체 분할 이미지 개수 대비 도복 이미지 개수의 비율을 전체 농지의 면적에 곱하여 산정하였다. training-set과 vali-set에 대한 학습 결과, 3개의 optimizer 모두 학습이 진행됨에 따라 정확도가 높아졌으며, 0.919 이상의 높은 정확도를 보였다. 평가를 위한 3개의 농지에 대한 결과는 모든 optimizer에서 높은 정확도를 보였으며, Adam이 가장 높은 정확도를 보였다(RMSE: 52.80 m2, NRMSE: 2.73%). 따라서 딥 러닝을 이용하여 신속하게 벼 도복 면적을 추정할 수 있을 것으로 예상된다.

Keywords

Acknowledgement

본 논문은 농촌진흥청 연구사업(과제번호: PJ01476802)의 지원에 의해 이루어진 결과로 이에 감사드립니다.

References

  1. Fukushima, K. 1980. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36 : 193-202. https://doi.org/10.1007/BF00344251
  2. Han, L., G. Yang, H. Feng, C. Zhou, H. Yang, B. Xu, Z. Li, and X. Yang. 2018. Quantitative Identification of Maize LodgingCausing Feature Factors using Unmanned Aerial Vehicle Images and a Nomogram Computation. Remote Sensing 10(10) : 1528. https://doi.org/10.3390/rs10101528.
  3. He, W., J. Y. Yang, C. F. Drury, W. N. Smith, B. B. Grant, P. He, B. Qian, W. Zhou, and G. Hoogenboom. 2018. Estimating the impacts of climate change on crop yields and N2O emissions for conventional and no-tillage in Southwestern Ontario, Canada. Agricultural Systems 159 : 187-198. http://dx.doi.org.10.1016/jagsy.2017.01.025.
  4. Im, J. M., W. Y. Kim, W. J. Byoum, and S. J. Shin. 2018. Fruit price prediction study using artificial intelligence. The Journal of the Convergence on Culture Technology 4(2) : 197-204. http://dx.doi.org/10.17703/JCCT.2018.4.2.197.
  5. Jang, H. and S. Cho. 2016. Automatic Tagging for Social images using Convolution Neural Networks. Korean Institute of Information Scientists and Engineers 43(1) : 47-53. http://dx.doi.org/10.5626/JOK.2016.43.1.47.
  6. Joo, G., C. Park, and H. Im. 2020. Performance Evaluation of Machine Learning Optimizers. Journal of Institute of Korean Electrical and Electronics Engineers 24(3) : 766-776. http://dx.doi.org/10.7471/ikeee.2020.24.3.766
  7. Khabbazan, S., P. Vermunt, S. Steele-Dunne, L. R. Arntz, C. Marinetti, D. Valk, L. Iannini, R. Molijn, K. Westerdijk, and C. Sanve. 2019. Crop monitoring Using Sentinel-1 Data: A Case Study from The Netherlands. Remote Sensing 11(16) : 1887. https://doi.org/10.3390/rs11161887
  8. Kim, S. J., J. G. Won, D. J. Ahn, and S. D. Park. 2008. Influence of Viviparous Germination on Quality and Yield in Rice. Korean Journal of Crop Science 53(S) : 15-18.
  9. Kim, Y. 2021. An Analysis of Artificial Intelligence Algorithms Applied to Rock Engineering. Tunnel and Underground Space 31(1) : 25-40. https://doi.org/10.7474/TUS.2021.31.1.025
  10. Kim, Y., G. H. Kwak, K. D. Lee, S. I. Na, C. W. Park, and N. W. Park. 2018. Performance Evaluation of machine learning and Deep Learning Algorithms in Crop Classification: Imapact of Hyper-parameters and Training Sample Size. Korean Journal of Remote Sensing 34(5) : 811-827. http://dx.doi.org/10.780/kjrs.2018.34.5.9.
  11. Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. Advances in neural information processing systems.
  12. Lee, J. G., S. Jun, Y. W. Cho, H. Lee, G. B. Kim, J. B. Seo, and N. Kim. 2017. Deep Learning in Medical Imaging: General Overview. Korean Journal of Radiology 18(4) : 570-584. https://doi.org/10.3348/kjr.2017.18.4.570.
  13. Lim, H. K., J. B. Kim, D. H. Kwon, and Y. H. Han. 2017. Comparison Analysis of TensorFlow's Optimizer Based on MNIST's CNN Model. Journal of Advanced Technology Research 2(1) : 6-14.
  14. Liu, T., R. Li, X. Zhong, M. Jiang, X. Jin, P. Zhou, S. Liu, C. Sun, and W. Guo. 2018. Estimates of rice lodging using indices from UAV visible and thermal infrared images. Agricultural and Forest Meteorology 252: 144-154. https://doi.org/10.1016/j.agrformet.2018.01.021.
  15. Miao, Z., K. M. Gaynor, J. Wang, Z. Liu, O. Muellerklein, M. S. Norouzzadeh, A. Mclntuff, R. C. K. Bowie, R. Nathan, S. X. Yu, and W. M. Getz. 2019. Insights and approaches using deep learning to classify wildlife. Scientific Reports 9 : 8137. Heetps://doi.org/10.1038/s41598-019-44565-w.
  16. Ministry of Agriculture, Food and rural Affairs (MAFRA), 2020. "The purchase of rice damaged by typhoons", Retrieved from https://www.mafra.go.kr/mafra/293/subview.do?enc=Zm5jdDF8QEB8JTJGYmJzJTJGbWFmcmElMkY2OCUyRjMyNDk5MCUyRmFydGNsVmlldy5kbyUzRmJic0NsU2VxJTNEJTI2cmdzRW5kZGVTdHIlM0QlMjZiYnNPcGVuV3JkU2VxJTNEJTI2cGFzc3dvcmQlM0QlMjZzcmNoQ29sdW1uJTNEJTI2cGFnZSUzRDElMjZyZ3NCZ25kZVN0ciUzRCUyNnJvdyUzRDEwJTI2aXNWaWV3TWluZSUzRGZhbHNlJTI2c3JjaFdyZCUzRCUyNg%3D%3D
  17. Nesbit, P. R. and C. H. Hugenholtz. 2019. Enhancing UAV-SfM 3D Model Accuracy in High-Relief Landscapes by Incorporating Oblique Images. Remote Sensing 11(3) : 239. https://doi.org/10.3390/rs11030239.
  18. Park, H. J. 2020. Trend Analysis of Korea Papers in the Fields of 'Artificial Intelligence', 'Machine Learning' and 'Deep Learning'. Journal of Korea Institute of Information, Electronics, and Communication Technology 13(4) : 283-292. http://dx.doi.org/10.17661/jkiiect.2020.13.4.283.
  19. Park, J. S. and H. D. Kim. 2009. Viviparous germination characteristics of rice varieties adaptable to central region of Korea. Korean Journal of Crop Science 54(3) : 241-248.
  20. Park, K. B. and R. K. Park. 1984. Studies on the viviparous germination of Indica × Japonica type varieties in paddy rice. Korean Journal of Crop Science 29(1) : 15-18.
  21. Robinson, T. R., N. Rosser, and R. J. Walters. 2019. The Spatial and Temporal Influence of Cloud Cover on Satellite-Based Emergency Mapping of Earthquake Disasters. Scientific Reports 9: 12455. https://doi.org/10.1038/s41598-019-49008-0.
  22. Shahbazi, M., G. Sohn, J. Theau, and P. Menard. 2015. Development and Evauation of a UAV-Photogrammetry System for Precise 3D Environmental Modeling. Sensors 15(11) : 27493-27524. https://doi.org/10.3390/s151127493.
  23. VerMilyea, M., J. M. M. Hall, S. M. Diakiw, A. Johnston, T. Nguyen, D. Perugini, A. Miller, A. Picou, A. P. Murphy, and M. Perugini. 2020. Development of an artificial intelligence based assessment model for prediction of embryo viability using static images capured by optical light microscopy during IVF. Human Reproduction 35(4) : 770-784. https://doi.org/10.1093/humrep/deaa013.
  24. Wilke, N., B. Siegmann, L. Klingbeil, A. Burkart, T. Kraska, O. Muller, A. Doorn, S. Heinemann, and U. Rascher. 2019. Quantifying Lodging Percentage and Lodging Severity Using a UAV-Based Canopy Height Model Combined with an Objective Threshold Approach. Remote Sensing 11(515) : https://doi.org/10.3390/rs11050515.
  25. Yadav, S. S. and S. M. Jadhav. 2019. Deep convolutional neural network based medical image classification for disease diagnosis. Journal of Big Data 6:113. https://doi.org/10.1186/s40537-019-0276-2.
  26. Yang, H., E. Chen, Z. Li, C. Zhao, G. Yang, S. Pignatti, R. Casa, and L. Zhao. 2015. Wheat lodging monitoring using polarimetric index from RADARSAT-2 data. International Journal of Applied Earch Observation and Geoinformation 34 : 157-166. http://dx.doi.org/10.1016/j.jag.2014.08.010.
  27. Zhou, L., Q. Li, G. Huo, and Y. Zhou. 2017. Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features. Computational Intelligence and Neuroscience. https://doi.org/10.1155.

Cited by

  1. 유·무인 항공영상을 이용한 심층학습 기반 녹피율 산정 vol.37, pp.6, 2021, https://doi.org/10.7780/kjrs.2021.37.6.1.22