Précédent|Prochain

Transferring deep convolutional neural network models for generalization mapping of autumn crops

  • role： First author第一作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

  • Email：201821051194@mail.bnu.edu.cn
  • Introduction：张凤，研究方向为农业遥感。E-mail： 201821051194@mail.bnu.edu.cn
ZHANG Feng123,  
  • role： Corresponding author通信作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Academy of Plateau Science and Sustainability, Qinghai Normal University, Xining 810016, China

  • Email：zhangjs@bnu.edu.cn
  • Introduction：张锦水，研究方向为农业遥感。E-mail： zhangjs@bnu.edu.cn
ZHANG Jinshui1234*,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

DUAN Yaming123,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China

    Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

    Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

YANG Zhi123

résumé

Deep Convolutional Neural Networks (DCNNs) have been increasingly applied in remote sensing crop recognition due to their “end-to-end” advantages and efficient extraction of shallow shape details and deep semantic features. However, deep learning models require a large number of labeled samples, which are time-consuming, labor-intensive, and costly to obtain, limiting the 2016—2020 period. The U-net model based on CDL training can be popularized and applied in the United States. First, the overall accuracy of time generalization in the three test areas in the United States from 2016 to 2020 is more than 80%, and the recognition accuracy of corn is higher than that of soybeans. Deep learning models have good transferability in space. Second, for autumn grain in Heihe City, the average recognition accuracy of corn for many years is 3% higher than that of soybean. This is because the corn planting plot is more regular and the planting scale is higher than that of soybean; the overall accuracy of autumn grain identification in a single year is between 69% and 79%. The year classification model is better than the single-year classification model, which may be because the representativeness of the training samples is enhanced with the increase of the number of labeled samples, and the difference in autumn grain planting between China and the United States can be compensated by the expansion of the number of samples. However, the model is migrated to the Heihe region of China. The accuracy of the models is lower than that of the continental United States, which is due to the inconsistency of remote sensing response characteristics due to differences in intercontinental climate and crop planting habits. These, in turn, reduce the generalization performance of the model. The DCNN model is better than random forest algorithm because of the training process driven by big data. The principle of transferring the basic trained crop classification model to map crop distribution timely and accurately has broad prospects for application across a large scale of time and space. The consistency of remote sensing features and phenology of the crops of the test area compared to the training data are fundamental factors that must be carefully considered, as these determine the success of high crop mapping performance. Therefore, it is essential to analyze the prerequisites when transferring the model to other places.

mots-clés

remote sensing;transfer learning;CDL;time-space generalization;soybeans;maize

References

  1. 1.
    Cai Y P, Guan K Y, Peng J, Wang S W, Seifert C, Wardlow B and Li Z. 2018. A high-performance and in-season classification system of field-level crop types using time-series Landsat data and a machine learning approach. Remote Sensing of Environment, 210: 35-47
  2. 2.
    Egli D B. 2008. Comparison of corn and soybean yields in the United States: historical trends and future prospects. Agronomy Journal, 100(S3): S-79-S-88
  3. 3.
    Hu Q, Wu W B, Song Q, Yu Y, Yang P and Tang H J. 2015. Recent progresses in research of crop patterns mapping by using remote sensing. Scientia Agricultura Sinica, 48(10): 1900-1914
  4. 4.
    Ji S L, Li J F, Du T Y and Li B. 2019. Survey on techniques, applications and security of machine learning interpretability. Journal of Computer Research and Development, 56(10): 2071-2096
  5. 5.
    Jiang T, Liu X N and Wu L. 2018. Method for mapping rice fields in complex landscape areas based on pre-trained convolutional neural network from HJ-1 A/B data. ISPRS International Journal of Geo-Information, 7(11): 418
  6. 6.
    Konduri V S, Kumar J, Hargrove W W, Hoffman F M and Ganguly A R. 2020. Mapping crops within the growing season across the United States. Remote Sensing of Environment, 251: 112048
  7. 7.
    Liu J, Wang L M, Yang F G, Yao B M and Yang L B. 2018. Recognition ability of red edge and short wave infrared spectrum on maize and soybean. Chinese Agricultural Science Bulletin, 34(35): 120-129
  8. 8.
    Ma L, Xu X G, Jia J H, Huang W J, Liu L Y and Cheng Y P. 2008. Crop classification method using multi-temporal TM images. Transactions of the Chinese Society of Agricultural Engineering, 24(S2): 191-195
  9. 9.
    Muhammad S, Niu Z, Wang L, Aablikim A, Hao P Y and Wang C Y. 2015b. Crop classification based on time series MODIS EVI and ground observation for three adjoining years in Xinjiang. Spectroscopy and Spectral Analysis, 35(5): 1345-1350
  10. 10.
    Pan Z K, Xu J S, Guo Y B, Hu Y M and Wang G X. 2020. Deep learning segmentation and classification for urban village using a worldview satellite image based on U-Net. Remote Sensing, 12(10): 1574
  11. 11.
    Phalke A R, Özdoğan M, Thenkabail P S, Erickson T, Gorelick N, Yadav K and Congalton R G. 2020. Mapping croplands of europe, middle east, russia, and central asia using landsat, random forest, and google earth engine. ISPRS Journal of Photogrammetry Remote Sensing, 167: 104-122
  12. 12.
    Ronneberger O, Fischer P and Brox T. 2015. U-net: convolutional networks for biomedical image segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer: 234-241 DOI: ]
  13. 13.
    Smith A, Sterba-Boatwright B and Mott J. 2010. Novel application of a statistical technique, Random Forests, in a bacterial source tracking study. Water Research, 44(14): 4067-4076
  14. 14.
    Song D J. 2019. Method Research on Extracting Spatial Distribution Information of Winter Wheat using Convolutional Neural Network. Taian: Shandong Agricultural University
  15. 15.
    Sun Z H, Di L P, Fang H and Burgess A. 2020. Deep learning classification for crop types in north dakota. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 2200-2213
  16. 16.
    Wang S, Azzari G and Lobell D B. 2019. Crop type mapping without field-level labels: random forest transfer and unsupervised clustering techniques. Remote Sensing of Environment, 222: 303-317
  17. 17.
    Wei S S, Zhang H, Wang C, Wang Y Y and Xu L. 2019. Multi-temporal SAR data large-scale crop mapping based on U-Net model. Remote Sensing, 11(1): 68
  18. 18.
    Xie D F, Zhang J S, Pan Y Z, Wun P J and Yuan Z M Q. 2015. Fusion of MODIS and Landsat 8 images to generate high spatial-temporal resolution data for mapping autumn crop distribution. National Remote Sensing Bulletin, 19(5): 791-805
  19. 19.
    Xu J F, Zhu Y, Zhong R H, Lin Z X, Xu J L, Jiang H, Huang J F, Li H F and Lin T. 2020. DeepCropMapping: a multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping. Remote Sensing of Environment, 247: 111946
  20. 20.
    Xu Q, Li Q L, De Vroey M, Zhang W P and Fan J L. 2019. Multi-crop synchronization identification based on random forest. Shandong Agricultural Sciences, 51(3): 135-139
  21. 21.
    Xu Q, Zhang J S, Zhang F, Gai S, Yang Z and Duan Y M. 2022. Applicability of weak samples to deep learning crop classification. National Remote Sensing Bulletin, 26(7): 1395-1409
  22. 22.
    Yang C H, Everitt J H and Murden D. 2011. Evaluating high resolution SPOT 5 satellite imagery for crop identification. Computers and Electronics in Agriculture, 75(2): 347-354
  23. 23.
    You N S and Dong J W. 2020. Examining earliest identifiable timing of crops using all available Sentinel 1/2 imagery and Google Earth Engine. ISPRS Journal of Photogrammetry and Remote Sensing, 161: 109-123
  24. 24.
    Zhang X, Wu B F, Ponce-Campos G E, Zhang M, Chang S and Tian F Y. 2018. Mapping up-to-date paddy rice extent at 10 m resolution in China through the integration of optical and synthetic aperture radar images. Remote Sensing, 10(8): 1200
  25. 25.
    Zhao Y S. 2003. Principles and Methods of Remote Sensing Application Analysis. Beijing: Science Press
  26. 26.
    Zhong L H, Hu L N and Zhou H. 2019. Deep learning based multi-temporal crop classification. Remote Sensing of Environment, 221: 430-443
  27. 27.
    Zhong Y F, Hu X, Luo C, Wang X Y, Zhao J and Zhang L P. 2020. WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF. Remote Sensing of Environment, 250: 112012
  28. 28.
    Zintgraf L M, Cohen T S, Adel T and Welling M. 2017. Visualizing deep neural network decisions: prediction difference analysis. [DOI:10.48550/arXiv.1702.04595].

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website