Anterior|Siguiente

Crop recognition and evaluationusing red edge features of GF-6 satellite

  • role： First author第一作者
  • Affiliation：

    National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology in the Hunan University of Science and Technology, Xiangtan 411201, China

    Key Laboratory of Land Surface Process and Climate Change in Cold and Arid Regions, Chinese Academy of Sciences, Lanzhou 730000, China

    School of Resource & Environment and Safety Engineering in the Hunan University of Science and Technology, Xiangtan 411201, China

  • Email：leung@lzb.ac.cn
  • Introduction：梁继，1976生，女，副教授，研究方向为冰冻圈遥感、辐射传输理论与数值计算模型。E-mail：leung@lzb.ac.cn
LIANG Ji123,  
  • Affiliation：

    National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology in the Hunan University of Science and Technology, Xiangtan 411201, China

    School of Resource & Environment and Safety Engineering in the Hunan University of Science and Technology, Xiangtan 411201, China

ZHENG Zhenwei13,  
  • Affiliation：

    National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology in the Hunan University of Science and Technology, Xiangtan 411201, China

    School of Resource & Environment and Safety Engineering in the Hunan University of Science and Technology, Xiangtan 411201, China

XIA Shiting13,  
  • Affiliation：

    National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology in the Hunan University of Science and Technology, Xiangtan 411201, China

    School of Resource & Environment and Safety Engineering in the Hunan University of Science and Technology, Xiangtan 411201, China

ZHANG Xiaotong13,  
  • Affiliation：

    National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology in the Hunan University of Science and Technology, Xiangtan 411201, China

    School of Resource & Environment and Safety Engineering in the Hunan University of Science and Technology, Xiangtan 411201, China

TANG Yuanyuan13

resumen

The application of red edge features, which are sensitive bands of vegetation, is a high-technology method for remote sensing to identify crops and realize precision agriculture. Multispectral GF-6 image of the study area in the northern region of Songnen Plain in Heilongjiang Province pioneers the use red edge bands in China. A total of 82859 crop samples of corn, soybean, and rice were used as research objects. The classification accuracy of crops was evaluated and the performance of red edge features in crop identification, such as red edge bands and vegetation index, was discussed from the following aspects. (1) Statistical characteristics of radiance values of crop samples initially showed that discrimination is better at Band 5-0.710 μm and Band 6-0.750 μm in the two red edge bands than findings of other GF-6 bands. (2) Traditional normalized (NDVI) and red-edge normalized difference vegetation indexes, namely, NDVI710 and NDVI750, are constructed. Results showed that the two indexes are more significant than the traditional NDVI in the classification of crop samples characterized using J-M distance. (3) Effective bands are screened using various methods, and classification strategies for the four types of crops are formulated using Support Vector Machine (SVM). Crop classification in the study area is completed using five sets of random sample segmentation schemes, namely, 5∶5, 6∶4, 7∶3, 8∶2, and 9∶1. Twenty types of classification accuracy demonstrated a kappa coefficient higher than 0.9609 and overall accuracy higher than 0.9742. The 5∶5 and 8∶2 segmentation schemes in the column direction exhibited the highest and lowest accuracy, respectively. The sorting accuracy in the horizontal direction demonstrated the following order: SVM-RFE > SVM-RF > SVM with red edge bands > SVM without red edge band, which also showed that the participation of red edge vegetation index and red edge band significantly improves the recognition precision of crops. (4) SVM-RFE and SVM-RF both obtained minimal misclassifications due to the lack of other samples, such as waters. However, SVM-RFE is superior to SVM-RF in terms of classification accuracy and image detail display with a kappa coefficient and overall accuracy of 0.8060 and 0.8743, respectively, in the cross-validation of two classified images. Hence, the red edge feature of GF-6 is superior in crop recognition with its significantly improved recognition accuracy. Subsequent investigations can focus on developing additional red edge-related vegetation indexes and optimize the role of red edge characteristics in precision agriculture.

palabra clave

remote sensing;GF-6 satellite;the red-edge band;Support Vector Machine (SVM);Random Forest method (RF);Recursive Feature Elimination method (RFE)

References

  1. 1.
    Bödinger C J. 2018. Remote Sensing of Vegetation: Along a Latitudinal Gradient in Chile. Wiesbaden: Springer: 123
  2. 2.
    Danson F M and Plummer S E. 1995. Red-edge response to forest leaf area index. International Journal of Remote Sensing, 16(1): 183-188
  3. 3.
    Deng S B, Chen Q J, Du H J and Xu E H. 2014. Remote Sensing Image Processing Method Using ENVI. 2nd ed. Beijing: Higher Education Press: 474
  4. 4.
    ENVI-IDL Technology Hall. 2019. Atmospheric correction method for WFV data of Gaofen-6 Satellite in ENVI[EB/OL]. (2019-07-12)[2019-08-06].
  5. 5.
    ESA. 2008. RapidEye[EB/OL]. [2019-08-06].
  6. 6.
    ESA. 2015. Sentinel-2[EB/OL]. [2019-08-06].
  7. 7.
    Filella I and Penuelas J. 1994. The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status. International Journal of Remote Sensing, 15(7): 1459-1470
  8. 8.
    Foster A J, Kakani V G, Ge J J, Gregory M and Mosali J. 2016. Discriminant analysis of nitrogen treatments in switchgrass and high biomass sorghum using leaf and canopy-scale reflectance spectroscopy. International Journal of Remote Sensing, 37(10): 2252-2279
  9. 9.
    Fu H and Xu G S. 2014. the research of combined feature selection based on random forest and RFE//Proceedings of the 19th National Youth Communication Academic Conference. Shanghai: China Institute of Communications: 200-204
  10. 10.
    Géron A, 2017. Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques for Building Intelligent Systems. Beijing: O'Reilly Media: 450
  11. 11.
    Huang B, Wu B, Liu B and Cao K. 2008. Spatial intelligence: advancement of geographic information science. Journal of Remote Sensing, 12(5): 766-771
  12. 12.
    Huang S Y, Yang L, Chen X and Yao Y. 2018. Study of typical arid crops classification based on machine learning. Spectroscopy and Spectral Analysis, 38(10): 3169-3176
  13. 13.
    Jiang J B, Chen Y H and Huang W J. 2010. Using the distance between hyperspectral red edge position and yellow edge position to identify wheat yellow rust disease. Spectroscopy and Spectral Analysis, 38(10): 1614-1618
  14. 14.
    Lamb D W, Steyn-Ross M, Schaare P, Hanna M M, Silvester W and Steyn-Ross A. 2002. Estimating leaf nitrogen concentration in ryegrass (Lolium spp.) pasture using the chlorophyll red-edge: theoretical modelling and experimental observations. International Journal of Remote Sensing, 23(18): 3619-3648
  15. 15.
    Li X C. 2018. Starting with Lasso[EB/OL]. (2018-10-22)[2019-08-06].
  16. 16.
    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
  17. 17.
    Liu L Y, Wang J H, Huang W J, Zhao C J, Zhang B and Tong Q X. 2004. Estimating winter wheat plant water content using red edge parameters. International Journal of Remote Sensing, 25(17): 3331-3342
  18. 18.
    Luo G. 2018. Perceiving the Earth - Questions and Answers on Satellite Remote Sensing Knowledge. Beijing: China Aerospace Publishing House:381
  19. 19.
    Milton N M, Eiswerth B A and Ager C M. 1991. Effect of phosphorus deficiency on spectral reflectance and morphology of soybean plants. Remote Sensing of Environment, 36(2): 121-127
  20. 20.
    Mutanga O and Kumar L. 2007. Estimating and mapping grass phosphorus concentration in an African savanna using hyperspectral image data. International Journal of Remote Sensing, 28(21): 4897-4911
  21. 21.
    Reichstein M, Camps-Valls G, Stevens B, Jung M, Denzler J, Carvalhais N and Prabhat. 2019. Deep learning and process understanding for data-driven Earth system science. Nature, 566(7743): 195-204
  22. 22.
    Satellite Imaging Corporation. 2017. WorldView-3 satellite sensor[EB/OL]. [2019-08-06].
  23. 23.
    Strobl C, Boulesteix A L, Kneib T, Augustin T and Zeileis A. 2008. Conditional variable importance for random forests. BMC Bioinformatics, 9(1): 307
  24. 24.
    Thenkabail P S, Lyon J G and Huete A. 2019. Hyperspectral Remote Sensing of Vegetation, Volume II: Hyperspectral Indices and Image Classifications for Agriculture and Vegetation. 2nd ed. Boca Raton, FL: CRC Press, Taylor & Francis Group: 333
  25. 25.
    Tian Z K, Fu Y Y and Liu S H. 2019. Remote sensing image classification based on heterogeneous machine learning algorithm fusion. Computer Science, 46(5): 235-240
  26. 26.
    Wang Y Y, Chen Y H, Li J and Huang W J. 2007. Two new red edge indices as indicators for stripe rust disease severity of winter wheat. Journal of Remote Sensing, 11(6): 875-881
  27. 27.
    Wu J Y, Yang X D, Zhang F J, Ni J, Tian W X and Xie L Y. 1997. Seasonal characteristics of spectral reflectance of Korean pine leaves in the gold mine area of Zhaoyuan City in Shandong province. Journal of Remote Sensing, 1(2): 124-128
  28. 28.
    Wu Y F, Hu X, Lü G H, Ren D C, Jiang W G and Song J Q. 2014. Comparison of red edge parameters of winter wheat canopy under late frost stress. Spectroscopy and Spectral Analysis, 38(10): 2190-2195
  29. 29.
    Wuyundeji, Yu L F, Bao J W, Xu H T and Wulantuya. 2017. Impact of red-edge waveband of RapidEye satellite on recognition ability of main crop. Journal of Northern Agriculture, 45(6): 118-123
  30. 30.
    Xie Q Y. 2017. Research on Leaf Area Index Retrieve Methods Based on the Red Edge Bands from Multi-Platform Remote Sensing Data. Beijing:
  31. 31.
    Yuan M Y. 2018. the Elements of Machine Learning: Principles Algorithms and Practices. Beijing: Tsinghua University Press: 304 (袁梅宇. 2018. 机器学习基础—原理、算法与实践. 北京: 清华大学出版社: 304)
  32. 32.
    Zhao C J, Wang Z J, Wang J H and Huang W J. 2012. Relationships of leaf nitrogen concentration and canopy nitrogen density with spectral features parameters and narrow-band spectral indices calculated from field winter wheat (Triticum aestivum L.) spectra. International Journal of Remote Sensing, 33(11): 3472-3491
  33. 33.
    Zhao D L, Li J H and Song Z J. 2003. Hyperspectral remote sensing for estimating biochemical variables of canopy. Advance in Earth Sciences, 18(1): 94-99
  34. 34.
    Zhao Y S. 2013. Principle and Method of Remote Sensing Application Analysis. 2nd ed. Beijing: Science Press: 502
  35. 35.
    Zheng L J. 2017. Crop Classification Using Multi-features of Chinese Gaofen-1/6 Satellite Remote Sensing Images.
  36. 36.
    Zheng Y, Wu B F and Zhang M. 2017. Estimating the above ground biomass of winter wheat using the Sentinel-2 data. Journal of Remote Sensing, 21(2): 318-328
  37. 37.
    Zhou X, Wang Y B, Liu S H, Yu P X and Wang X K. 2018. A machine learning algorithm for automatic identification of cultivated land in remote sensing images. Remote sensing for Land and Resources, 30(4): 68-73
  38. 38.
    Zhou Z H. 2016. Machine Learning. Beijing: Tsinghua University Press: 425
  39. 39.
    Zhu Y Q, Qu Y H, Liu S H and Chen S B. 2014. Spectral response of wheat and lettuce to copper pollution. Journal of Remote Sensing, 18(2): 335-352

Leer el texto completo

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