Estimation Model Based on Spectral-Reflectance Data

  • Tao ChiEmail author
  • Guangpu Cao
  • Bingchun Li
  • Zi Kerr Abdurahman
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 69)


A new estimation model based on BPNN is proposed in the thesis to recognize the characteristics of the spectral-reflectance data rapidly and estimate soil salt content accurately. Take the case of USGS Digital Spectral Library to estimate salt content of different soils, BP neural network model has been optimized, improved and realized in MATLAB. In this experiment, the prediction accuracy of multiple BPNN model reaches 83%, which is superior to traditional BP neural network model and multi-factor orthogonal regression analysis, indicating that the multiple BPNN model is suitable for the complex regression analysis of nonlinear spectral data and the high-precision estimation model of soil salt content. This method could also be used in embedded system, and design real-time testing equipment of soil salt content.


Big spectral data Digital spectral library BP neural network Soil salt content estimation 



This work is partly supported by the national natural science fund (61561027) and the shanghai natural science fund (16ZR1415100). Thanks to Key Laboratory of Fisheries Information Ministry of Agriculture.


  1. 1.
    Yi, S., Yaqin, L.: The characteristics of soil spectra and the correlation of the spectral reflectance with the salt content of soda salt-affected-soils. J. Jilin Agric. Sci. 1992(1), 53–56Google Scholar
  2. 2.
    Yongling, W., Haoping, Q.: PLSR-based hyperspectral remote sensing retrieval of soil salinity of Chaka-gonghe Basin in Qinghai Province. Acta Pedol. Sin. 47(6), 1255–1263 (2010)Google Scholar
  3. 3.
    Fanguo, M., Chunling, H.: Research on salinity inversion from remote sensing of saline soil based on BP neural network. Geogr. Geo-Inf. Sci. 26(6), 24–27 (2010)Google Scholar
  4. 4.
    Satir, O., Berberoglu, S.: Crop yield prediction under soil salinity using satellite derived vegetation indices. Field Crops Res. 192, 134–143 (2016)CrossRefGoogle Scholar
  5. 5.
    Dong, T., Zhang, Z., Zuo, L.: Quantitative research on soil erosion based on BP artificial neural network. 6790, 67901E–67901E-7 (2007)Google Scholar
  6. 6.
    Narendua, K.S., Mukhopadhyay, S.: Adoptive control using neural networks and approximate models. IEEE Trans. Neural Netw. 8(3), 475–485 (1997)CrossRefGoogle Scholar
  7. 7.
    Annaswamy, A.M., Yu, S.H.: Adaptive neural networks: a new approach to parameter estimation. IEEE Trans. Neural Networks 7(4), 907–918 (1996)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Tao Chi
    • 1
    • 2
    Email author
  • Guangpu Cao
    • 1
  • Bingchun Li
    • 3
  • Zi Kerr Abdurahman
    • 3
  1. 1.College of Information TechnologyShanghai Ocean UniversityShanghaiChina
  2. 2.Key Laboratory of Fisheries InformationMinistry of AgricultureShanghaiChina
  3. 3.School of Computer Science and TechnologyKashgar UniversityXinjiangChina

Personalised recommendations