Results in Chemistry (Dec 2023)

Study on the rapid measurement of carbon content in marine sediments based on the model transfer of hyperspectral imaging camera and spectrometer

  • Wang Zijian,
  • Jia Zongchao,
  • Li Xueying,
  • Qiu Huimin,
  • Hou Guangli,
  • Fan Pingping

Journal volume & issue
Vol. 6
p. 101086

Abstract

Read online

Laboratory spectrometer and hyperspectral imaging camera are two instruments for obtaining spectral information of substances. Both instruments have advantages in practical applications. In this paper, a total of 164 sediment samples were collected from two locations in the marine intertidal zone of Qingdao Aoshan Bay. The total carbon content (TC) concentration in marine sediments was obtained by chemical method. The spectral data of sediments were obtained by the spectrometer and the hyperspectral data were obtained by a hyperspectral imaging camera. With a spectrometer as the main instrument and a hyperspectral imaging camera as the slave instrument, the rapid measurement of carbon content in marine sediments was realized through the model transfer. Two model transfer algorithms were used: piecewise direct standardization, deviation model updating, and slope/bias correction method (PDS-DMP-S/B), and piecewise direct standardization, model updating, and slope/bias correction method (PDS-MP-S/B). Different modeling results were obtained by changing the proportion of the calibration set and test set and adding preprocessing. Compared with the single model transfer algorithm, PDS-MP-S/B and PDS-DMP-S/B were more effective. Standard normal variable transform (SNV) preprocessing had little effect on the modeling results in the model transfer between the spectrometer and hyperspectral imaging camera. After the data normalization of spectral data, all models were improved. When the ratio of the calibration set to the test set was 3:1, the PDS-DMP-S/B algorithm was used for the model transfer, the RP2 value of the modeling result was 0.693, the RMSEP value was 2.332, and the RPD value was 1.615, which achieved a relatively ideal modeling result. This study provides a new and fast method for predicting the carbon content in marine sediments.

Keywords