Sedimentary manganese deposits widely distribute in North Guangxi with the characteristic existing
Celosia argentea. Celosia argentea is a kind of plant which has a strong ability to enrich manganese. In
order to study the relationship between the hyperspectral characteristics of Celosia argentea and the
concentration effect of manganese in the soil, we used soil of B layer in mining area, background soil
and the soil adding reagent of MnCl4 to make up experimental sample soil with 10 levels Manganese
content for the same batch Celosia argentea. The levels are 0mg/kg, 4500mg/kg, 9000mg/kg,
13500mg/kg, 18000mg/kg, 18020mg/kg, 18040mg/kg, 18080mg/kg, 18160mg/kg. ASD FieldSpec-4
has been used to measure the abnormal spectrums of these Celosia argentea through a whole growth
cycle. After pretreating the spectral data, we used Successive Projections Algorithm (SPA) to extract
the characteristic variables for extracting 1603 bands into 8 bands. Finally, the relationship between the
spectral variables and the concentration of manganese was predicted by the Model of Partial Least
Squares Regression (PLSR). The results show that the correlation coefficient-r2 are 0.8714 and 0.9141
in two sets of data. The prediction results are satisfactory, but the front 5 groups are closer to the
regression line than the last 5 groups.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.