Description
Ground hyperspectral images of sericite–Artemisia desert grassland in different seasons were obtained by a soc710 VP imaging spectrometer. Analysis of variance was used to extract the main species Seriphidium transiliense, Ceratocarpus arenarius, and Petrosimonia sibirica and the spectral characteristic parameters and vegetation indices of bare land in different seasons. On this basis, Fisher discriminant analysis was used to divide the samples into a training set and test set according to a ratio of 7:3. The spectral characteristic parameters and vegetation indices were used to identify the three main plants and bare land. Results showed that under Fisher discriminant analysis, whether using the spectral characteristic parameters or vegetation indices, the identification model established by the vegetation indices had the best discrimination accuracy for the test set samples of S. transiliense, C. arenarius, P. sibirica and bare land. Although the total discrimination accuracy of the test set samples exceeded 80% in different seasons, the identification model established by the vegetation indices had the best discrimination, reaching 100.00%, 95.60%, 100.00% and 95.90%, respectively, and a total accuracy of 98.89%.
Included in
Agricultural Science Commons, Agronomy and Crop Sciences Commons, Plant Biology Commons, Plant Pathology Commons, Soil Science Commons, Weed Science Commons
Identification of Hyperspectral Characteristics of The Main Plants in Seriphidium transiliense Desert Grassland
Ground hyperspectral images of sericite–Artemisia desert grassland in different seasons were obtained by a soc710 VP imaging spectrometer. Analysis of variance was used to extract the main species Seriphidium transiliense, Ceratocarpus arenarius, and Petrosimonia sibirica and the spectral characteristic parameters and vegetation indices of bare land in different seasons. On this basis, Fisher discriminant analysis was used to divide the samples into a training set and test set according to a ratio of 7:3. The spectral characteristic parameters and vegetation indices were used to identify the three main plants and bare land. Results showed that under Fisher discriminant analysis, whether using the spectral characteristic parameters or vegetation indices, the identification model established by the vegetation indices had the best discrimination accuracy for the test set samples of S. transiliense, C. arenarius, P. sibirica and bare land. Although the total discrimination accuracy of the test set samples exceeded 80% in different seasons, the identification model established by the vegetation indices had the best discrimination, reaching 100.00%, 95.60%, 100.00% and 95.90%, respectively, and a total accuracy of 98.89%.
