The best hyperspectral estimation model of soil total nitrogen (TN) was established, which provided the basis for rapid and accurate estimation of soil total nitrogen content, scientific and rational fertilization and...The best hyperspectral estimation model of soil total nitrogen (TN) was established, which provided the basis for rapid and accurate estimation of soil total nitrogen content, scientific and rational fertilization and soil informatization management. A total of 92 brown soil samples were collected from the orchard of Qixia County, Yantai City, Shandong Province. After drying and grinding, the hyperspectrum of the soil was measured in the laboratory using ASD FieldSpec3. The TN contents of brown soil were measured by Kjeldahl method. The sensitive wavelengths were selected by multiple linear stepwise regression method. The hyperspectral estimation model of TN was established by Random Forest (RF) and Support Vector Machines (SVM). The models were validated by independent samples. The best estimation model was obtained. The sensitive wavelengths were 956 nm, 995 nm, 1020 nm, 1410 nm, 1659 nm and 2020 nm. The coefficients of determination (R2) of the two estimation models were 0.8011 and 0.8283, the root mean square errors (RMSE) were 0.022 and 0.025, and relative errors (RE) were 0.1422 and 0.1639, respectively. Random Forest model and Support Vector Machines model are feasible in estimating TN contents, but the Support Vector Machines model is better.展开更多
The spectral characteristic of geography objects is not only the important content of remote sensing mechanism, but also the important basis for remote sensing application. The reflectance spectral characteristics ref...The spectral characteristic of geography objects is not only the important content of remote sensing mechanism, but also the important basis for remote sensing application. The reflectance spectral characteristics reflect the physiochemi-cal properties of saline soil. With 3 kinds of typical saline soils in the arid area as the study objects, the reflectance spectrums of soils with different salt contents and soil moistures were measured, and the spectral characteristics of the spectrums were analyzed. The results showed that under dry condition, the reflectance of the three kinds of saline soils presented obvious high-low patterns, while under damp condition, there was no obvious pattern. With continuum removed ,the three kinds of saline soils showed significant difference in reflectance spectral characteristics. There was significant difference in the absorption depth of the two absorption val eys un-der dry and damp conditions, which could be used to identify these 3 saline soils. The result of this research can be used for the parametric inversion and classifica-tion of saline soil retrieval and classification, as wel as for the remote sensing monitoring on saline soil.展开更多
文摘The best hyperspectral estimation model of soil total nitrogen (TN) was established, which provided the basis for rapid and accurate estimation of soil total nitrogen content, scientific and rational fertilization and soil informatization management. A total of 92 brown soil samples were collected from the orchard of Qixia County, Yantai City, Shandong Province. After drying and grinding, the hyperspectrum of the soil was measured in the laboratory using ASD FieldSpec3. The TN contents of brown soil were measured by Kjeldahl method. The sensitive wavelengths were selected by multiple linear stepwise regression method. The hyperspectral estimation model of TN was established by Random Forest (RF) and Support Vector Machines (SVM). The models were validated by independent samples. The best estimation model was obtained. The sensitive wavelengths were 956 nm, 995 nm, 1020 nm, 1410 nm, 1659 nm and 2020 nm. The coefficients of determination (R2) of the two estimation models were 0.8011 and 0.8283, the root mean square errors (RMSE) were 0.022 and 0.025, and relative errors (RE) were 0.1422 and 0.1639, respectively. Random Forest model and Support Vector Machines model are feasible in estimating TN contents, but the Support Vector Machines model is better.
基金Supported by the Fund for the Prophase Financial Aid Project of Xinjiang Agricultural University(XJAU201114)~~
文摘The spectral characteristic of geography objects is not only the important content of remote sensing mechanism, but also the important basis for remote sensing application. The reflectance spectral characteristics reflect the physiochemi-cal properties of saline soil. With 3 kinds of typical saline soils in the arid area as the study objects, the reflectance spectrums of soils with different salt contents and soil moistures were measured, and the spectral characteristics of the spectrums were analyzed. The results showed that under dry condition, the reflectance of the three kinds of saline soils presented obvious high-low patterns, while under damp condition, there was no obvious pattern. With continuum removed ,the three kinds of saline soils showed significant difference in reflectance spectral characteristics. There was significant difference in the absorption depth of the two absorption val eys un-der dry and damp conditions, which could be used to identify these 3 saline soils. The result of this research can be used for the parametric inversion and classifica-tion of saline soil retrieval and classification, as wel as for the remote sensing monitoring on saline soil.
