关键词: 南方水稻土, 机载高光谱, 土壤有机质, 特征光谱, 建模精度

Abstract: Organic matter spectra in paddy soils are often influenced by soil background such as water and straw. In order to weaken and remove the influence of nonorganic matter components, an estimation model of organic matter in paddy soils in southern China was constructed. In this paper, Airborne Hyperspectral (GaiaSkyMini2VN) was used as data source to extract onedimensional characteristic spectra by single and combined transformation of the original reflectance (continuum removal, inverse, logarithmic, firstorder differential, secondorder differential single transformation and inverse firstorder differential, logarithmic firstorder differential, reciprocal logarithmic combined transformation); twodimensional characteristic spectra were extracted by ratio and normalization processing of the transformed spectra; linear (multiple linear regression, partial least squares) and nonlinear(back propagation neural network and support vector machine) organic matter prediction models based on characteristic spectra were constructed to monitor the organic matter of paddy soils in Southern China. The results showed that onedimensional spectral transformation could significantly enhanced the sensitivity of spectral response to organic matter. Twodimensional spectral transformation fully mined spectral information, enhanced the intrinsic relationship between organic matter and spectrum, and improved the modeling accuracy. Nonlinear models (BPNN, SVM), especially BPNN, had good fit for soil organic matter and high modeling accuracy. The BPNN model based on the original reflectance ratio indexhad the best modeling effect, with modeling accuracy of 0952 and testing accuracy of 0889. Above results were applicable to the monitoring of organic quality of paddy soils in southern China. It could provide important reference in feature band extraction and modeling method selection of soil organic monitoring by airborne hyperspectral spectroscopy and put forward new ideas for the management of modern agricultural development.

Key words: paddy soil in southern China, airborne hyperspectral, soil organic matter, characteristic spectrum, modeling accuracy