摘要：Soil total nitrogen is an important indicator of soil fertility. In order to achieve a general applicability of the soil total nitrogen content detector developed based on the principle of spectroscopy, this paper selects the universal nitrogen-sensitive wavelength of soil suitable for different types of soil and models optimization. Firstly, the spectral characteristic curves of black soil, cinnamon soil and tidal soil were measured, the analysis found that under the same soil total nitrogen content, the absorbance curves of different types of soils are quite different. Then, the Monte Carlo non-information variable elimination (MC-UVE) algorithm was used to screen the soil total nitrogen sensitive wavelengths of the three soil types, the common sensitive spectral regions of different soil types were screened, and the spectral wavelength ranges were 895-911 nm, 1047-1065 nm, 1211-1232 nm, 1468-1482 nm, 1691-1699 nm and 2095-2109 nm. On the basis of the selected spectrum, the continuous projection algorithm was used tooptimize the sensitive wavelength again, and the characteristic wavelengths suitable for the prediction of three soil types were 902, 1054, 1221, 1478, 1697, 1969, 2104 nm. The prediction model was established by the absorbance values of the soil total sensitive wavelength and the soil total nitrogen standard value, the highest model accuracy was obtained from the Support Vector Regression model of different soil type. The calibrationRc2of the black soil model was 0.922 and the verificationRv2of the black model was 0.892. The calibrationRc2of the cinnamon soil model was 0.905 and the verificationRv2of the cinnamon model was 0.877. The calibrationRc2of the tidal soil model was 0.892 and the verificationRv2of the tidal model was 0.873. The experimental results show that the common sensitive wavelengths of different soils can be used as a reference for the selection of light source and filter for soil total nitrogen content detector. However, the soil total nitrogen model needs to consider parameter setting for different soil types when modelling different soils to achieve universal applicability of the detector for different soil types.
关键词：KeywordsSoil total nitrogenNear-infrared spectroscopySensitive wavelengthMC-UVERadial basis neural network
