Compared with the chemical analytical technique, the soil nitrogen acquisition method based on near infrared (NIR) sensors shows significant advantages, being rapid, nondestructive, and convenient. Providing an accurate grasp of different soil types, sensitive wavebands could enhance the nitrogen estimation efficiency to a large extent. In this paper, loess, calcium soil, black soil, and red soil were used as experimental samples. The prediction models between soil nitrogen and NIR spectral reflectance were established based on three chemometric methods, that is, partial least squares (PLS), backward interval partial least squares (BIPLS), and back propagation neural network (BPNN). In addition, the sensitive wavebands of four kinds of soils were selected by competitive adaptive reweighted sampling (CARS) and BIPLS. The predictive ability was assessed by the coefficient of determination R² and the root mean square error (RMSE). As a result, loess ( 0.93 < R p 2 < 0.95 , 0.066 g / kg < RMSE p < 0.075 g / kg ) and calcium soil ( 0.95 < R p 2 < 0.96 , 0.080 g / kg < RMSE p < 0.102 g / kg ) achieved a high prediction accuracy regardless of which algorithm was used, while black soil ( 0.79 < R p 2 < 0.86 , 0.232 g / kg < RMSE p < 0.325 g / kg ) obtained a relatively lower prediction accuracy caused by the interference of high humus content and strong absorption. The prediction accuracy of red soil ( 0.86 < R p 2 < 0.87 , 0.231 g / kg < RMSE p < 0.236 g / kg ) was similar to black soil, partly due to the high content of iron-aluminum oxide. Compared with PLS and BPNN, BIPLS performed well in removing noise and enhancing the prediction effect. In addition, the determined sensitive wavebands were 1152 nm-1162 nm and 1296 nm-1309 nm (loess), 1036 nm-1055 nm and 1129 nm-1156 nm (calcium soil), 1055 nm, 1281 nm, 1414 nm-1428 nm and 1472 nm-1493 nm (black soil), 1250 nm, 1480 nm and 1680 nm (red soil). It is of great value to investigate the differences among the NIR spectral characteristics of different soil types and determine sensitive wavebands for the more efficient and portable NIR sensors in practical application.
Keywords: BIPLS; BPNN; CARS; NIR sensors; PLS; sensitive wavebands; soil nitrogen.