Search

• Soil TN estimation accuracy using vis-NIR spectra is higher than pXRF spectra. • Feature selection & geographical stratification improve soil TN estimation accuracy. • CARS is the optimal feature selection method for multi-sensor data fusion models. • SO-PLS fusion method increases model accuracy by fully using multiple sensor data. Fast and accurate monitoring of soil total nitrogen (TN) content is particularly important to optimize agricultural inputs (e.g. fertilizers) and inhibit N loss-induced pollution. Proximal soil sensing combined with multi-sensor fusion has been considered to be a promising alternative to traditional laboratory analysis because it can achieve fast, non-destructive, environmentally friendly, and low-cost monitoring. However, the accuracy of this technique depends on the heterogeneity of the dataset and the data fusion strategy. In this study, a total of 500 soil samples were collected from two locations with high degree of soil and environment heterogeneity in Xinjiang, China, and then visible-near-infrared spectroscopy (vis-NIR), portable X-ray fluorescence (pXRF) spectroscopy and soil TN measurement were conducted in the laboratory. Based on partial least squares regression algorithm, direct concatenation, outer-product matrix analysis, and sequentially orthogonalized partial least-square (SO-PLS) were applied for multi-sensor data fusion by using full spectra or spectral features. The results showed that the estimation accuracy using vis-NIR spectral data were higher than pXRF spectral data. Compared with single sensor data and full-spectrum data fusion, the feature selection combined with data fusion contributed to a higher soil TN estimation accuracy, and the competitive adaptive reweighted sampling combined with SO-PLS fusion and geographical stratification modeling strategy had the highest soil TN estimation accuracy, with a root mean square error (RMSE) of 0.1838 g kg−1, and a Lin's concordance correlation coefficient of 0.86. It was worth noting that geographical stratification was an effective modeling strategy to improve the TN estimation accuracy based on multi-sensor data fusion, and its RMSE was 0.10 % ∼ 11.70 % lower than that of global modeling. This study highlights the potential of feature selection combined with geographic stratification to increase the soil TN estimation accuracy based on multi-sensor fusion, especially in regions with high soil and environmental heterogeneity. [ABSTRACT FROM AUTHOR]

• Blue-edge area vegetation index （BEAVI） improves the estimation ability. • Multi-angle combined vegetation index improves prediction accuracy. • Estimation models can be used for interannual testing. Rapid, non-destructive, and accurate monitoring is of great significance for determining crop nitrogen status and improving nitrogen fertilizer management. Multiple angle spectral data contains comprehensive and abundant information of crop canopy. In this study, the spectral data of cotton leaves at different leaf inclination angles (0°, 15°, 30°, and 45°) were collected using hyperspectral imaging technology at the seedling stage, bud stage, flowering stage, and boll-forming stage of cotton from 2018 to 2020, and indoor determination of cotton leaf nitrogen concentration (LNC) was conducted simultaneously. Based on the spectral features in blue edge and green edge regions, a new multi-angle blue-edge absorption vegetation index (MBEAVI) was constructed. Then, the MBEAVI and 16 vegetation indices (VI) reported in previous studies were constructed using single-angle and multi-angle spectral data of 2018 (320 sets) and 2019 (320 sets), and the inter-annual test was conducted with the data of 2020 (320 sets). The results showed that the VI models based on multi-angle spectral data (multi-angle models) had higher accuracy than the models based on single-angle spectral data (single-angle models). Among single-angle models, the model based on the optimized red edge absorption index (OREA) had the highest accuracy in cotton LNC estimation, with R2 of 0.735. However, the accuracy of multi-angle model, MBEAVI, was significantly higher than that of the OREA model, with R2 of 0.812. Besides, the R2 of the MBEAVI model reached 0.789 in the inter-annual test. Therefore, the MBEAVI model based on multi-angle spectral data had a higher accuracy and stability in predicting cotton LNC compared with the single-angle models. This study provides theoretical support for improving the accuracy of monitoring cotton nitrogen status by using multi-angle hyperspectral data. [ABSTRACT FROM AUTHOR]

• Leaf nitrogen concentration was significantly correlated with MDA and POD activities. • Band extraction by SPA reduced the collinearity and redundancy of N-sensitive bands. • Combining of LNC and OA-sensitive bands improved the model accuracy. Oxidase activities (OA) are highly correlated with the nitrogen concentration in crop leaves. To improve the universality and inter-annual repeatability of the model for estimating cotton leaf nitrogen concentration (LNC), a method for model construction was proposed based on the combination of the bands sensitive to LNC with the bands sensitive to OA. In this plot experiment, 320 and 250 sets of hyperspectral data of cotton leaves in seedling stage, bud stage, initial flowering stage, full flowering stage, and boll setting stage were collected in 2019 and 2020, respectively by using hyperspectral technology, and the LNC and OA were also measured in indoor biochemical experiments. Then, successive projection algorithm (SPA) was used to analyze the LNC and OA-sensitive bands in the original spectrum and five kinds of spectral conversions in 2019, to construct the partial least squares regression (PLSR) and principal component regression (PCR) models. Finally, the accuracy of the models were verified using the spectral data in 2020. The results showed that the selection of LNC and OA-sensitive bands could greatly reduce the collinearity and redundant information among bands. The accuracy of the models based on the LNC and OA-sensitive bands in all stages were higher than those of the models based on the LNC-sensitive bands. The optimal was the model based on the malondialdehyde (MDA), peroxidase (POD), and LNC sensitive bands in full flowering stage, with determination coefficients (R2) of 0.846, root mean squared error (RMSE) of 3.081, and residual prediction deviation (RPD) of 2.975. The universality and inter-annual repeatability of the optimal model were significantly improved, with R2 increasing by 12.24%-79.89% and RMSE reducing by 19.80%-72.52%, compared with those of the model based on the LNC-sensitive bands. Besides, the accuracy and stability of PLSR models were significantly higher than those of PCR models. In conclusion, the combination of LNC and OA-sensitive bands could obviously improve the accuracy and universality of the LNC estimation model. This study provides a new method for improving the accuracy and universality of crop nitrogen estimation model. [ABSTRACT FROM AUTHOR]