Search

Unmanned aerial vehicle (UAV) hyperspectral data can provide accurate and detailed spectral information on the surface of features, leading to a better understanding of the physiological characteristics and optical properties of objects. Compared to satellite hyperspectral, UAV hyperspectral has a greater image spatial resolution, but it also collects more impurity information along with more image detail information. The nitrogen (N) content in shallow soils is of great significance for crop growth, and most of its remote sensing inversions are currently based on satellite images, whereas relatively few studies have used hyperspectral UAV images in the near-infrared band for inversions. Based on this, we propose a high-accuracy inversion model based on UAV hyperspectral imagery using an elastic net (EN) dimensionality reduction algorithm combined with a decision tree (DT) model. In this study, a hyperspectral imager carried by a drone was used to acquire the surface soil spectral data of winter wheat in the study area after sowing and fertilizing, and the measured N content of the sampled soil was determined by chemical analysis methods. We used various pre-processing methods to denoise and reduce the dimensionality of the original hyperspectral images and utilized a DT regression model to construct an inversion model of N content with different preprocessing results. Then we compared the accuracy of the models and used the optimal model to obtain the spatial distribution map of soil N content in the study area. The results show that (1) the dimensionality reduction of hyperspectral data can effectively remove redundant information and prevent data overfitting. Among them, the successive projections algorithm and correlation analysis method are more suitable for analyzing pre-processed spectral data, whereas the Lasso and EN algorithms are more suitable for processing original spectral data. (2) For the original spectral images, the EN dimensionality reduction algorithm (R2 of the EN-Unt-DT inversion model is 0.930, RMSE is 0.045) performed better than the other three algorithms. For the pre-processed spectral images, the successive projections algorithm (R2 of the SPA-Pre-DT inversion model is 0.906, RMSE is 0.055) performed better than the other three algorithms. The constructed EN-Unt-DT inversion model had the highest fitting accuracy. The research results provide a corresponding technical reference for the inversion of soil N content using UAV NIR hyperspectral data. • The FD-SNV-SG pretreatment method was chosen based on the features of the spectral curves. • Hyperspectral data were dimensionally reduced to reduce data redundancy and avoid overfitting. • Eight inversion models were built, among which the best model was EN-Unt-DT, R2 = 0.93, RMSE = 0.045. [ABSTRACT FROM AUTHOR]

Inadequate fertilization may result in water pollution and nutrient leaching, especially in paddy fields. It is expected that the combination of organic and inorganic fertilizers reduces water pollution in addition to crop yield improvement. In this study, combined fertilization with organic and inorganic fertilizers was tested under controlled irrigation conditions. With the addition of organic fertilizer, the pH of paddy soil could be maintained in a rather neutral environment, and the soil organic matter concentration could increase - especially under a controlled irrigation regime. Hydrolyzed nitrogen was noticed in the fertilized plots with an increasing trend compared to unfertilized plots. However, available phosphorus concentration decreased in all treatments after rice harvest. During the drainage process, the ammonium nitrogen was the main form of nitrogen loss. Organic fertilizer application significantly improved productive panicles and thus increased paddy yield. We concluded that with the combination of organic-inorganic fertilizer application and controlled irrigation, the pollutants can be removed to some extent and the rice yield can be increased significantly, which is favorable for environmental protection and yield promotion. [ABSTRACT FROM AUTHOR]

Macro- and micro nutrients were managed in soil and mulberry foliage through application of urea and diammonium phosphate (DAP). Urea at the rate of 608 kg/ha and DAP at the rate of 260 kg/ha was applied on six mulberry varieties. The results showed a deficiency in nitrogen, phosphorus, zinc and manganese in soil before the fertilizer application. Contrarily, high copper and potassium contents were found. After three weeks of fertilizer application, concentration of N, P, K and Fe in the soil almost doubled. Zinc and Cu contents decreased significantly (p<0.01). The highest N, P and K were found in mulberry variety PFI-1, M. latifolia and Karyansuban, respectively. The highest Cu and Mn were found in Kanmasi. The highest Zn and Fe were found in Husang and Karyansuban, respectively. A significant variation in uptake and retention of macro- and micro nutrients was found in the mulberry varieties after fertilizer application. The highest N was taken up by Kanmasi, while the highest P and K were taken up by Husang. Iron and Cu increased, and Zn and Mn decreased after week 3 of fertilizer application. Nitrogen was 1.5 to 2.6 times greater after week 6 of fertilizer application compared to before fertilizer application. Similarly, P and K were 4.7 to 6.6 times and 2.6 to 3.9 times greater, respectively. Based on these findings, it is concluded that urea in split doses and diammonium phosphate in single dose should be applied 3-4 weeks before the commencement of rearing of Mulberry Silkworm Moth for nutritionally rich mulberry foliage. Ghulam Ali Bajwa*, Muhammad Arshad Khan [ABSTRACT FROM AUTHOR]