Abstract
Soil nitrogen content is one of the important growth nutrient parameters of crops. It is a prerequisite for scientific fertilization to accurately grasp soil nutrient information in precision agriculture. The information about nutrients such as nitrogen in the soil can be obtained quickly by using a near-infrared sensor. The data can be analyzed in the detection process, which is nondestructive and non-polluting. In order to investigate the effect of soil pretreatment on nitrogen content by near infrared sensor, 16 nitrogen concentrations were mixed with soil and the soil samples were divided into three groups with different pretreatment. The first group of soil samples with strict pretreatment were dried, ground, sieved and pressed. The second group of soil samples were dried and ground. The third group of soil samples were simply dried. Three linear different modeling methods are used to analyze the spectrum, including partial least squares (PLS), uninformative variable elimination (UVE), competitive adaptive reweighted algorithm (CARS). The model of nonlinear partial least squares which supports vector machine (LS-SVM) is also used to analyze the soil reflectance spectrum. The results show that the soil samples with strict pretreatment have the best accuracy in predicting nitrogen content by near-infrared sensor, and the pretreatment method is suitable for practical application.
Highlights
The soil, whose main role is to provide nutrients in the process of plant growth [1,2], is the foundation and an important part of agriculture
Modeling methods on a visible near-infrared sensor, and found that the BPNN method was superior to the partial least squares (PLS) modeling method in detecting soil organic nitrogen [7]
The results showed that the method had obvious advantages in the prediction of soil nitrogen content [14]
Summary
The soil, whose main role is to provide nutrients in the process of plant growth [1,2], is the foundation and an important part of agriculture. It is very important to obtain the soil nitrogen content information quickly and reasonably for proper fertilization and agricultural production [3]. Near-infrared sensors applied to the detection of soil nitrogen can quickly obtain information such as nitrogen nutrient levels in the soil and realize data analysis and the detection process is non-destructive and pollution-free [5,6]. Mouazen et al compared the PLS and BPNN modeling methods on a visible near-infrared sensor, and found that the BPNN method was superior to the PLS modeling method in detecting soil organic nitrogen [7]. Shi used a multiple linear regression method to estimate organic nitrogen content
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
