Improve the Prediction Accuracy of Apple Tree Canopy Nitrogen Content through Multiple Scattering Correction Using Spectroscopy

Method: Use Multiple Scattering Correction to eliminate the interference of scattering on spectrum in the process of field measurement so as to improve the accuracy of prediction model of tree canopy nitrogen content. Apple trees in Qixia of Yantai City were taken as the test material. The spectral reflectivity of apple tree canopy went through the First Derivative (FD) and Multiple Scattering Correction (MSC) plus first derivative, respectively. The correlation coefficients were calculated between spectral reflectivity and nitrogen content. The Support Vector Machine (SVM) method was used to establish the prediction model. The result indicates that the MSC pre-processing can improve the correlation between spectral reflectivity and nitrogen content. The SVM model with MSC + FD pre-processing was a good way to predict the nitrogen content. The calibration R2 of the model was 0.746;the validation R2 was 0.720;and its RMSE was 0.452 g·kgˉ1. MSC can commendably eliminate scattering error to improve the prediction accuracy of prediction model.

Characteristics and Spatial Variability of Saline-Alkaline Soil Degradation in the Typical Yellow River Delta Area of Kenli County, China

As an important area of reserve land resources, the Yellow River Delta is faced with the problem of soil salinization. Grasping the characteristics of soil salinity as well as its spatial variation patterns is an important foundation of prevention, control and utilization of saline soil. This study selected Kenli County of the Yellow River Delta, obtained soil salinity data through field survey and lab experiment, and used statistical, GIS interpolation and buffer analysis methods to analyze the characteristics of soil salinity and its spatial variation patterns. Our results showed that the general soil salinity in the study area was mainly moderate and there was a significant positive correlation between different soil layers of 0 - 15 cm, 15 - 30 cm and 30 - 45 cm and soil salinity increased with the increase of soil depth. The areas with high soil salinity in each soil layer mainly distributed in the east near the Bo Sea in the county, while the areas with lower soil salinity mainly distributed in the southwest, centre and the two sides of the Yellow River in the northeast. Soil salinity showed a trend of decrease with the increase in distance to the Bo Sea, while stretching from the Yellow River, it showed increase tendency with the increase in distance to the Yellow River. The order from high soil salinity to low of different vegetation types was naked land → suaeda glauca → tamarix → vervain → reed → couch grass → paddy → cotton → winter wheat → maize;the order for different geomorphic types was depression → slightly sloping ground → slow hillock → high flood land. This study preliminary delineated the characteristics of soil salinity as well as its spatial variation patterns in the study area, and provided scientific basis for soil resource sustainable utilization in the Yellow River Delta.

Monitoring Soil Nitrate Nitrogen Based on Hyperspectral Data in the Apple Orchards

This paper is aimed to monitor the soil nitrate nitrogen content in the apple orchards rapidly, accurately and in real time by making full use of the effective information of soil spectra. The 96 air-dried soil samples of the apple orchards in Qixia county, Yantai city, Shandong province were used as the data source. Spectral measurements of soil samples were carried out by ASD Fieldspec 3 in the darkroom, and the content of the soil nitrate nitrogen was determined by chemical method. Then the hyperspectral reflectance of soil samples were preprocessed by Multivariate Scatter Correction (MSC) and First Derivative (FD), the correlation analysis was carried out with the soil nitrate nitrogen content. The sensitive wavelength of soil nitrate nitrogen was screened. Finally, the Support Vector Machine (SVM) model for the soil nitrate nitrogen content was established. The results showed that the selected sensitive wavelength were 617 nm, 760 nm, 1239 nm, 1442 nm, 1535 nm, 1695 nm, 1776 nm, 1907 nm and 2088 nm. Hyperspectral monitoring model was established by SVM, in which the prediction set R2 was 0.959, RMSE was 0.281, RPD was 3.835;the correction set R2 was 0.822, RMSE was 0.392, RPD was 2.037. The SVM model could be used to monitor the soil nitrate content accurately.

Information Extraction Method of Soil Salinity in Typical Areas of the Yellow River Delta Based on Landsat Imagery

In order to get RS method to extract soil salinity of the Yellow River Delta, we set Kenli County as typical Yellow River Delta to be research area and get data of soil salinity through field investigation. By using RS image of Landsat-8 of March 14, 2014 and analyzing information features of each band and surface spectral features of research areas, we select out sensitive bands and build Soil Salinity Information Extraction (SSIE) model and vegetation index NDVI model for comparison. And then, we accordingly classify grades of soil salinity and get soil salinity information by decision tree approach based on expert knowledge. The results show that overall accuracy of SSIE model is 93.04% and coefficient of Kappa is 0.7869, while overall accuracy of NDVI model is 83.67% and coefficient of Kappa is 0.7017 respectively. By comparing with measured proportions of each class, we see that results from SSIE model is more accurate, which indicates significant advantage for soil salinity information extraction. This research provides scientific basis to get and monitoring soil salinity of the Yellow River Delta region quickly and accurately.

Estimating Canopy Nitrogen Contents of an Apple Tree Using Hyperspectral Remote Sensing

Estimating an apple tree canopy nitrogen contents using hyperspectral techniques is important in theoretical and realistic significance for fertilization and management.Taking 80 Fuji apple trees at the early fruiting stage as the research objects,the hyperspectral characteristics of the apple canopy were analyzed systematically.The apple canopy hyperspectral and the canopy nitrogen contents were measured respectively.The canopy hyperspectral characteristics under different nitrogen contents were analyzed and selected the sensitive wave bands.The apple canopy nitrogen content monitoring models were established by using multiple regression method,robust regression and BP neural network method.The results showed that the canopy hyperspectral reflectance had obvious differences under different nitrogen contents.The sensitive bands concentrate on 724~1136 nm.Estimation models based on hyperspectral indices are not ideal.Models based on robust regression(M regression)and BP neural network are better than multiple statistical model,and the accuracy of the BP neural network monitoring model is the best.The results of the study provide a certain reference for estimating apple nutrition using hyperspectral technology.

Hyperspectral Inversion of Potassium Content in Apple Leaves Based on Vegetation Index

The aim of this study is to establish the estimation model of potassium content in apple leaves by using vegetation index. A total of 96 fresh apple leaves were collected from 24 orchards in Qixia County, Shandong Province. The spectral reflectance of the leaves was measured by ASD FieldSpec4. The difference vegetation index (DVI), ratio vegetation index (RVI) and normalized vegetation index (NDVI) were used to make the contour map through Matlab platform, and the combination of high correlation wavelength was selected to establish the random forest (RF) regression model of potassium content. The hyperspectral reflectance increased with the increase of leaf potassium content. The correlation between DVI and the content of potassium is higher than NDVI and RVI. The optimal vegetation index was DVI (364,740), the correlation coefficient was 0.5355. The random forest regression model established with DVI selected vegetation index was the best. R2 was 0.8995, RMSE and RE% were 0.0791 and 0.0617 respectively. Using DVI to establish the random forest regression model to reverse the potassium content of apple leaves has achieved good results. It is important to determine the growth status of apple in hyperspectral and to determine the potash fertilizer of apple trees.

Estimating Chlorophyll Content of Apple Leaves Based on Different Scales in Differential Window

The aims of this study are to explore the effect of different scales in the high spectral data on the estimation of chlorophyll content of apple leaves, to find out the optimal differential window scale and to establish a model for estimating the chlorophyll content of apple leaves. Taking the apple leaves as the research object, the actual spectral reflectance of the leaves was determined by the ASD Field Spec 3 spectrometer and the chlorophyll contents of the leaves were measured in the laboratory. Firstly, the differential transformations from 1 to 30 window scales were done for actual spectral data respectively, and correlation analyses were done between apple leaf chlorophyll content and differential data, then two sensitive wavelengths were chosen under each window. Secondly, taking five consecutive differential windows as a group, the best differential window was selected in each group. Lastly, after the conversion of two sensitive wavelengths in six differential windows, relationship analyses between chlorophyll content of apple leaves and two sensitive wavelengths were done, then two new parameters with the largest correlation coefficient were chosen to establish estimation model. Results showed that with increasing differential window, the determination coefficient (R2) of estimation model decreased after an initial increase, the tipping point was at the 13th differential window scale. Testing the partial least squares (PLS) model and the stepwise regression (SR) model established under differential window scale of the 13th, the R2 of the SR model was higher than that of the PLS model. The RMSE and RE% of the SR model were lower than that of the PLS model, which showed that SR model was more suitable to estimate chlorophyll content.