Estimating Canopy Nitrogen Content of Rice Using Hyperspectral Reflectance Combined with SG-FD-CARS-ELM in Cold Region

Wang Shuwen

doi:10.11648/j.ijimse.20180304.11

Abstract

In this study, visible and near infrared hyperspectral imaging technique was used to predict canopy leaf nitrogen content (CLNC) of rice in cold region. Canopy hyperspectral images of rice were acquired at tillering, jointing and heading stage, respectively. Original spectra was extracted using ENVI5.0 software, and leaf nitrogen content was obtained by chemical analysis method. 5 pre-processing methods of savitzky-golay smoothing (SG), multiplicative scatter correction (MSC), standard normal variate (SNV), first derivative (FD) and second derivative (SD) were used to eliminate unexpected noise. After comparing the performance of PLSR models based on spectra of full wavelengths after pre-processing, SG combined with FD had the best performance for eliminating the noise interference and improving the performance of models. In order to further simplify and enhance the models, 3 variable selection methods of successive projections algorithm (SPA), uninformative variable elimination (UVE) and competitive adaptive reweighted sampling (CARS) were used to select the characteristic wavelengths, and partial least square regression (PLSR) and extreme learning machine (ELM) were used to establish prediction models. After comparing the performance of PLSR models and ELM models, CARS could effectively select the wavelengths that had strong information and were not sensitive to external disturbance factors, and the nonlinear ELM model was more suitable for predicting CLNC of rice in cold region, the specific values of RC2 and RP2 of ELM models based on CARS were 0.906 and 0.888 for tillering stage, 0.903 and 0.892 for jointing stage, and 0.894, 0.887 for heading stage, respectively. The results of this study could provide a reference for quantitative analysis of nitrogen content of rice using hyperspectral technology.

Highlights

Nitrogen is one of the essential nutrients for rice growth and the most active factor in soil fertility [1, 2]
This study was conducted to evaluate the feasibility of using visible and near infrared hyperspectral imaging technology combined with multiple spectral pro-processing methods, different characteristic wavelength selection methods, linear and nonlinear models for the rapid and non-destructive prediction of canopy leaf nitrogen content (CLNC) of rice in cold region
competitive adaptive reweighted sampling (CARS) could effectively select the characteristic wavelengths that had strong information and were not sensitive to external disturbance factors, and the nonlinear extreme learning machine (ELM) model was more suitable for predicting CLNC of rice in cold region

Summary

Introduction

Nitrogen is one of the essential nutrients for rice growth and the most active factor in soil fertility [1, 2]. If nitrogen application is excessive, it will lead to reduced nitrogen utilization efficiency, soil degradation, decreased rice yield and inferior grain quality, and may even cause ecological pollution. It is very meaningful to realize the rapid diagnosis of nitrogen status of rice in order to rationally and accurately apply nitrogen fertilizer. Traditional nitrogen diagnostic methods are visual diagnosis, chemistry diagnosis and chlorophyll meter diagnosis. The chlorophyll meter diagnosis can only quantitatively estimate nutritional content of specified leaf, which is difficult to reflect nutritional status of large areas of cropland [3,4,5]. Traditional diagnosis methods have been difficult to meet the actual demand of large scale rice production in time and space hyperspectral technology has the advantages of convenience, accuracy and environmentally friendly, and has

Methods

Results

Conclusion