Spectral Diagnostic Model for Agricultural Robot System Based on Binary Wavelet Algorithm.

Weibin Wu,Ting Tang,Chongyang Han,Ying Zhang,Jie Li,Yuanjiao Feng,Xiaoyi Wang,Ting Gao,Jianwu Wang

doi:10.3390/s22051822

Abstract

The application of agricultural robots can liberate labor. The improvement of robot sensing systems is the premise of making it work. At present, more research is being conducted on weeding and harvesting systems of field robot, but less research is being conducted on crop disease and insect pest perception, nutritional element diagnosis and precision fertilizer spraying systems. In this study, the effects of the nitrogen application rate on the absorption and accumulation of nitrogen, phosphorus and potassium in sweet maize were determined. Firstly, linear, parabolic, exponential and logarithmic diagnostic models of nitrogen, phosphorus and potassium contents were constructed by spectral characteristic variables. Secondly, the partial least squares regression and neural network nonlinear diagnosis model of nitrogen, phosphorus and potassium contents were constructed by the high-frequency wavelet sensitivity coefficient of binary wavelet decomposition. The results show that the neural network nonlinear diagnosis model of nitrogen, phosphorus and potassium content based on the high-frequency wavelet sensitivity coefficient of binary wavelet decomposition is better. The R2, MRE and NRMSE of nn of nitrogen, phosphorus and potassium were 0.974, 1.65% and 0.0198; 0.969, 9.02% and 0.1041; and 0.821, 2.16% and 0.0301, respectively. The model can provide growth monitoring for sweet corn and a perception model for the nutrient element perception system of an agricultural robot, while making preliminary preparations for the realization of intelligent and accurate field fertilization.

Highlights

With the rapid development of robot technology, it has been increasingly applied in the agricultural field [1]
The results showed that an appropriate increase in the nitrogen application rate could promote the absorption and accumulation of nitrogen in maize leaves, while a high nitrogen application rate inhibited the accumulation of nitrogen in maize leaves, which significantly decreased the nitrogen accumulation rate and reduced the utilization rate of nitrogen fertilizer
The R2, Mean Relative Error (MRE) and Normalized Root Mean Square Error (NRMSE) of the neural network nonlinear model are increased by 44.94%, 69.39% and 78.70%, respectively, and their comprehensive performance is improved by 28.14%

Summary

Introduction

With the rapid development of robot technology, it has been increasingly applied in the agricultural field [1]. The weeding and harvesting function systems of field robots have been the most studied, while there is little research on crop disease and insect pest perception, nutrient element content diagnosis and precision fertilizer spraying function systems [10–12]. The diagnosis of the nutrient elements content can provide a basis for field robots to perceive the crop growth status. Hyperspectral imaging technology is a simple, rapid and non-destructive method for the detection of crop nutrient elements. This method has become an important means to obtain field information in the field of digital agriculture and has been widely used in the detection of nutrient information of crops such as corn, wheat, tea and so on [19–23]. Through spectral technology, researchers have used stepwise regression, principal component analysis, support vector basis, random forest algorithm, continuous wavelet transform and other methods to estimate the crop chlorophyll content, nutrient element content, water content and other indicators quickly and in a nondestructive manner [24–31]

Methods

Results

Conclusion