Development of a Mobile Bivariate Fertilizer Applicator Integrating Spectral Detection Technology
Preprint
- 23 April 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Soil fertility is critical for crop production. However, conventional uniform fertilization often causes over-application, leading to resource waste and pollution. Variable-rate fertilization (VRF) is a core precision agriculture technology for optimizing nutrient use. Nevertheless, current VRF equipment suffers from inefficient soil nutrient prediction, limited precision and low intelligence. This study develops a mobile bivariate fertilizer applicator integrating a spectral detection system, a mechanical system and a control system. The equipment breaks through the traditional fixed combination mode of motor speed and gate opening degree in conventional bivariate fertilization devices. The vehicle-mounted spectral sensor offers greater mobility and field-deployment capability than portable spectral detection devices. The self-designed mechanical structure incorporates an external groove wheel fertilizer discharger and a disc plow, enhances field efficiency and prevents optical fiber twisting. The Raspberry Pi 4B-based control system implements a three-level precision enhancement mechanism that includes experimental calibration, data screening, and polynomial regression. This process involves collecting raw data from stepwise univariate experiments, eliminating data segments with abnormal uniformity, and employing response surface methodology to establish a bivariate interaction model. An average accuracy of 98.09% and a fertilizer discharge range of 0.0430–0.2055 kg/s are maintained across the operational range of 40% to 100% for both rotational speed and opening degree. The bivariate combination algorithm overcomes traditional fixed-parameter selection mode, and the system addresses the shortcomings of existing VRF systems in terms of integration, accuracy, efficiency, and robustness.Keywords
This publication has 16 references indexed in Scilit:
- Review of the granular fertilizer mass flow rate measurement techniques for variable-rate fertilization drillsComputers and Electronics in Agriculture, 2025
- Development of a mobile online detector for soil total nitrogen based on visible and short-wave near-infrared spectroscopyMeasurement, 2025
- A robust deep learning model for predicting green tea moisture content during fixation using near-infrared spectroscopy: Integration of multi-scale feature fusion and attention mechanismsFood Research International, 2025
- A novel on-line dual sensing system for soil property measurement and mappingSmart Agricultural Technology, 2024
- Map-sensor-based site-specific manure application in wheatComputers and Electronics in Agriculture, 2024
- Within-field spatial variability and potential for profitability of variable rate applicationsPrecision Agriculture, 2023
- Map-based variable-rate manure application in wheat using a data fusion approachSoil and Tillage Research, 2021
- Determination of pin-roller parameters and evaluation of the uniformity of granular fertilizer application metering devices in precision farmingComputers and Electronics in Agriculture, 2020
- MOEA/D-DE based bivariate control sequence optimization of a variable-rate fertilizer applicatorComputers and Electronics in Agriculture, 2019
- On-the-go variable-rate phosphorus fertilisation based on a visible and near-infrared soil sensorBiosystems Engineering, 2008