Soil organic carbon (SOC) plays an important role in the global carbon cycle and soil fertility supply. Rapid and accurate estimation of SOC content could provide critical information for crop production, soil management and soil carbon pool regulation. Many researchers have confirmed the feasibility and great potential of visible and near-infrared (Vis-NIR) spectroscopy in evaluating SOC content rapidly and accurately. Here, to evaluate the feasibility of different spectral bands variable selection methods for SOC prediction, we collected a total of 330 surface soil samples from the cotton field in the Alar Reclamation area in the southern part of Xinjiang, which is located in the arid region of northwest China. Then, we estimated the SOC content using laboratory Vis-NIR spectral. The Particle Swarm optimization (PSO), Competitive adaptive reweighted sampling (CARS) and Ant colony optimization (ACO) were adopted to select SOC feature bands. The partial least squares regression (PLSR), random forest (RF) and convolutional neural network (CNN) inversion models were constructed by using full-bands (400–2400 nm) spectra (R) and feature bands, respectively. And we also analyzed the effects of spectral feature band selection methods and modeling methods on the prediction accuracy of SOC. The results indicated that: (1) There are significant differences in the feature bands selected using different methods. The feature bands selected methods substantially reduced the spectral variable dimensionality and model complexity. The models built by the feature bands selected by CARS, PSO and ACO methods showed the different potential of improvement in model accuracy compared with the full-band models. (2) The CNN model had the best performance for predicting SOC. The R² of the optimal CNN model is 0.90 in the validation, which was improved by 0.05 and 0.04 in comparison with the PLSR and RF model, respectively. (3) The highest prediction accuracy was archived by the CNN model using the feature bands selected by CARS (validation set R² = 0.90, RMSE = 0.97 g kg⁻¹, RPD = 3.18, RPIQ = 3.11). This study indicated that using the CARS method to select spectral feature bands, combined with the CNN modeling method can well predict SOC content with higher accuracy.

In order to improve the precision of the variable-rate fertilization system in orchards, this paper conducted a simulation by MATLAB and experimental research based on a variable-rate fertilization experiment platform. The variable-rate fertilization experimental platform was mainly composed of a power supply, DC motors, a PPC-15A1 on-board computer that contains a PCI8932 PC-DAQ, speed sensors, fertilizer dischargers, and a NAV60 module that can receive Beidou Navigation Satellite System positioning data. According to the fertilizer application mechanism of an external grooved wheel fertilizer applicator, the control system model of the variable-rate fertilization driven by the DC motor for orchards was established. A BP neural network adaptive PID controller based on particle swarm optimization (PSO) was proposed to improve the control precision of the system. The step response simulation results by MATLAB show that the overshoot of the BP-PID controller optimized by the PSO algorithm (PSO-BP-PID) is 12.7%, and the adjustment time is 0.557 s. The variable-rate fertilization experiments were conducted, in which the control system was tested by using the PSO-BP-PID controller. The variable fertilizer seeder control system of the Chinese national standard was adopted to evaluate the performance indexes of the system, such as the range of fertilizer amount adjustment, the response time of fertilizer amount adjustment, and the control precision of fertilizer amount. In the variable rate fertilization experiments, the average fertilization errors, respectively, are 1.16% and 1.07%, under the conditions of changing the target fertilization amount and the vehicle speed. The test results are consistent with the simulation results, and the variable-rate fertilization performance parameters are improved.