The nanoemulsions of soy protein isolate-phosphatidylcholine (SPI-PC) with different emulsion conditions were studied. Homogenization pressure and homogenization cycle times were varied, along with SPI and PC concentration. Evaluations included turbidity, particle size, ζ-potential, particle distribution index, and turbiscan stability index (TSI). The nanoemulsions had the best stability when SPI was at 1.5%, PC was at 0.22%, the homogenization pressure was 100 MPa and homogenization was performed 4 times. The average particle size of the SPI-PC nanoemulsions was 217 nm, the TSI was 3.02 and the emulsification yield was 93.4% of nanoemulsions.

Increasing crop yield is a significant objective in modern agriculture, with adjusted planting density and rational fertilization strategies standing out as the foremost approaches for attaining such a goal. Through the use of modern artificial intelligence techniques such as genetic algorithms and neural networks, the CPDOS (Crop Planting Density Optimization System), an online intelligent system that can automate the modeling, optimization, and analysis of the two models, was developed in the present study. The goal of the system is to optimize the planting density model and fertilizer application in combination with other computer system development techniques. The CPDOS comprises three main modules: yield density optimization module, optimal planting density range module, and fertilization and planting density optimization module. The three modules are complemented by two modules for data input and result visualization, culminating in the comprehensive process of optimizing planting density and fertilizer allocation through the CPDOS. The CPDOS was tested using potato, corn, and soybean data, and the results show that the optimization effects of planting density and fertilizer application were satisfactory. The CPDOS is an automated crop planting optimization system that integrates algorithms and models and is driven by artificial intelligence technology. The introduction of the CPDOS reduces the barriers to utilizing these algorithms and models, facilitating wider adoption of intelligently optimized planting technology. The platform’s launch will accelerate the swift advancement of this field.