The rhizosphere microbiota plays a critical and crucial role in plant health and growth, assisting plants in resisting adverse stresses, including soil salinity. Plastic film mulching is an important method to adjust soil properties and improve crop yield, especially in saline–alkali soil. However, it remains unclear whether and to what extent the association between these improvements and rhizosphere microbiota exists. Here, from a field survey and a greenhouse mesocosm experiment, we found that mulching plastic films on saline–alkali soil can promote the growth of soybeans in the field. Results of the greenhouse experiment showed that soybeans grew better in unsterilized saline–alkali soil than in sterilized saline–alkali soil under plastic film mulching. By detecting the variations in soil properties and analyzing the high-throughput sequencing data, we found that with the effect of film mulching, soil moisture content was effectively maintained, soil salinity was obviously reduced, and rhizosphere bacterial and fungal communities were significantly changed. Ulteriorly, correlation analysis methods were applied. The optimization of soil properties ameliorated the survival conditions of soil microbes and promoted the increase in relative abundance of potential beneficial microorganisms, contributing to the growth of soybeans. Furthermore, the classification of potential key rhizosphere microbial OTUs were identified. In summary, our study suggests the important influence of soil properties as drivers on the alteration of rhizosphere microbial communities and indicates the important role of rhizosphere microbiota in promoting plant performance in saline–alkali soil under plastic film mulching.

The automated collection of plant phenotypic information has become a trend in breeding and smart agriculture. Four YOLOv8-based models were used to segment mature soybean plants placed in a simple background in a laboratory environment, identify pods, distinguish the number of soybeans in each pod, and obtain soybean phenotypes. The YOLOv8-Repvit model yielded the most optimal recognition results, with an $R^2$ coefficient value of 0.96 for both pods and beans, and the RMSE values were 2.89 and 6.90, respectively. Moreover, a novel algorithm was devised to efficiently differentiate between the main stem and branches of soybean plants, called the midpoint coordinate algorithm (MCA). This was accomplished by linking the white pixels representing the stems in each column of the binary image to draw curves that represent the plant structure. The proposed method reduces computational time and spatial complexity in comparison to the A* algorithm, thereby providing an efficient and accurate approach for measuring the phenotypic characteristics of soybean plants. This research lays a technical foundation for obtaining the phenotypic data of densely overlapped and partitioned mature soybean plants under field conditions at harvest.