The measurement of plant sap flow has long been a traditional method for quantifying transpiration. However, conventional direct measurement methods are often costly and complex, thereby limiting the widespread application of tree sap flow monitoring techniques. The concept of a Virtual Measurement Instrument (VMI) has emerged in response to this challenge by combining simple instruments with Artificial Intelligence (AI) algorithms to indirectly assess specific measurement objects. This study proposes a tree sap flow estimation method based on environmental factors and AI algorithms. Through the acquisition of environmental factor data and the integration of AI algorithms, we successfully achieved indirect measurement of tree sap flow. Accounting for the time lag response of the flow to environmental factors, we constructed the Magnolia denudata sap flow estimation model using the K-Nearest Neighbor (KNN), Random Forest (RF), Backpropagation Neural Network (BPNN), and Long Short-Term Memory network (LSTM) algorithms. The research results showed that the LSTM model demonstrated greater reliability in predicting sap flow velocity, with R² of 0.957, MAE of 0.189, MSE of 0.059, and RMSE of 0.243. The validation of the target tree yielded an R² of 0.821 and an error rate of only 4.89% when applying the model. In summary, this sap flow estimation method based on environmental factors and AI provides new insights and has practical value in the field of tree sap flow monitoring.

Magnolias, renowned for their diverse botanic classification and myriad uses, are increasingly recognized not only for their aesthetic value in urban landscaping but also for their potential in pharmaceutical and cosmetic applications due to their rich bioactive metabolites. This review aims to provide a comprehensive examination of the classification, cultivation, and utility of Magnolia species, focusing on their integration into urban landscapes and the exploitation of their chemical properties in various industries. We delve into the existing literature to assess the cultivation practices, ecological advantages, and the sophisticated chemical profiling of magnolia metabolites. We consolidate the ecological contributions of magnolias in urban environments, emphasizing their role in enhancing biodiversity, air quality, and aesthetic appeal. Furthermore, we explore the therapeutic potential of magnolia-derived compounds, highlighting their effectiveness in anti-inflammatory, antioxidant, and neuroprotective applications and their incorporation into cosmetic products. The conclusion underscores the significant yet underexploited potential of magnolias, advocating for intensified research to harness their full spectrum of benefits. This review not only sheds light on the current status of magnolia applications but also sets the stage for future innovative uses in ecological management and biotechnological advances.

This study explored the relationship between endophytic bacterial communities and the accumulation of the bioactive lignan, magnolin, in the flower buds of three important species: Magnolia biondii, Magnolia denudata, and Magnolia liliiflora. We employed 16S rRNA gene sequencing to characterize the diversity and composition of endophytic bacteria and used high-performance liquid chromatography Mass Spectrometry (LC-MS) to quantify magnolin content. Our results revealed significant differences in bacterial diversity and community structure among the three host species, with Proteobacteria and Actinobacteria being the dominant phyla. Notably, the abundance of specific genera, such as Pseudomonas and Bacillus, showed a significant positive correlation with magnolin concentrations. These findings suggest a potential link between specific endophytic taxa and the biosynthesis of magnolin, providing novel insights for improving the medicinal value of Magnolia plants through microbial regulation. This research lays a foundation for future studies on harnessing endophytic microorganisms to enhance the production of valuable secondary metabolites in medicinal plants.

Urban microtopography plays an important role in regulating soil processes and vegetation performance in newly constructed green spaces, yet its effects on surface runoff, soil nutrients, and plant growth remain insufficiently quantified in urban relocation sites. This study investigated how slope gradient, slope position, and slope curvature influence surface runoff, soil nutrient distribution, and tree growth in Shanghai Expo Cultural Park. Field monitoring was conducted in 36 plots planted with Cinnamomum camphora and Ginkgo biloba in 2017, 2020, and 2024. Microtopographic characteristics were quantified using terrestrial and handheld three-dimensional laser scanning, point-cloud processing, and digital elevation models (DEMs), and plant growth, calculated runoff, and soil physiochemical properties were analyzed using analysis of variance (ANOVA) and regression analysis. Annual DBH increments were greatest on meso slopes (mean = 0.558 cm), followed by gentle slopes (0.513 cm) and abrupt slopes (0.511 cm). Growth was also greater at slope-tail positions than at slope-head positions and greater on concave slopes than on convex slopes. The mean calculated runoff increased from gentle to meso and abrupt slopes, and soil organic matter, total nitrogen, hydrolysable nitrogen, available phosphorus, available potassium, and cation exchange capacity were generally higher at slope-tail positions. These results indicate that micrographic design affects tree growth mainly through runoff-mediated redistribution of water and soil nutrients. These findings provide practical guidance for optimizing microtopographic design, tree species selection, and soil management in urban green spaces established on relocation sites.