Irrigation prediction of integrated water and fertilizer for strawberries based on LabVIEW and decision tree model

This paper focuses on the critical water and fertilizer management stage in strawberry cultivation, proposing a new method to predict the required level of soil water and fertilizer for strawberries based on decision tree models and LabVIEW intelligent image analysis techniques. By collecting multi-dimensional images of strawberry growing soil samples and color differences in strawberry leaves across different growth stages and environmental conditions, an advanced image processing algorithm is employed to extract and analyze features such as color, texture, and shape from the soil images, establishing a correlation model between strawberry growth characteristics and water and fertilizer content. Experimental results indicate that this model can predict the primary nutrient content (nitrogen, phosphorus, potassium, etc.) needed for strawberry growth based on leaf color and estimate irrigation water volume based on soil color and climatic characteristics. Compared with traditional chemical analysis methods, the accuracy deviation is controlled within a reasonable range, and the method has significant advantages of being fast, non-destructive, and real-time monitoring. The intelligent image analysis prediction system developed based on these research findings is expected to provide convenient and efficient water and fertilizer management decision support for strawberry growers, facilitating the precision and intelligence development of the strawberry cultivation industry. This not only improves strawberry yield and quality but also effectively reduces resource wastage and environmental pollution, promoting sustainable agricultural development.