Skip to main content
ARS Home » Midwest Area » Wooster, Ohio » Application Technology Research » Research » Publications at this Location » Publication #416252
Research Project: Sustainable Production and Pest Management Practices for Nursery, Greenhouse, and Protected Culture Crops

Location: Application Technology Research

Title: A data-driven approach for generating foliar nutrient interpretation ranges and machine learning-based interpretation for petunia

Author
item VEAZIE, PATRICK - North Carolina State University
item CHEN, HSUAN - North Carolina State University
item HICKS, KRISTIN - North Carolina Department Of Agriculture & Consumer Services
item Boldt, Jennifer
item WHIPKER, BRIAN - North Carolina State University

Submitted to: HortScience
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/7/2025
Publication Date: 5/8/2025
Citation: Veazie, P., Chen, H., Hicks, K., Boldt, J.K., Whipker, B. 2025. A data-driven approach for generating foliar nutrient interpretation ranges and machine learning-based interpretation for petunia. HortScience. 60(6): 878-888. https://doi.org/10.21273/hortsci18508-25.
DOI: https://doi.org/10.21273/hortsci18508-25

Interpretive Summary: Published leaf nutrient ranges guide the interpretation of plant nutrient analyses. These ranges help growers identify if a plant has a nutrient deficiency or toxicity. However, many leaf nutrient ranges are crop-specific and based on small datasets. A large dataset of leaf nutrient analyses was modeled to refine leaf nutrient ranges for petunia, a popular ornamental crop. Deficient, low, sufficient, high, and excessive values were defined for eleven essential elements. Additionally, we identified two machine learning models that classified the leaf nutrient analyses with high accuracy. This will help growers, researchers, and laboratories 1) better identify when petunia plants are deficient or excessive in a particular nutrient and 2) provide a more accurate interpretation of the nutrient analysis. Improved interpretation of leaf nutrient status will improve crop yields, reduce overuse of fertilizers, and improve grower profitability.

Technical Abstract: Historically, leaf tissue standards have been developed and used to interpret foliar tissue analyses for the majority of horticultural crops to diagnose nutrient disorders. However, leaf tissue standards for petunia (Petunia ×hybrida) are based on survey concentrations from small datasets. This study presents a novel method to create data-driven nutrient interpretation ranges by fitting models to provide more refined ranges of deficient, low, sufficient, high, and excessive for 11 essential elements, based on n=1420 data points. Data distributions were analyzed by fitting Normal, Gamma, and Weibull distributions. Additionally, four machine learning algorithms [J48, Random Forest (RF), SMO, and MLP] were examined to determine if machine learning models could accurately classify foliar tissue analysis samples into the correct interpretation range. For all examined essential nutrients, J48 or RF yielded the greatest percent correct classification compared to MLP or SMO. This study establishes the novel use of machine learning for interpretation of petunia foliar nutrient analysis results with a higher accuracy rate by traditional statistical methods.