Effect of vermicompost application on the development of plant properties and root architecture analysis with machine learning in <i>Buxus herlandii</i>

ABSTRACT The effects of liquid vermicompost (commercial product) on nutrient content, root architecture, and plant development were studied at doses of 0, 10, 20, 40, and 80 mL · pot −1 . Significant increases in plant height (3.5%), shoot length (25%), leaf width (16.9%), and leaf length (15.8%) were observed at the 40 mL · pot −1 application compared to the control group. The highest number of shoots was observed at 10 mL · pot −1 , while the 80 mL · pot −1 application led to a 3.9% reduction in shoot count. Root architecture showed a general decline compared to the control, though root length and tips number increased with 10 mL · pot −1 , and root volume was highest at 40 mL · pot −1 . However, high doses (40 and 80 mL · pot −1 ) caused a decrease in root surface area, forks number, and root crossings number. The highest nitrogen (31%) and manganese (57%) values were found at 10 mL · pot −1 . Phosphorus (–41%) and magnesium (40%) were lowest at 80 mL · pot −1 , while zinc (–46%) was lowest at 10 mL · pot −1 . The highest potassium content was recorded at 40 mL · pot −1 (58%). The highest calcium (1.2%), iron (23%), and copper (77%) levels were obtained at 20 mL · pot −1 . Machine learning algorithms used for root growth prediction showed the following performance ranking: PART &gt; J48 &gt; Multilayer Perceptron &gt; Multi-Class Classifier. These findings provide valuable insights for predicting root growth in Buxus crops