Abstract
The key objective of the research was to investigate the potential of Hydrocotyle umbellata L. as a hyperaccumulator in Copper (Cu) contaminated environments and to enhance understanding of its phytoextraction efficiency through the application of unsupervised machine learning techniques alongside statistical comparisons. Here effects of Cu toxicity on pigments content, total flavonoids, total phenolic content, electrolyte leakage, translocation and bio-concentration factor were analyzed in H. umbellata L. by Analysis of Variance (ANOVA), paired t-test and correlation analysis. Whereas, the ML was applied to various experimental outputs of H. umbellata after Cu phytoextraction. The ML techniques included cluster analysis and Classification and Regression Tree (CART). There were 48 samples available for the clustering analysis with three variables (TF observations, plant part and treatment levels.) Results indicated the highest metal uptake was by roots and value of TF was 1.114 making the plant appropriate for phytoextraction of Cu. This would be one of the first attempts showing the effects of Cu toxicity on physiology, biochemical compounds, leakage ratio along with BCF and TF in H. umbellata L. Moreover, new insights from ML model interpretation along with statistical models against Cu stress could guide the effective phytoremediation by detecting the phytoextraction ability of H. umbellate L.