Artificial Neural Network Modeling for Predicting Heavy Metal Phytoremediation Efficiency: A Machine Learning Approach

The intent of this project was to determine if Helianthus annuus (sunflower) can be utilized as a remedial or phytoremediation plant, to remove and detoxify heavy metals from contaminated soils. Since there are growing concerns about the presence of heavy metals in soil due to industrial pollution, finding sustainable and effective ways to eliminate and mitigate these pollutants has become very important. We used ANNs to evaluate various parameters in phytoremediation, including type of soil, concentration of metals, moisture level, and climate/temporal conditions. The data was gathered from experimental tests in controlled pots, and an ANN was utilized to analyze the parameters affecting sunflower uptake efficiency and overall health. Findings: The input of an Artificial Neural Network (ANN) are essential to understanding how the selected variables related with Helainthus annuus (sunflower) phytoremediation of soil. Analysis resulted in identifying the best conditions for improving the ability of Helainthus annuus to Phyto-remediate soils. This research has led to some new insights into the capabilities of Helainthus annuus to Phyto remediate and proved that modern computer assisted methods provide credible support for researchers within the field of Environment Sciences. This research will also allow for greater use of Helainthus annuus for improving the sustainability of soil management and reducing pollution in the environment.