Speaker
Description
The study explored the potential of applying Machine Learning (ML) techniques for Polycyclic Aromatic Hydrocarbon (PAH) determination in diesel tainted soils. A diesel contaminated soil was remediated by employing bio-geotechnical methods of plant (i.e. Megathyrsus maximus) and soil microbes obtained from poultry manure. PAH contaminants from the hydrocarbon contamination were degraded and reduced to 3.77mg/kg from 47.25 mg/kg. However, the effectiveness of phytoremediation is solely based on the time that is up for various planting cycles to ensure the uptake of the contaminants by the plants, which is time consuming and tedious. However, the use of data mining techniques to forecast the obliteration efficacy was achieved with the help of machine learning techniques, phytoremediation data/parameters generated from pot and field experiments such as the soil pH, organic carbon, and electrical conductivity, as well as the relative pollutant concentrations. These were subjected to data mining categorization. Four ML algorithms (Random Forest, RF; Support Vector Machine, SVM; Multi-Layer Perceptron, MLP; and Linear Regression, LR) were deployed and compared to each other with the help of the 10-fold cross-validation tool of the machine learning software WEKA. Results from the evaluation parameters of the algorithms showed that RF algorithm which had a correlation coefficient of 0.9277 was better than the other algorithms (SVM = 0.8659, MLP = 0.872, and LR = 0.8749). Comparatively, the RF present the best algorithm in building a PAH prediction for diesel contaminated soils. As such the RF algorithm can be deployed for use as a learning tool in phytoremediation analysis.
Keywords: Megathyrsus maximus, Random Forest (RF), Phytoremediation, PAH.