An important practice in environmental risk management is assessing the consequences of heavy metal concentrations resulting from a mine dam tailing failure on soil, water, and trees. To appraise the extent of pollution, an effective classification is essential. In this study, trace element contamination is handled as a two-group classification problem and examined the performance of supervised regularization algorithms as spatial classifiers using imbalanced uncertain data. In addition to conventional shrinkage algorithms such as Ridge, the Lasso and Elastic-Net, the generalized t-statistic-based U-Lasso classifiers have been introduced and tested for mitigating such imbalances and adjusting weights for class distributions. The feature interpretation studies underlined that the most important indicator of the models is Zinc (Zn). The experimental studies revealed that the Ridge classifier (l2 penalty) outperforms the other models. Statistically, the U-Lasso models exhibited notable explanation capacity and their performances recorded close to the conventional shrinkage algorithms. The use of statistical learning-based classification approach to appraise geo-environmental contamination under the conditions of natural variability and spatial uncertainty provides useful meta-data and reliable classification models.

Magnetic properties are used throughout the world to measure the concentration of (ferri) magnetic minerals in soil, sediment and dust. These minerals in soil come from a variety of sources, including air-borne particulate pollution, parent rock and paedogenesis. Changes in the content of magnetic minerals, as well as their spatial and vertical distribution in soil profiles are caused by human activity. Magnetic minerals are distinguished by their affinity for other elements found in soil, such as heavy metal. As a result, magnetic susceptibility has been widely used as an approximation of heavy metal contamination in soil. The current study was conducted in a tropical deciduous forest in Central Uttar Pradesh, namely the kukrail reserve forest in Lucknow to assess heavy metal contamination levels caused by various anthropogenic activities and to confirm the utility of using MS surveying in these types of studies. The current study was conducted at two sites viz. agricultural area and forest area because these sites are the most contaminated ones. Significant correlation between heavy metal concentration and magnetic susceptibility with p<0.005 is noticed for Co, Cr, Pb, Zn, Cu and Fe of agricultural area. Similarly in forest area significant correlation exists between Cr, Ni, Pb and Zn.  The χLF values show a significant correlation with the concentration of heavy metals except for Cu and Cr in forest area and Pb and Zn in agricultural area. In comparison to the methodologies of chemical analysis, the χLF measurement techniques provide us with lower cost and less time consuming method for identification of possible soil pollution.

Bioremediation has become a trending and developing field in environmental restoration through the use of micro-organisms to utilize and reduced the concentration and toxicity of various chemical pollutants. This study is on bioremediation of hydrocarbon-polluted soils using some agricultural wastes. Ninety (90) plastic buckets were filled with 4kg each of the composite soil. The soil contained in the plastic buckets was spiked with 250ml crude oil, except in the unpolluted plastic buckets (0%) crude oil. The agro-wastes (plantain stem sap, bush mango peels, and fruited pumpkin husk powder) in single and combined forms were applied after 14 days soil pollution. The amendments were applied as follows: Pristine control (0% agro-wastes), crude-oil control (0% agro-wastes), 150g, 250g, and 350g of the agro-wastes. Soil samples were collected at 90 days for soil microbial counts and the total hydrocarbon content of the soil. Data collected were subjected to 2-way ANOVA. The result showed that the microbial population in the crude-oil polluted soil amended with different agricultural wastes significantly increased (p<0.05) the total heterotrophic and crude oil utilizing bacterial and fungal counts in the soils and the increase in microbial population result in a significant reduction in total hydrocarbon content (THC) of the soils. The reduction in the THC of the soil was treatment dependent. It is, therefore concluded that based on the efficiency of these agro-wastes in enhancing microbial degradation, further studies should be carried out on the enzyme activities and production of bio-surfactant from the wastes to shorten the degradation time.