Every human activity that results in natural environment degradation can be perceived as pollution. Land pollution occurs through the contamination of land with liquid or solid waste materials. While pollution has existed for a long time throughout human history, land pollution presents one of the most significant issues modern society faces. Soil fertility depends on the balance of minerals and the soil’s overall quality and texture. Thus, using soil to grow specific plants requires the right balance of useful substances and minerals. Similarly, to ensure healthy living, humanity needs to maintain the correct balance of substances in the soil because it determines the quality of air and water resources. This paper will explore the literature on the topic of land pollution and analyze the qualitative data to define effective preventative measures in land pollution management.
Next, many potential factors can directly or indirectly cause land pollution, and to a large extent, these reasons are related to the process of extracting economic benefits. Firstly, the mining industry is often acknowledged as a substantial contributor to the pollution of soil because mining produces vast qualities of structureless geologic materials containing toxic metals (Artiola, 2019). The toxic metals from mining can infiltrate deep soil and enter groundwater at a significant distance away from the place of the mine. For example, the research conducted by Avkopashvili et al. (2022), which studied the metal pollution in mining areas, found that the high lead concentration was in a two-kilometer radius of the mining location. Moreover, a dangerously high cadmium concentration was discovered in a village 15 km from the mining area (Figure 1). Thus, the example of toxic metals spread illustrates the importance of taking the necessary measures to stop the spread of land pollution.
Furthermore, industrial wastes from oil drilling and coal-fired power plants stored in ponds and landfills also contribute to land pollution, even though they are comparatively less dangerous than toxic metals. Lately, the topic of land pollution with plastic has started receiving more attention due to the presence of toxic additives used in the production and the direct impact the plastic litter causes on animals (Ukaogo et al., 2020). While environmental laws provide penalties for companies contributing to environmental pollution, it is necessary to develop methods that will help to address the issue more effectively and avoid land pollution in future.
The existing pollution prevention methods focus on the corrective policies in corporate organizations. The policies apply to the production of iron, cement, leather, paper, and pharmaceutical products and generally apply to reduction, reuse, and recovery processes. According to Basu et al. (2019), in cement production, the pollution prevention methods include cleaning the wind box during sintering, mixing coke fuel blends with sunflower seed husk, and using a roll press for refining. However, there is a significant gap between the potential and actual implementation of prevention policies across different industries (Figure 2). Thus, the data signals the growing need to develop more effective land pollution prevention methods.
The rapid development of technologies marked a significant step in studies on environmental pollution. The research conducted by Ye et al. (2019) explores how such data as ground slope, land use, vegetation index, soil type, and topographic wetness index can be used to assess pollution in aquatic environments. Thus, with the application of machine learning and artificial intelligence to pollution data, researchers can acquire estimated data about the concentration of pollutants in soil and groundwater. For example, the study conducted by Band et al. (2020) compares several models based on machine-learning methods which allow estimation of nitrate concentration in groundwater. The models included the fandom forest algorithm, which constructs decision trees, the support vector machine method algorithms, which analyze data for its classification, and the artificial neural network, which imitates the work of animal brains. The study determined that different models performed better or worse depending on the specific conditions of the region. Similar machine-learning programs with the use of the same models can be developed to predict land pollution levels and take timely preventative measures.
In conclusion, this research paper aimed to identify effective methods for preventing land pollution through an examination of existing literature. Firstly, the paper explained the importance of addressing land pollution for environmental safety. Next, the paper identified that the common sources of land pollution primarily include activities aimed at extracting economic benefits, such as mining and industrial production of iron, cement, leather, paper, and pharmaceutical goods. Furthermore, the research identified that the policies in the prevention of land pollution for corporate organizations generally focus on reduction, reuse, and recovery processes. However, the research defined a significant gap between the potential and actual implementation of prevention policies, especially in the leather industry. After examining the existing body of knowledge on pollution assessment and prevention, the research paper proposed the application of machine learning and artificial intelligence technologies for the effective prevention of land pollution.
References
Artiola, J.F. (2019). Soil and land pollution. In M. L. Brusseau, I. L. Pepper, & C. P. Gerba (Eds), Environmental and pollution science (3rd ed.) (pp. 219–235). Academic Press.
Avkopashvili, M., Avkopashvili, G., Avkopashvili, I., Asanidze, L., Matchavariani, L., Gongadze, A., & Gakhokidze, R. (2022). Mining-related metal pollution and ecological risk factors in South-Eastern Georgia. Sustainability, 14(9), 1-15.
Band, S. S., Janizadeh, S., Pal, S. C., Chowdhuri, I., Siabi, Z., Norouzi, A., Melesse, A. M., Shokri, M., & Mosavi, A. (2020). Comparative analysis of Artificial Intelligence models for accurate estimation of groundwater nitrate concentration. Sensors, 20, 1-23.
Basu, S., Roy, M. & Pal, P. (2019). Corporate greening in a large developing economy: pollution prevention strategies. Environment, Development and Sustainability, 21, 1603–1633.
Ukaogo, P. O., Ugochukwu, E., & Onwuka, C. V. (2020). Environmental pollution: Causes, effects, and the remedies. In P. Chowdhary, A. Raj, D. Verma, & Y. Akher (Eds.), Microorganisms for sustainable environment and health (pp. 419–429). Elsevier.
Ye, Z., Yang, J., Zhong, N., Tu, X., Jia, J., & Wang, J. (2019). Tackle environmental challenges in pollution controls using artificial intelligence: A review. Science of The Total Environment, 699, 1-78.