Spatial Distribution Prediction and Migration Characteristic of Petroleum Hydrocarbons in Soil Based on Artificial Neural Networks
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Soil pollution resulting from petroleum hydrocarbons (PHCs) arising from industrialization and humanactivities has emerged as a progressively severe global concern. Establishing an accurate spatial distributionprediction model for PHCs through limited sampling data play an important role in understanding the migrationcharacteristics of PHCs and effectively preventing soil pollution. This article employs soil samples within 8 mof a chemical plant, in conjunction with hydrogeological data, to model the spatial distribution of PHC contentusing a feedforward neural network (FNN). The prediction outcomes are characterized through three-dimensionalvisualization. The findings indicate that FNN demonstrates superior estimation accuracy compared to traditionalinterpolation method. Regarding the horizontal distribution within surface soil, there is pronounced lateralmigration of PHC content in both the storage area and manufacturing shop, with migration aligning followingthe direction of groundwater. Vertically, PHC content exhibits a consistent pattern of increasing and thendecreasing with greater depth. It is predominantly enriched in the lower section of the aeration zone and theupper part of the saturated zone, particularly within 4 m, under influence of groundwater. In this study, theprediction model offers an original approach to the spatial distribution of soil pollutants.
Abstract
Soil pollution resulting from petroleum hydrocarbons (PHCs) arising from industrialization and humanactivities has emerged as a progressively severe global concern. Establishing an accurate spatial distributionprediction model for PHCs through limited sampling data play an important role in understanding the migrationcharacteristics of PHCs and effectively preventing soil pollution. This article employs soil samples within 8 mof a chemical plant, in conjunction with hydrogeological data, to model the spatial distribution of PHC contentusing a feedforward neural network (FNN). The prediction outcomes are characterized through three-dimensionalvisualization. The findings indicate that FNN demonstrates superior estimation accuracy compared to traditionalinterpolation method. Regarding the horizontal distribution within surface soil, there is pronounced lateralmigration of PHC content in both the storage area and manufacturing shop, with migration aligning followingthe direction of groundwater. Vertically, PHC content exhibits a consistent pattern of increasing and thendecreasing with greater depth. It is predominantly enriched in the lower section of the aeration zone and theupper part of the saturated zone, particularly within 4 m, under influence of groundwater. In this study, theprediction model offers an original approach to the spatial distribution of soil pollutants.
참고문헌 (10)
- D. Daassi, "Petroleum-contaminated soil : environmental occurrence and remediation strategies", 3 Biotech, 12(6) (2022)[DOI]
- A. A. Elijah, "A review of the petroleum hydrocarbons contamination of soil, water and air and the available remediation techniques, taking into consideration the sustainable development goals", Earthline Journal of Chemical Sciences, 7(1), pp.97~113 (2022)[DOI]
- D. Zhao, "A knowledge-based human-computer interaction system for the building design evaluation using artificial neural network", Human-Centric Computing and Information Sciences, 13 (2023)[DOI]
- S. S. Alotaibi, "Quantum-enhanced machine learning algorithms for heart disease prediction", Human-Centric Computing and Information Sciences, 13 (2023)[DOI]
- W. Ding, "Role of sensors based on machine learning health monitoring in athletes’ wearable heart rate monitoring", Human-Centric Computing and Information Sciences, 13 (2023)[DOI]
- S. Shi, "Estimation of heavy metal content in soil based on machine learning models", Land, 11(7) (2022)[DOI]
- S. Zheng, "Spatial distribution model of DEHP contamination categories in soil based on Bi-LSTM and sparse sampling", Ecotoxicology and Environmental Safety, 229 (2022)[DOI]
- C. Li, "Use of artificial neural network to evaluate cadmium contamination in farmland soils in a karst area with naturally high background values", Environmental Pollution, 304 (2022)[DOI]
- M. M. Mijwel, "Artificial neural networks advantages and disadvantages", Mesopotamian Journal of Big Data, 2021, pp.29~31 (2021)[DOI]
- L. Wang, "The key factors for the fate and transport of petroleum hydrocarbons in soil with related in", ex situ measurement methods : an overview, 2021, pp.9, ~