Predicting potential soil and groundwater contamination risks from gas stations using three machine learning models (XGBoost, LightGBM, and Random Forest)
Прогнозирование потенциальных рисков загрязнения почвы и грунтовых вод на автозаправочных станциях с использованием трех моделей машинного обучения (XGBoost, LightGBM и Random Forest)
2025-05-01
SCID: 54.1/pxhm6qqy
Discuss with AI
LightGBMRandom ForestXGBoostgas station sitessoil and groundwater contamination
Figures from the paper
Abstract (AI)
Gas station sites pose potential risks of soil and groundwater contamination , which not only threatens public health and property but may also damage the assets and reputation of businesses and government entities. Given the complex nature of soil and groundwater contamination at gas station sites, this study utilizes field data from basic and environmental information, maintenance information for tank and pipeline monitoring, and environmental monitoring to develop machine learning models for predicting potential contamination risks and evaluating high-impact risk factors . The research employs three machine learning models: XGBoost, LightGBM, and Random Forest (RF). To compare the performance of these models in predicting soil and groundwater contamination, multiple performance metrics were utilized, including Receiver Operating Characteristic (ROC) curves, Precision-Recall graphs, and Confusion Matrix (CM). The Confusion Matrix analysis revealed the following results: accuracy of 85.1–87.4 %, precision of 86.6–88.3 %, recall of 83.0–87.2 %, and F1 score of 84.8–87.8 %. Performance ranking across all metrics consistently showed: XGBoost > LightGBM > RF. The area under the ROC curve and precision-recall curve for the three models were 0.95 (XGBoost), 0.94 (LightGBM), and 0.93 (RF), respectively. While all three machine learning approaches demonstrated satisfactory predictive capabilities, the XGBoost model exhibited optimal performance across all evaluation metrics. This research demonstrates that properly trained machine learning models can serve as effective tools for environmental risk assessment and management. These findings have significant implications for decision-makers in environmental protection, enabling more accurate prediction and control of contamination risks, thereby enhancing the preservation of ecological systems, public health, and property security.
Key Findings
1
All models achieved satisfactory predictive performance, with accuracy of 85.1–87.4%, precision of 86.6–88.3%, recall of 83.0–87.2%, and F1 scores of 84.8–87.8%.
2
Models integrated site, environmental, maintenance, tank and pipeline monitoring, and environmental monitoring data to assess contamination risk factors.
3
The findings support properly trained machine learning models as effective tools for environmental risk assessment and contamination-risk management at gas station sites.
4
Three machine learning models—XGBoost, LightGBM, and Random Forest—were developed to predict potential soil and groundwater contamination risks at gas stations.
5
XGBoost consistently outperformed LightGBM and Random Forest across evaluation metrics, achieving the highest ROC and precision-recall AUC of 0.95.
Research Object
Gas station sites and their associated soil and groundwater systems
Research Subject
Potential soil and groundwater contamination risks and their high-impact risk factors, including the predictive performance of machine-learning models
Publication Details
Publication Date
2025-05-01
Journal
Publisher
ISSN
Cited by
66
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest