An ensemble machine learning model to uncover potential sites of hazardous waste illegal dumping based on limited supervision experience.

With the soaring generation of hazardous waste (HW) during industrialization and urbanization, HW illegal dumping continues to be an intractable global issue. Particularly in developing regions with lax regulations, it has become a major source of soil and groundwater contamination. One dominant challenge for HW illegal dumping supervision is the invisibility of dumping sites, which makes HW illegal dumping difficult to be found, thereby causing a long-term adverse impact on the environment. How to utilize the limited historic supervision records to screen the potential dumping sites in the whole region is a key challenge to be addressed. In this study, a novel machine learning model based on the positive-unlabeled (PU) learning algorithm was proposed to resolve this problem through the ensemble method which could iteratively mine the features of limited historic cases. Validation of the random forest-based PU model showed that the predicted top 30% of high-risk areas could cover 68.1% of newly reported cases in the studied region, indicating the reliability of the model prediction. This novel framework will also be promising in other environmental management scenarios to deal with numerous unknown samples based on limited prior experience.

Health risks of odorous compounds during the whole process of municipal solid waste collection and treatment in China.

The high moisture content and perishable organic waste of municipal solid waste (MSW) in China have caused the severe odor nuisance to be one of the crucial reasons for resident complaints. Understanding the environmental risks of odorous compounds lays the foundations for resolving the problems. This study collected concentration data of 86 odorous compounds in five types of MSW processing facilities/equipment which can well represent the whole process of MSW stream, including waste bins and transfer stations for collection, compost plants and anaerobic digestion plants for utilization, and landfills for final disposal. The results revealed that the occupational health risks of odorants were not fully consistent with the compound concentrations and olfactory annoyance. Higher odorous compound concentrations and more severe olfactory annoyance can be found in the MSW utilization and disposal facilities, but the occupational carcinogenic risk (2.79 × 10-5-1.12 × 10-3) was non-negligible along the whole MSW stream. Aromatic hydrocarbons and halogenated hydrocarbons were crucial contributors to the carcinogenic risk of odorous compounds emission from these facilities. Particularly for estimating the adverse impact range of MSW facilities, the carcinogenic risk was the most critical factor, implying impact distance of ∼1.5 km for MSW transfer station and ∼5 km for landfill, and even higher for the regions (such as southwest China) with lower wind speed and higher atmospheric stability. In addition to current regulations, another 5 compounds (acetaldehyde, 1,3,5-trimethylbenzene, 1,2-dichloroethane, acrolein, and benzyl chloride) that displayed high carcinogenic risks were suggested to be concerned. This study provided insights for the policymakers regarding MSW odors management, especially underscoring the importance of considering the health risks of odorous compounds.