Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM

Natural attenuation of BTEX and chlorobenzenes in a formerly contaminated pesticide site in China: Examining kinetics, mechanisms, and isotopes analysis

Groundwater contamination from abandoned pesticide sites is a prevalent issue in China. To address this problem, natural attenuation (NA) of pollutants has been increasingly employed as a management strategy for abandoned pesticide sites. However, limited studies have focused on the long-term NA process of co-existing organic pollutants in abandoned pesticide sites by an integrated approach. In this study, the NA of benzene, toluene, ethylbenzene, and xylene (BTEX), and chlorobenzenes (CBs) in groundwater of a retired industry in China was systematically investigated during the monitoring period from June 2016 to December 2021. The findings revealed that concentrations of BTEX and CBs were effectively reduced, and their NA followed first-order kinetics with different rate constants. The sulfate-reducing bacteria, nitrate-reducing bacteria, fermenting bacteria, aromatic hydrocarbon metabolizing bacteria, and reductive dechlorinating bacteria were detected in groundwater. It was observed that distinct environmental parameters played a role in shaping both overall and key bacterial communities. ORP (14.72%) and BTEX (12.89%) were the main drivers for variations of the whole and key functional microbial community, respectively. Moreover, BTEX accelerated reductive dechlorination. Furthermore, BTEX and CBs exhibited significant enrichment of 13C, ranging from +2.9 to +27.3‰, demonstrating their significance in situ biodegradation. This study provides a scientific basis for site management.

Water-Quality Assessment and Pollution-Risk Early-Warning System Based on Web Crawler Technology and LSTM

The openly released and measured data from automatic hydrological and water quality stations in China provide strong data support for water environmental protection management and scientific research. However, current public data on hydrology and water quality only provide real-time data through data tables in a shared page. To excavate the supporting effect of these data on water environmental protection, this paper designs a water-quality-prediction and pollution-risk early-warning system. In this system, crawler technology was used for data collection from public real-time data. Additionally, a modified long short-term memory (LSTM) was adopted to predict the water quality and provide an early warning for pollution risks. According to geographic information technology, this system can show the process of spatial and temporal variations of hydrology and water quality in China. At the same time, the current and future water quality of important monitoring sites can be quickly evaluated and predicted, together with the pollution-risk early warning. The data collected and the water-quality-prediction technique in the system can be shared and used for supporting hydrology and in water quality research and management.