Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM
Open Access
- 30 July 2022
- journal article
- research article
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (15) , 9374
Abstract
Chlorinated aliphatic hydrocarbons (CAHs) are widely used in agriculture and industries and have become one of the most common groundwater contaminations. With the excellent performance of the deep learning method in predicting, LSTM and XGBoost were used to forecast dichloroethene (DCE) concentrations in a pesticide-contaminated site undergoing natural attenuation. The input variables included BTEX, vinyl chloride (VC), and five water quality indicators. In this study, the predictive performances of long short-term memory (LSTM) and extreme gradient boosting (XGBoost) were compared, and the influences of variables on models’ performances were evaluated. The results indicated XGBoost was more likely to capture DCE variation and was robust in high values, while the LSTM model presented better accuracy for all wells. The well with higher DCE concentrations would lower the model’s accuracy, and its influence was more evident in XGBoost than LSTM. The explanation of the SHapley Additive exPlanations (SHAP) value of each variable indicated high consistency with the rules of biodegradation in the real environment. LSTM and XGBoost could predict DCE concentrations through only using water quality variables, and LSTM performed better than XGBoost.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFC1800202)
- National Natural Science Foundation of China (41977139)
- Special Fund of Chinese Central Government for Basic Scientific Research Operations in Commonweal Research Institute (GYZX220101, GYZX220303)
- Jiangsu Innovative and Entrepreneurial Talent Programme (JSSCBS20211318)
This publication has 34 references indexed in Scilit:
- Detoxification of 1,1,2-trichloroethane to ethene in a bioreactor co-culture of Dehalogenimonas and Dehalococcoides mccartyi strainsJournal of Hazardous Materials, 2017
- Simulation of combined anaerobic/aerobic bioremediation of tetrachloroethylene in groundwater by a column systemInternational Biodeterioration & Biodegradation, 2017
- XGBoost2016
- Enhanced bioremediation of TCE-contaminated groundwater with coexistence of fuel oil: Effectiveness and mechanism studyChemical Engineering Journal, 2016
- Characterization of Chlorinated Aliphatic Hydrocarbons and Environmental Variables in a Shallow Groundwater in Shanghai Using Kriging Interpolation and Multifactorial AnalysisPLOS ONE, 2015
- A Simplified Image Analysis Method to Study LNAPL Migration in Porous MediaSoils and Foundations, 2011
- Removal of trichloroethylene from soil using the hydration of calcium oxideJournal of Environmental Management, 2011
- Natural and enhanced anaerobic degradation of 1,1,1-trichloroethane and its degradation products in the subsurface – A critical reviewWater Research, 2011
- Aerobic biodegradation of vinyl chloride and cis-1,2-dichloroethylene in aquifer sedimentsChemosphere, 2005
- Long Short-Term MemoryNeural Computation, 1997