Using a stochastic forest prediction model to predict the hazardous gas concentration in a one-way roadway
Source abstract
Abstract
To accurately and quantitatively analyze the pollutant gas concentration in tunneling roadways, a prediction model of the pollutant gas concentration was proposed and established. Through downhole gas composition data acquisition and correlation analysis, the prediction variables of downhole gas pollution are obtained with both short-term and long-term memory neural network prediction methods and random forest regression modeling methods, making full use of historical target gas concentration data for the future in a short period of time to evaluate the model performance and prediction results. Compared with the results of the stochastic forest regression prediction and the long- and short-term memory neural network prediction, the stochastic forest regression prediction model has a good prediction effect and better generalization effect and is a reliable method with excellent performance for downhole gas concentration prediction. The analysis of the predicted results shows that the change in CO concentration is strongly correlated with CH4 and CO2 and strongly correlated with N2, making it possible to obtain the potential influencing factors of the target gas. These results provide a scientific basis for the prediction of underground pollution gas concentration and the protection and treatment of the atmospheric environment in mining areas.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Quality Monitoring and Forecasting · Traffic Prediction and Management Techniques · Coal Properties and Utilization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Environment and Resources, Xiangtan University 1 , Xiangtan 411105, China
School of Resource and Safety Engineering, Central South University 2 , Changsha 410083, China
Funding
Hunan Provincial Department of Education General Project · Hunan Provence Science Foundation for Youth Scholars of China
References (30)
Show source-provided references
1. Unascertained measure evaluation model and application of occupational hazards in underground coal mines
2. Research status and development trend of underground ventilation system in coal mines
3. Some problems of ventilation management in underground mines
4. Research on time series prediction method of gas data in fully mechanized mining face
5. Prediction of multi-factor gas concentration based on PSO-SVR
6. Prediction of gas concentration based on stochastic hidden layer weight neural network
7. Research on multi-parameter index system of coal spontaneous combustion prediction
8. Research on reliability of coal spontaneous combustion prediction index based on grey correlation analysis
9. Determination of early spontaneous combustion of coal based on prediction model of CO2 and CO concentration ratio
10. Early detection system for coal spontaneous combustion by laser dual-species sensor of CO and CH410.1016/j.optlastec.2019.105832 ↗
11. Financial market timing prediction based on deep empirical mode decomposition
12. Forecasting currency circulation data of Bank Indonesia by using hybrid ARIMAX-ANN model10.1063/1.4982867 ↗
13. Air pollution prediction using long short-term memory (LSTM) and deep autoencoder (DAE) models10.3390/su12062570 ↗
14. A long short-term memory approach to predicting air quality based on social media data10.1016/j.atmosenv.2020.117411 ↗
15. Long term rolling prediction model for solar radiation combining empirical mode decomposition (EMD) and artificial neural network (ANN) techniques10.1063/1.4999240 ↗
16. Prediction of dust storms in construction projects using intelligent artificial neural network technology10.21533/pen.v7i4.857 ↗
17. Based on empirical mode decomposition and complementary set both short-term and long-term memory neural network short-term power load forecasting
18. Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor10.1016/j.neucom.2019.11.006 ↗
19. Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting10.1016/j.ins.2020.01.043 ↗
20. Evolving differential evolution method with random forest for prediction of air pollution10.1016/j.procs.2018.05.094 ↗
21. Random forests models of particulate matter PM10: A case study10.1063/1.5064879 ↗
22. Use of random forests regression for predicting IRI of asphalt pavements10.1016/j.conbuildmat.2018.09.017 ↗
23. Application of random forest algorithm to predict the average issued amounts in ATMs10.1063/1.5137947 ↗
24. Single nucleotide polymorphism relevance learning with random forests for type 2 diabetes risk prediction10.1016/j.artmed.2017.09.005 ↗
25. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
26. Recognition of natural hand gestures using bidirectional long short-term memory model10.5391/ijfis.2018.18.4.326 ↗
27. Random forests10.1023/a:1010933404324 ↗
28. A comparison of random forest variable selection methods for classification prediction modeling10.1016/j.eswa.2019.05.028 ↗
29. Approximating prediction uncertainty for random forest regression models10.14358/pers.82.3.189 ↗
30. Using smart persistence and random forests to predict photovoltaic energy production10.3390/en12010100 ↗