Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution
During long-term geological tectonic processes, multiple fractures are often developed in the rock mass of high-level radioactive waste disposal sites, which provide channels for release of radioactive material or radionuclides. Studies on the permeability of fractured rock masses are essential for...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-02-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2022.835308/full |
| _version_ | 1819349918670651392 |
|---|---|
| author | Nisong Pei Nisong Pei Yong Wu Rui Su Xueling Li Zhenghao Wu Renhai Li Heng Yin Heng Yin |
| author_facet | Nisong Pei Nisong Pei Yong Wu Rui Su Xueling Li Zhenghao Wu Renhai Li Heng Yin Heng Yin |
| author_sort | Nisong Pei |
| collection | DOAJ |
| description | During long-term geological tectonic processes, multiple fractures are often developed in the rock mass of high-level radioactive waste disposal sites, which provide channels for release of radioactive material or radionuclides. Studies on the permeability of fractured rock masses are essential for the selection and evaluation of geological disposal sites. With traditional methods, observation and operation of fractured rock mass penetration is time-consuming and costly. However, it is possible to improve the process using new methods. Based on the penetration characteristics of fractured rock mass, and using machine learning techniques, this study has created a prediction model of the fractured rock mass permeability based on select physical and mechanical parameters. Using the correlation coefficients developed by Pearson, Spearman, and Kendall, the proposed framework was first used to analyze the correlation between the physical and mechanical parameters and permeability and determine the model input parameters. Then, a comparison model was created for permeability prediction using four different machine-learning algorithms. The algorithm hyper-parameters are determined by a ten-fold cross-validation. Finally, the permeability interval prediction values are obtained by comparing and selecting the prediction results and probability distribution density function. Overall, the computational results indicate the framework proposed in this paper outperforms the other benchmarking machine learning algorithms through case studies in Beishan District, Gansu, China. |
| first_indexed | 2024-12-24T19:08:09Z |
| format | Article |
| id | doaj.art-889875ef3b6e4e22ba74ce921008f893 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-12-24T19:08:09Z |
| publishDate | 2022-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-889875ef3b6e4e22ba74ce921008f8932022-12-21T16:43:04ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632022-02-011010.3389/feart.2022.835308835308Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability DistributionNisong Pei0Nisong Pei1Yong Wu2Rui Su3Xueling Li4Zhenghao Wu5Renhai Li6Heng Yin7Heng Yin8College of Environment and Civil Engineering, Chengdu University of Technology, Chengdu, ChinaSichuan Academy of Safety Science and Technology, Chengdu, ChinaCollege of Environment and Civil Engineering, Chengdu University of Technology, Chengdu, ChinaBeijing Research Institute of Uranium Geology, Beijing, ChinaCollege of Environment and Civil Engineering, Chengdu University of Technology, Chengdu, ChinaCollege of Environment and Civil Engineering, Chengdu University of Technology, Chengdu, ChinaSichuan Academy of Safety Science and Technology, Chengdu, ChinaCollege of Environment and Civil Engineering, Chengdu University of Technology, Chengdu, ChinaSichuan Academy of Safety Science and Technology, Chengdu, ChinaDuring long-term geological tectonic processes, multiple fractures are often developed in the rock mass of high-level radioactive waste disposal sites, which provide channels for release of radioactive material or radionuclides. Studies on the permeability of fractured rock masses are essential for the selection and evaluation of geological disposal sites. With traditional methods, observation and operation of fractured rock mass penetration is time-consuming and costly. However, it is possible to improve the process using new methods. Based on the penetration characteristics of fractured rock mass, and using machine learning techniques, this study has created a prediction model of the fractured rock mass permeability based on select physical and mechanical parameters. Using the correlation coefficients developed by Pearson, Spearman, and Kendall, the proposed framework was first used to analyze the correlation between the physical and mechanical parameters and permeability and determine the model input parameters. Then, a comparison model was created for permeability prediction using four different machine-learning algorithms. The algorithm hyper-parameters are determined by a ten-fold cross-validation. Finally, the permeability interval prediction values are obtained by comparing and selecting the prediction results and probability distribution density function. Overall, the computational results indicate the framework proposed in this paper outperforms the other benchmarking machine learning algorithms through case studies in Beishan District, Gansu, China.https://www.frontiersin.org/articles/10.3389/feart.2022.835308/fullhigh-level waste disposalfractured rock mass permeabilitymachine learninginterval predictionprobability distribution |
| spellingShingle | Nisong Pei Nisong Pei Yong Wu Rui Su Xueling Li Zhenghao Wu Renhai Li Heng Yin Heng Yin Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution Frontiers in Earth Science high-level waste disposal fractured rock mass permeability machine learning interval prediction probability distribution |
| title | Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution |
| title_full | Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution |
| title_fullStr | Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution |
| title_full_unstemmed | Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution |
| title_short | Interval Prediction of the Permeability of Granite Bodies in a High-Level Radioactive Waste Disposal Site Using LSTM-RNNs and Probability Distribution |
| title_sort | interval prediction of the permeability of granite bodies in a high level radioactive waste disposal site using lstm rnns and probability distribution |
| topic | high-level waste disposal fractured rock mass permeability machine learning interval prediction probability distribution |
| url | https://www.frontiersin.org/articles/10.3389/feart.2022.835308/full |
| work_keys_str_mv | AT nisongpei intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT nisongpei intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT yongwu intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT ruisu intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT xuelingli intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT zhenghaowu intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT renhaili intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT hengyin intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution AT hengyin intervalpredictionofthepermeabilityofgranitebodiesinahighlevelradioactivewastedisposalsiteusinglstmrnnsandprobabilitydistribution |