PDF
Full
Outline
The permeability of karst medium is affected by multiple factors such as the geological characteristics of soluble rocks, the degree of karst development, and the fluid properties. The permeability coefficient estimation model of fractured rock mass is difficult to reflect the complexity of karst development, which makes it poorly applicable. Random Forest (RF), Support Vector Regression (SVR), CatBoost machine learning algorithm combined with Bayesian optimization algorithm were used to construct the permeability coefficient estimation model of karst media. The root mean square error (RRMSE), mean square error (MMSE) and coefficient of determination (R2) were used to verify the evaluation accuracy of the estimation model. The SHAP algorithm was used to analyze the dominant influencing factors of the permeability coefficient of karst media in machine learning model, and the influence of each influencing factor on the permeability coefficient of karst medium was clarified. The results show that the RRMSE of the optimized SVR model is 0.128 8, MMSE is 0.016 6 and R2 is 0.74, which are better than the random forest and CatBoost models, and can better estimate the permeability coefficient of karst media. The SHAP diagram revealed that there were obvious differences in the permeability coefficient of karst media between different eigenvalues of each dominant factor, and the karst rate (BK), depth (Z) and filling content (AFC) of the borehole line were the main influencing factors of the permeability coefficient of karst media, and had a significant impact on the permeability coefficient of karst media. The SVR model has high estimation accuracy and strong interpretability, which provides a certain reference value for engineering applications in karst areas.
PDF
109
42
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
