PDF
Full
Outline
To address the issue of settlement in existing subway tunnels due to the construction of new adjacent tunnels, an automated machine learning approach and a strategy for weighting multisource data were employed. A predictive model was developed, taking into account tunnel characteristics, stratum properties, and relative positional relationships as input parameters, with the settlement values of the existing tunnels as the output. The model was tested using tens of thousands of simulation data points and realworld data. The findings suggest that while the automated machine learning algorithm can produce a highly accurate predictive model based on simulation data, it may not perform as well with multisource data sets. By assigning weights to multisource data, the model's ability to generalize can be improved, leading to an optimized model that specializes in realworld data, based on simulation data. When the quantity of weighted realworld data is comparable to the simulation data, the model's error rate is reduced. Additionally, according to the feature importance of the bestperforming model, the stratum loss rate emerges as a critical input parameter for prediction, with the significance of geological conditions, spatial relationships, and construction attributes being nearly equivalent.
PDF
320
130
| 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
