气候变化领域集成服务门户(CCPortal): A deep learning forecasting method for frost heave deformation of high-speed railway subgrade

CCPortal

DOI	10.1016/j.coldregions.2021.103265
	A deep learning forecasting method for frost heave deformation of high-speed railway subgrade
	Chen, Jing; Li, Anyuan; Bao, Chunyan; Dai, Yanhua; Liu, Minghao; Lin, Zhanju; Niu, Fujun; Zhou, Tianxiang
通讯作者	Li, AY (通讯作者)，Shaoxing Univ, Coll Civil Engn, Shaoxing 31200, Peoples R China. ; Liu, MH ; Zhou, TX (通讯作者)，Shaoxing Univ, Coll Elect & Mech Engn, Shaoxing 31200, Peoples R China.
发表日期	2021
ISSN	0165-232X
EISSN	1872-7441
卷号	185
英文摘要	Deformation of high-speed railway subgrades, due to low temperatures, is a common phenomenon in cold regions. In winter, the uneven frost heave of subgrade soil would cause hazards to train safety. It is therefore necessary to estimate and predict the subgrade properties. Since the variation of frost heave is non-stationary over time, traditional time series analyses have difficulties where complex physical parameters are not available. In this study, we introduce two models based on deep learning technology to predict frost heave deformation of railway subgrade. These include the artificial neural network (ANN) and long-short term memory (LSTM) network, where we used data of four sections to build the ANN and LSTM. The experimental results of the LSTM model provided lower MAE and RMSE with different datasets. The prediction of three deep deformations for the K1959 + 580 and K1962 + 618 section with slight fluctuation in the data and the performance of the ANN with MAE is 0.0090-?0.0660 and 0.0069-?0.0201 of the LSTM models. In the K2005 + 948 and K2029 + 829 section, ANN and LSTM estimated the frost heave deformation with MAE of 0.0061-?0.0681 and 0.0054-?0.0309 for a more intense fluctuation on the deformation. Our findings suggest that the network topology of the LSTM model with 12 hidden neurons performs best with fewer parameters, with an average RMSE of 0.0210 mm and MAE of 0.0138 for all the training samples, indicating that the deep learning model has high precision in this scenario.
关键词	MEMORY NEURAL-NETWORK DISPLACEMENT PREDICTION GROUND TEMPERATURES SOIL-MOISTURE TERM EMBANKMENT
英文关键词	Deep Learning; Frost heave; Time series; Forecasting
语种	英语
WOS研究方向	Engineering ; Geology
WOS类目	Engineering, Environmental ; Engineering, Civil ; Geosciences, Multidisciplinary
WOS记录号	WOS:000630878000001
来源期刊	COLD REGIONS SCIENCE AND TECHNOLOGY
来源机构	中国科学院西北生态环境资源研究院
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/254998
作者单位	[Chen, Jing; Li, Anyuan; Bao, Chunyan; Dai, Yanhua] Shaoxing Univ, Coll Civil Engn, Shaoxing 31200, Peoples R China; [Li, Anyuan; Bao, Chunyan; Dai, Yanhua] Shaoxing Univ, Key Lab Rock Mech & Geohazards Zhejiang Prov, Shaoxing 31200, Peoples R China; [Liu, Minghao; Lin, Zhanju; Niu, Fujun] Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, State Key Lab Frozen Soil Engn, Lanzhou, Peoples R China; [Zhou, Tianxiang] Shaoxing Univ, Coll Elect & Mech Engn, Shaoxing 31200, Peoples R China
推荐引用方式 GB/T 7714	Chen, Jing,Li, Anyuan,Bao, Chunyan,et al. A deep learning forecasting method for frost heave deformation of high-speed railway subgrade[J]. 中国科学院西北生态环境资源研究院,2021,185.
APA	Chen, Jing.,Li, Anyuan.,Bao, Chunyan.,Dai, Yanhua.,Liu, Minghao.,...&Zhou, Tianxiang.(2021).A deep learning forecasting method for frost heave deformation of high-speed railway subgrade.COLD REGIONS SCIENCE AND TECHNOLOGY,185.
MLA	Chen, Jing,et al."A deep learning forecasting method for frost heave deformation of high-speed railway subgrade".COLD REGIONS SCIENCE AND TECHNOLOGY 185(2021).