Step-like displacement prediction of landslides guided by deformation mechanism

doi:10.11947/j.AGCS.2024.20230463

Abstract

Abstract:

Rainfall reservoir-induced landslides in the Three Gorges Reservoir (TGR), China, exhibit distinctive step-like deformation characteristics, involving mutation and creep states. These particular features pose a challenge for accurate early warning and prediction. Previous landslide displacement forecasting models have shown limited prediction accuracy, particularly when it comes to mutational displacements. The proposed prediction model in this study, based on Informer, utilizes a multi-head attention mechanism to capture temporal dependencies and incorporates pooling layers for emphasizing crucial features, enabling adaptive learning of feature weights and more effective extraction of periodic information from time series data. The Baishuihe landslide was used for case studies with monitoring data collected from July 2013 to December 2018, including monthly displacements, daily rainfall and reservoir water level. Firstly, cumulative displacement was decomposed into trend displacement and periodic displacement by the variational mode decomposition (VMD). After triggering factors selection and decomposition, the double exponential smoothing (DES) method and the Informer model are used to predict the trend and periodic component displacements, respectively. Finally, the predicted trend and periodic components are combined to generate the cumulative displacement prediction. Results demonstrate that the proposed model achieves impressive results with a root mean square error of 12.21 mm, a mean absolute error of 10.05 mm, and a coefficient of determination of 0.99 for the next 27 months' cumulative displacement prediction. Compared to other four mainstream models, this approach exhibits higher prediction accuracy, particularly in predicting the rapid deformation phase of step-like bank landslides. Consequently, it holds significant credibility and practical value in the early warning research of rainfall reservoir-induced landslides.

Key words: step-like landslide, deformation mechanism, displacement prediction, Informer, attention mechanism, triggering factors

CLC Number:

P228

Yanan JIANG, Linfeng ZHENG, Qiang XU, Minggao TANG, Xing ZHU. Step-like displacement prediction of landslides guided by deformation mechanism[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(6): 1128-1139.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Fig.5

Fig.6

Tab.2

Fig.7

Tab.3

Fig.8

Tab.4

Fig.9

Fig.10

References 29

[1]	陈军, 刘万增, 武昊, 等. 智能化测绘的基本问题与发展方向[J]. 测绘学报, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
	CHEN Jun, LIU Wanzeng, WU Hao, et al. Smart surveying and mapping: fundamental issues and research agenda[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):995-1005. DOI:10.11947/j.AGCS.2021.20210235.
[2]	黄润秋. 20世纪以来中国的大型滑坡及其发生机制[J]. 岩石力学与工程学报, 2007, 26(3):433-454.
	HUANG Runqiu. Large-scale landslides and their sliding mechanisms in China since the 20th century[J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(3):433-454.
[3]	许强. 对滑坡监测预警相关问题的认识与思考[J]. 工程地质学报, 2020, 28(2):360-374.
	XU Qiang. Understanding the landslide monitoring and early warning: consideration to practical issues[J]. Journal of Engineering Geology, 2020, 28(2):360-374.
[4]	YIN Yueping, WANG Hongde, GAO Youlong, et al. Real-time monitoring and early warning of landslides at relocated Wushan Town, the Three Gorges Reservoir, China[J]. Landslides, 2010, 7(3):339-349.
[5]	郭飞, 黄晓虎, 邓茂林, 等. 三峡库区“阶跃”型滑坡变形机理与预警模型[J]. 测绘学报, 2022, 51(10):2205-2215.DOI:10.11947/j.AGCS.2022.20220296.
	GUO Fei, HUANG Xiaohu, DENG Maolin, et al. Study on deformation mechanism and warning model of step-like landslide in Three Gorges Reservoir Area[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10):2205-2215.DOI:10.11947/j.AGCS.2022.20220296.
[6]	邓冬梅, 梁烨, 王亮清, 等. 基于集合经验模态分解与支持向量机回归的位移预测方法：以三峡库区滑坡为例[J]. 岩土力学, 2017, 38(12):3660-3669.
	DENG Dongmei, LIANG Ye, WANG Liangqing, et al. Displacement prediction method based on ensemble empirical mode decomposition and support vector machine regression: a case of landslides in Three Gorges Reservoir Area[J]. Rock and Soil Mechanics, 2017, 38(12):3660-3669.
[7]	ZHU Xing, XU Qiang, TANG Minggao, et al. A hybrid machine learning and computing model for forecasting displacement of multifactor-induced landslides[J]. Neural Computing and Applications, 2018, 30(12):3825-3835.
[8]	杜娟, 殷坤龙, 柴波. 基于诱发因素响应分析的滑坡位移预测模型研究[J]. 岩石力学与工程学报, 2009, 28(9):1783-1789.
	DU Juan, YIN Kunlong, CHAI Bo. Study of displacement prediction model of landslide based on response analysis of inducing factors[J]. Chinese Journal of Rock Mechanics and Engineering, 2009, 28(9):1783-1789.
[9]	许强, 黄润秋, 李秀珍. 滑坡时间预测预报研究进展[J]. 地球科学进展, 2004, 19(3):478-483.
	XU Qiang, HUANG Runqiu, LI Xiuzhen. Research progress in time forecast and prediction of landslides[J]. Advance in Earth Sciences, 2004, 19(3):478-483.
[10]	CORSINI A, MULAS M. Use of ROC curves for early warning of landslide displacement rates in response to precipitation (Piagneto landslide, Northern Apennines, Italy) [J]. Landslides, 2017, 14(3):1241-1252.
[11]	WANG Jianmin, HUANG Jiapeng. An improved extreme learning machine prediction model for ionospheric total electron content[J]. Journal of Geodesy and Geoinformation Science, 2023 (1):1-10.
[12]	罗袆沅, 蒋亚楠, 许强, 等. 基于最优分解模态和GRU模型的库岸滑坡位移预测研究[J]. 武汉大学学报(信息科学版), 2023, 48(5):702-709.
	LUO Huiyuan, JIANG Yanan, XU Qiang, et al. Displacement prediction of reservoir bank landslide based on optimal decomposition mode and GRU model[J]. Geomatics and Information Science of Wuhan University, 2023, 48(5):702-709.
[13]	罗袆沅, 蒋亚楠, 许强, 等. 基于深度学习的滑坡位移时空预测[J]. 测绘学报, 2022, 51(10):2160-2170. DOI:10.11947/j.AGCS.2022.20220297.
	LUO Huiyuan, JIANG Yanan, XU Qiang, et al. A spatio-temporal network for landslide displacement prediction based on deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10):2160-2170. DOI:10.11947/j.AGCS.2022.20220297.
[14]	杨背背, 殷坤龙, 杜娟. 基于时间序列与长短时记忆网络的滑坡位移动态预测模型[J]. 岩石力学与工程学报, 2018, 37(10):2334-2343.
	YANG Beibei, YIN Kunlong, DU Juan. A model for predicting landslide displacement based on time series and long and short term memory neural network[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(10):2334-2343.
[15]	郭子正, 杨玉飞, 何俊, 等. 考虑注意力机制的新型深度学习模型预测滑坡位移[J]. 地球科学, 2024, 49(5):1665-1678.
	GUO Zizheng, YANG Yufei, HE Jun, et al. Landslide displacement prediction based on a deep learning model considering the attention mechanism[J]. Earth Science, 2024, 49(5):1665-1678.
[16]	廖康, 吴益平, 李麟玮, 等. 基于时间序列与GWO-ELM模型的滑坡位移预测[J]. 中南大学学报(自然科学版), 2019, 50(3):619-626.
	LIAO Kang, WU Yiping, LI Linwei, et al. Displacement prediction model of landslide based on time series and GWO-ELM[J]. Journal of Central South University (Science and Technology), 2019, 50(3):619-626.
[17]	张振坤, 张冬梅, 李江, 等. 基于多头自注意力机制的LSTM-MH-SA滑坡位移预测模型研究[J]. 岩土力学, 2022, 43(S2):477-486, 507.
	ZHANG Zhenkun, ZHANG Dongmei, LI Jiang, et al. Study on LSTM-MH-SA landslide displacement prediction model based on multi-head self-attention mechanism[J]. Rock and Soil Mechanics, 2022, 43(S2):477-486, 507.
[18]	ZHOU Haoyi, ZHANG Shanghang, PENG J, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[EB/OL]. [2023-10-07]. https://doi.org/10.1609/aaai.v35i12.17325.
[19]	李麟玮, 吴益平, 苗发盛, 等. 基于变分模态分解与GWO-MIC-SVR模型的滑坡位移预测研究[J]. 岩石力学与工程学报, 2018, 37(6):1395-1406.
	LI Linwei, WU Yiping, MIAO Fasheng, et al. Displacement prediction of landslides based on variational mode decomposition and GWO-MIC-SVR model[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(6):1395-1406.
[20]	DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3):531-544.
[21]	ZHU Xing, ZHANG Fuling, DENG Maolin, et al. A hybrid machine learning model coupling double exponential smoothing and ELM to predict multi-factor landslide displacement[J]. Remote Sensing, 2022, 14(14):3384.
[22]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. [2023-10-07]. https://arxiv.org/abs/1706.03762.
[23]	许强, 汤明高, 徐开祥, 等. 滑坡时空演化规律及预警预报研究[J]. 岩石力学与工程学报, 2008, 27(6):1104-1112.
	XU Qiang, TANG Minggao, XU Kaixiang, et al. Research on space-time evolution laws and early warning-prediction of landslides[J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(6):1104-1112.
[24]	MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69:46-61.
[25]	李卓, 何勇军, 盛金保, 等. 降雨与库水位共同作用下近坝库岸边坡滑坡模型试验研究[J]. 岩土工程学报, 2017, 39(3):452-459.
	LI Zhuo, HE Yongjun, SHENG Jinbao, et al. Landslide model for slope of reservoir bank under combined effects of rainfall and reservoir water level[J]. Chinese Journal of Geotechnical Engineering, 2017, 39(3):452-459.
[26]	JIANG Yanan, LIAO Lu, LUO Huiyuan, et al. Multi-scale response analysis and displacement prediction of landslides using deep learning with JTFA: a case study in the Three Gorges Reservoir, China[J]. Remote Sensing, 2023, 15(16):3995.
[27]	YANG Haiqing, SONG Kanglei, CHEN Lichuan, et al. Hysteresis effect and seasonal step-like creep deformation of the Jiuxianping landslide in the Three Gorges Reservoir Region[J]. Engineering Geology, 2023, 317:107089.
[28]	AZZEH M, NEAGU D, COWLING P I. Fuzzy grey relational analysis for software effort estimation[J]. Empirical Software Engineering, 2010, 15(1):60-90.
[29]	KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of 1995 International Conference on Neural Networks. Perth: IEEE, 1995, 4: 1942-1948.

阶段	时期	水位/m	主要影响因子
第一阶段	2003年6月—2006年8月	135~140	降水
第二阶段	2006年8月—2008年8月	145~156	降水、库水位
第三阶段	2008年8月—2018年12月	145~175	降水、库水位

触发因子	灰色关联度	触发因子	灰色关联度
r₁	0.764 5	r₁_l	0.791 2
r₂	0.786 3	r₂_l	0.799 4
r₃	0.697 5	r₃_l	0.732 8
k₁	0.774 0	k₁_l	0.802 2
k₂	0.823 6	k₂_l	0.887 3
k₃	0.821 7	k₃_l	0.903 9

类别	参数	类别	参数	类别	参数
seq_len	12	e_layers	2	激活函数	GELU
lable_len	11	d_layers	1	epoch	100
pred_len	1	dropout	0.05	batch_size	1
初始学习率	0.001	n_heads	8	优化算法	Adam

模型	RMSE/mm	MAE/mm	R²
Informer	9.93	8.86	0.93
GRU	15.84	14.08	0.82
LSTM	17.47	15.73	0.78
PSO-LSSVM	23.76	20.97	0.60
PSO-SVR	39.94	23.83	0.36