Research on landslide deformation rate prediction method based on dynamic serial PSO-BiLSTM
-
摘要:
针对现有突发型滑坡变形速率预测方法存在诸如精度不足、计算效率低等问题，提出一种基于动态串联PSO-BiLSTM的滑坡变形速率预测方法。首先，采用动态滑窗方式截取滑坡变形速率，并通过集合经验模态分解（EEMD）对截取的变形速率序列进行分解，得到趋势项及周期项；其次，分别通过多项式拟合和周期项PSO-BiLSTM网络得到趋势项和周期项的变形速率预测序列；再次，经过一系列循环得到残差变形速率序列后，结合趋势项及周期项变形速率预测序列，建立总PSO-BiLSTM预测网络，得到总预测变形速率；最后，以四川省某滑坡监测为例对方法进行了验证。结果表明：基于动态串联PSO-BiLSTM算法的MAE、MAPE、RMSE、R2分别为0.28、5.41%、0.57、0.98，计算时间为380.22 s，在具有较高的精度的同时保证了计算效率。
-
关键词:
- PSO /
- 双向长短时记忆神经网络 /
- 集合经验模态分解 /
- 变形速率预测
Abstract:This paper proposed a method for predicting landslide deformation rates using a dynamic serial PSO-BiLSTM approach, aiming to overcome the limitation such as insufficient accuracy and low computational efficiency found in existing methods. Initially, the deformation rate of landslides is captured through a dynamic sliding window technique, and the resulting sequence is decomposed using ensemble empirical mode decomposition (EEMD) to extract trend and periodic components. Subsequently, the deformation rate prediction sequences of trend and periodic components were obtained through polynomial fitting and a periodic component of PSO-BiLSTM network, respectively. After several cycles that produce residual deformation rate sequences, these are integrated with the initial prediction sequences to establish a comprehensive PSO-BiLSTM prediction network that yields the total predicted deformation rate. The method was validated with a landslide monitoring case in Sichuan Province, achieving a MAE of 0.28, a MAPE of 5.41%, an RMSE of 0.57, and an R2 of 0.98, with a computation time of 380.22 seconds, thus ensuring high accuracy and computational efficiency.
-
-
表 1 预测结果评价
Table 1. Evaluation of prediction results
预测
类型位移评价指标 计算时间/s MAE MAPE/% RMSE R2 类型Ⅰ 0.43 8.45 0.70 0.96 24.89 类型Ⅱ 0.36 7.07 0.61 0.97 294.50 类型Ⅲ 0.30 5.82 0.51 0.98 1861.87 类型Ⅳ 0.28 5.41 0.57 0.98 380.22 
下载: 导出CSV
-
[1] 国家统计局. 中国统计年鉴2024[J]. 北京:中国统计出版社,2024. National Bureau of Statistics. China Statistical Yearbook 2024 [J]. Beijing:China Statistical Publishing House,2024.
[2] 许强,彭大雷,何朝阳,等. 突发型黄土滑坡监测预警理论方法研究——以甘肃黑方台为例[J]. 工程地质学报,2020,28(1):111 − 121. [XU Qiang,PENG Dalei,HE Chaoyang,et al. Theory and method of monitoring and early warning for sudden loess landslide:A case study at Heifangtai terrace[J]. Journal of Engineering Geology,2020,28(1):111 − 121. (in Chinese with English abstract)]
XU Qiang, PENG Dalei, HE Chaoyang, et al. Theory and method of monitoring and early warning for sudden loess landslide: A case study at Heifangtai terrace［J］. Journal of Engineering Geology, 2020, 28（1）: 111 − 121. （in Chinese with English abstract）
[3] 陈文涛,杨志全,朱颖彦,等. 阿塔巴德滑坡形成条件与诱发机制分析[J]. 中国安全科学学报,2020,30(11):148 − 155. [CHEN Wentao,YANG Zhiquan,ZHU Yingyan,et al. Analyses on formation conditions and triggering mechanism of Atabad landslide[J]. China Safety Science Journal,2020,30(11):148 − 155. (in Chinese with English abstract)]
CHEN Wentao, YANG Zhiquan, ZHU Yingyan, et al. Analyses on formation conditions and triggering mechanism of Atabad landslide［J］. China Safety Science Journal, 2020, 30（11）: 148 − 155. （in Chinese with English abstract）
[4] 董力豪,刘艳辉,黄俊宝,等. 基于卷积神经网络的福建省区域滑坡灾害预警模型[J]. 水文地质工程地质,2024,51(1):145 − 153. [DONG Lihao,LIU Yanhui,HUANG Junbao,et al. An early preiction model of regional landslide disasters in Fujian Province based on convolutional neural network[J]. Hydrogeology & Engineering Geology,2024,51(1):145 − 153. (in Chinese with English abstract)]
DONG Lihao, LIU Yanhui, HUANG Junbao, et al. An early preiction model of regional landslide disasters in Fujian Province based on convolutional neural network［J］. Hydrogeology & Engineering Geology, 2024, 51（1）: 145 − 153. （in Chinese with English abstract）
[5] 杨伟东,王再旺,赵涵卓,等. 基于APSO-SVR-GRU模型的白水河滑坡周期项位移预测[J]. 中国地质灾害与防治学报,2022,33(6):20 − 28. [YANG Weidong,WANG Zaiwang,ZHAO Hanzhuo,et al. Displacement prediction of periodic term of Baishuihe landslide based on APSO-SVR-GRU model[J]. The Chinese Journal of Geological Hazard and Control,2022,33(6):20 − 28. (in Chinese with English abstract)]
YANG Weidong, WANG Zaiwang, ZHAO Hanzhuo, et al. Displacement prediction of periodic term of Baishuihe landslide based on APSO-SVR-GRU model［J］. The Chinese Journal of Geological Hazard and Control, 2022, 33（6）: 20 − 28. （in Chinese with English abstract）
[6] 刘莹,杨超宇. 基于多因素的LSTM瓦斯浓度预测模型[J]. 中国安全生产科学技术,2022,18(1):108 − 113. [LIU Ying,YANG Chaoyu. LSTM gas concentration prediction model based on multiple factors[J]. Journal of Safety Science and Technology,2022,18(1):108 − 113. (in Chinese with English abstract)]
LIU Ying, YANG Chaoyu. LSTM gas concentration prediction model based on multiple factors［J］. Journal of Safety Science and Technology, 2022, 18（1）: 108 − 113. （in Chinese with English abstract）
[7] 陶雪杰,徐金明,王树成,等. 使用长短期记忆人工神经网络进行花岗岩变形破坏阶段的判别[J]. 水文地质工程地质,2021,48(3):126 − 134. [TAO Xuejie,XU Jinming,WANG Shucheng,et al. Determination of granite deformation and failure stages using the long short term memory neural network[J]. Hydrogeology & Engineering Geology,2021,48(3):126 − 134. (in Chinese with English abstract)]
TAO Xuejie, XU Jinming, WANG Shucheng, et al. Determination of granite deformation and failure stages using the long short term memory neural network［J］. Hydrogeology & Engineering Geology, 2021, 48（3）: 126 − 134. （in Chinese with English abstract）
[8] 李丽敏,郭伏,温宗周,等. 基于长短时记忆与多影响因子的滑坡位移动态预测[J]. 科学技术与工程,2020,20(33):13559 − 13567. [LI Limin,GUO Fu,WEN Zongzhou,et al. Dynamic prediction of landslide displacement based on long short time memory and multiple influencing factors[J]. Science Technology and Engineering,2020,20(33):13559 − 13567. (in Chinese with English abstract)]
LI Limin, GUO Fu, WEN Zongzhou, et al. Dynamic prediction of landslide displacement based on long short time memory and multiple influencing factors［J］. Science Technology and Engineering, 2020, 20（33）: 13559 − 13567. （in Chinese with English abstract）
[9] 张明岳,李丽敏,温宗周. RNN与LSTM 方法用于滑坡位移动态预测的研究[J]. 人民珠江,2021,42(9):6 − 13. [ZHANG Mingyue,LI Limin,WEN Zongzhou. Research on RNN and LSTM method for dynamic prediction of landslide displacement[J]. Pearl River,2021,42(9):6 − 13. (in Chinese with English abstract)] doi: 10.3969/j.issn.1001-9235.2021.09.002
ZHANG Mingyue, LI Limin, WEN Zongzhou. Research on RNN and LSTM method for dynamic prediction of landslide displacement［J］. Pearl River, 2021, 42（9）: 6 − 13. （in Chinese with English abstract） doi: 10.3969/j.issn.1001-9235.2021.09.002
[10] LI Jiaying, WANG Weidong, HAN Zheng. A variable weight combination model for prediction on landslide displacement using AR model, LSTM model, and SVM model: A case study of the Xinming landslide in China[J]. Environmental Earth Sciences, 2021, 80(10): 386.
[11] 唐宇峰,胡光忠,周帅. 动态残差修正 LSTM 算法的突发型滑坡位移预测[J]. 中国安全科学学报,2023,33(8):109 − 116. [TANG Yufeng,HU Guangzhong,ZHOU Shuai. Displacement prediction of sudden landslide based on dynamic residual correction LSTM algorithm[J]. China Safety Science Journal,2023,33(8):109 − 116. (in Chinese with English abstract)]
TANG Yufeng, HU Guangzhong, ZHOU Shuai. Displacement prediction of sudden landslide based on dynamic residual correction LSTM algorithm［J］. China Safety Science Journal, 2023, 33（8）: 109 − 116. （in Chinese with English abstract）
[12] TENGTRAIRAT N,WOO W L,PARATHAI P,et al. Automated landslide-risk prediction using web GIS and machine learning models[J]. Sensors (Basel),2021,21(13):4620.
[13] 韩丽有,谭钦红,刘家森. 基于CNN-BiLSTM的FMCW雷达生命体征信号检测[J]. 激光杂志,2024,45(3):68 − 73. [HAN Liyou,TAN Qinhong,Llu jiasen. FMCW radar vital sian signal detection based on CNN-BiLSTM[J]. Laser Journal,2024,45(3):68 − 73. (in Chinese with English abstract)]
HAN Liyou, TAN Qinhong, Llu jiasen. FMCW radar vital sian signal detection based on CNN-BiLSTM［J］. Laser Journal, 2024, 45（3）: 68 − 73. （in Chinese with English abstract）
[14] CUI Wenqi,HE Xin,YAO Meng,et al. Landslide image captioning method based on semantic gate and bi-temporal LSTM[J]. ISPRS International Journal of Geo-Information,2020,9(4):194.
[15] WANG Haojie,ZHANG Limin,LUO Hongyu,et al. AI-powered landslide susceptibility assessment in Hong Kong[J]. Engineering Geology,2021,288:106103.
[16] LIN Zian,JI Yuanfa,SUN Xiyan. Landslide displacement prediction based on CEEMDAN method and CNN–BiLSTM model[J]. Sustainability,2023,15(13):10071.
[17] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735 − 1780.
[18] YANG Beibei,YIN Kunlong,LACASSE S,et al. Time series analysis and long short-term memory neural network to predict landslide displacement[J]. Landslides,2019,16(4):677 − 694.
[19] 任远芳,牛坤,丁静,等. 基于改进PSO算法优化SVR的信息安全风险评估研究[J]. 贵州大学学报(自然科学版),2024,41(1):103 − 109. [REN Yuanfang, NIU Kun, DING Jing, et al. Research on information security risk assessment based on improved PSO algorithm to optimize SVR[J]. Journal of Guizhou University (Natural Sciences),2024,41(1):103 − 109. (in Chinese with English abstract)]
REN Yuanfang, NIU Kun, DING Jing, et al. Research on information security risk assessment based on improved PSO algorithm to optimize SVR［J］. Journal of Guizhou University （Natural Sciences）, 2024, 41（1）: 103 − 109. （in Chinese with English abstract）
[20] KALE S. Development of an adaptive neuro-fuzzy inference system (ANFIS) model to predict sea surface temperature (SST)[J]. Oceanological and Hydrobiological Studies,2020,49(4):354 − 373.
-
图(10)
表(1)
计量
- 文章访问数: 28
- PDF下载数: 3
- 施引文献: 0