[1]王继波,张智纲,邵景干,等.公路滑坡预警中的多模态数据融合与评估模型优化研究*[J].中国安全生产科学技术,2025,21(9):184-190.[doi:10.11731/j.issn.1673-193x.2025.09.023]
WANG Jibo,ZHANG Zhigang,SHAO Jinggan,et al.Research on multimodal data fusion and evaluation model optimization in highway landslide early warning[J].Journal of Safety Science and Technology,2025,21(9):184-190.[doi:10.11731/j.issn.1673-193x.2025.09.023]
点击复制
公路滑坡预警中的多模态数据融合与评估模型优化研究*
WANG Jibo,ZHANG Zhigang,SHAO Jinggan,et al.Research on multimodal data fusion and evaluation model optimization in highway landslide early warning[J].Journal of Safety Science and Technology,2025,21(9):184-190.[doi:10.11731/j.issn.1673-193x.2025.09.023]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 21
- 期数:
- 2025年9期
- 页码:
- 184-190
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2025-09-30
文章信息/Info
- Title:
- Research on multimodal data fusion and evaluation model optimization in highway landslide early warning
- 文章编号:
- 1673-193X(2025)-09-0184-07
- Keywords:
- highway slope; landslide risk; multimodal data fusion; risk assessment; early warning methods
- 分类号:
- X951
- 文献标志码:
- A
- 摘要:
- 为了及时准确评估和预警公路边坡滑坡风险，保障公路交通基础设施安全与运营效率，通过改进的DRNN卷积神经网络模型，整合地形地貌、水文条件、土壤植被等10个影响因素，提出1种多模态数据融合的公路滑坡风险评估与预警方法。该方法聚焦公路滑坡的多因素耦合影响规律，在传统DRNN卷积神经网络中替换主干网络、引入注意力机制、增设条形池分支模块，强化模型对公路滑坡关键风险因素及其交互关系的学习。研究结果表明：改进的DRNN卷积神经网络可融合多模态滑坡风险因素评估与预测公路滑坡风险，评估精度高于传统DRNN卷积神经网络的评估预测，且准确率、召回率、精确度以及F值更高，在公路滑坡风险评估预警过程中具有更强的泛化能力。研究结果可为公路滑坡风险的监测预警提供方法支撑。
- Abstract:
- In order to enable timely and accurate assessment and early warning of highway slope landslide risks,thereby ensuring the safety and operational efficiency of highway transportation infrastructure,this study proposed a multimodal data fusion approach for landslide risk assessment and early warning.By improving the Deep Random Neural Network (DRNN) convolutional neural network model,the method integrates ten influencing factors—including topography,hydrological conditions,and soil vegetation—to reveal the coupled effects of multiple factors on highway landslides.Specifically,the traditional DRNN convolutional neural network is enhanced by replacing its backbone network,introducing an attention mechanism,and adding a strip pooling branch module to strengthen the model’s ability to learn key risk factors and their interactions.The results demonstrate that the improved DRNN convolutional neural network effectively fuses multimodal landslide risk factors for assessing and predicting highway landslide risks.The improved DRNN convolutional neural network can integrate multimodal landslide risk factor assessment and prediction of highway landslide risk,with higher evaluation accuracy than traditional DRNN convolutional neural networks,and higher accuracy,recall,precision,and F-value.It has stronger generalization ability in the process of highway landslide risk assessment and early warning.These findings provide methodological support for monitoring and early warning of highway landslide risks.
参考文献/References:
［1］李洁,张欣宇,朱全军,等.滑坡灾害影响下高速公路网络鲁棒性分析［J］.湖南大学学报(自然科学版),2025,52(1):176-186.
LI Jie,ZHANG Xinyu,ZHU Quanjun,et al.Robustness analysis of expressway network under influence of landslide disasters［J］.Journal of Hunan University (Natural Sciences),2025,52(1):176-186.
［2］宋亚兵,贺拿,胡桂胜,等.川藏公路朗嘎村冲沟型泥石流形成演化机制与防治模式［J］.成都理工大学学报(自然科学版),2022,49(6):739-750.
SONG Yabing,HE Na,HU Guisheng,et al.Formation evolution mechanism and control model of gully debris flow in Langga Village of Sichuan-Tibet Highway［J］.Journal of Chengdu University of Technology (Science & Technology Edition),2022,49(6):739-750.
［3］王世宝,庄建琦,郑佳,等.基于深度学习的CZ铁路康定—理塘段滑坡易发性评价［J］.工程地质学报,2022,30(3):908-919.
WANG Shibao,ZHUANG Jianqi,ZHENG Jia,et al.Landslide susceptibility evaluation based on deep learning along kangding-litang section of CZ railway［J］.Journal of Engineering Geology,2022,30(3):908-919.
［4］胡致远，罗文强，晏鄂川，等.基于改进层次分析法的英山县地质灾害易发性评价［J］.安全与环境工程，2018,25(4):28-32.
HU Zhiyuan,LUO Wenqiang,YAN Echuan,et al.IAHP-based evaluation of susceptibility of geological hazards in Yingshan County［J］.Safety and Environmental Engineering,2018,25(4):28-32.
［5］杨昭颖,韩灵怡,郑向向,等.基于卷积神经网络的遥感影像及DEM滑坡识别——以黄土滑坡为例［J］.自然资源遥感,2022,34(2):224-230.
YANG Zhaoying,HAN Lingyi,ZHENG Xiangxiang,et al.Landslide identification using remote sensing images and DEM based on convolutional neural network:a case study of loess landslide［J］.Remote Sensing for Natural Resources,2022,34(2):224-230.
［6］吴润泽,胡旭东,梅红波,等.基于随机森林的滑坡空间易发性评价：以三峡库区湖北段为例［J］.地球科学,2021,46(1):321-330.
WU Runze,HU Xudong,MEI Hongbo,et al.Spatial susceptibility assessment of landslides based on random forest:a case study from Hubei section in the Three Gorges Reservoir area［J］.Earth Science,2021,46(1):321-330.
［7］徐乔,余飞,余绍淮.基于多源遥感数据的山区铁路滑坡危险性评价［J］.铁道工程学报,2021,38(11):8-14.
XU Qiao,YU Fei,YU Shaohuai.Landslide hazard assessment of mountain railways based on multi-source remote sensing data［J］.Journal of Railway Engineering Society,2021,38(11):8-14.
［8］CHENG H,FANG L,LEI W,et al.Landslide susceptibility modeling using a deep random neural network［J］.Applied Sciences,2022,12(24):12887-12887.
［9］AZARAFZA,M,AZARAFZA M,AKGUN H,et al.Deep learning-based landslide susceptibility mapping［J］.Scientific Reports,2021(11):1-16.
［10］XU S L,NIU R Q,Displacement prediction of baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in three gorges area,China［J］.Computers & Geosciences,2018,111,87-96.
［11］LE C Y,BENGIO Y,HINTON G.Deep learning［J］.Nature,2015,521:436-444.
［12］LI W J,FANG Z.C,WANG Y.Stacking ensemble of deep learning methods for landslide susceptibility mapping in the three gorges reservoir area,China［J］.Stochastic Environmental Research and Risk Assessment,2022,36:2207-2228.
［13］CHENG H,FANG L,LEI W,et al.Landslide susceptibility modeling using a deep random neural network［J］.Applied Sciences,2022,12(24):12887-12887.
［14］高明,李虎,刘鑫锦,等.基于距离-属性混合聚类结合ConvLSTM模型的岩溶地层地下水预测方法［J］.科学技术与工程,2025,25(20):8424-8434.
GAO Ming,LI Hu,LIU Xinjin,et al.Prediction method of groundwater in karst strata based on distance-attribute hybrid clustering combined with ConvLSTM Model［J］.Science Technology and Engineering,2025,25(20):8424-8434.
［15］CHAUDHARI S,MITHAL V,POLATKAN G,et al.An attentive survey of attention models［J］.ACM Transactions on Intelligent Systems and Technology,2021,12(5):1-32.
［16］李旺平,尉文博,刘晓杰,等.基于改进DeepLabV3+算法的遥感影像滑坡识别［J］.地球信息科学学报,2025,27(6):1448-1461.
LI Wangping,WEI Wenbo,LIU Xiaojie,et al.Landslide detection in remote sensing image using an improved DeepLabV3 + Algorithm［J］.Geo-Information Science,2025,27(6):1448-1461.
［17］周华平,邓彬.融合多层次特征的DeepLabv3+轻量级图像分割算法［J］.计算机工程与应用,2024,60(16):269-275.
ZHOU Huaping,DENG Bin.DeepLabv3+ lightweight image segmentation algorithm based on multilevel feature fusion［J］.Computer Engineering and Applications,2024,60(16):269-275.
［18］张华,康晓莉,彭淑惠,等.云贵高原典型串珠状岩溶湿地水文地质演化研究［J］.中国岩溶,2022,41(4):532-541.
ZHANG Hua,KANG Xiaoli,PENG Shuhui,et al.Hydrogeological evolution of typical moniliform karst wetlandin the Yunnan-Guizhou Plateau［J］.Carsologica Sinica,2022,41(4):532-541.
［19］NGUYEN D D,NGUYEN D M,NGUYEN V T,et al.Enhanced landslide spatial prediction using hybrid deep learning model and SHAP analysis:A case study of the tuyen quang-ha giang expressway,vietnam［J］.Journal of the Indian Society of Remote Sensing,2024,53(5):1-20.
［20］VIET N T,NGUYEN D D,DUC N M,et al.Exploring deep learning models for roadside landslide prediction:insights and implications from comparative analysis［J］.Physics and Chemistry of the Earth,2024,136:103741.
［21］LIMING X,YONGHONG Z,GONGZHUANG P.Landslide susceptibility assessment using integrated deep learning algorithm along the China-Nepal Highway.［J］.Sensors (Basel,Switzerland),2018,18(12):4436-4436.
［22］王守华,王睿菘,孙希延,等.基于CF-CNN-LSTM模型的滑坡易发性评价［J］.自然灾害学报,2024,33(5):84-95.
WANG Shouhua,WANG Ruisong,SUN Xiyan,et al.Landslide susceptibility evaluation based on CF-CNN-LSTM model［J］.Journal of Natural Disasters,2024,33(5):84-95.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2025-07-31
* 基金项目： 河南省交通运输厅科技项目（2021J4）
作者简介： 王继波，硕士，高级工程师，主要研究方向为公路与桥梁工程。
