[1]薛洪文,苏俊武,孙银锁,等.基于多源数据地质灾害监测预警应用研究[J].华南地震,2026,46(01):53-61.[doi:10.13512/j.hndz.2026.01.07]
　XUE Hongwen,SU Junwu,SUN Yinsuo,et al.Research on the Application of Geological Hazard Monitoring and Early Warning Based on Multi Source Data[J].,2026,46(01):53-61.[doi:10.13512/j.hndz.2026.01.07]
点击复制

基于多源数据地质灾害监测预警应用研究()

华南地震[ISSN:1006-6977/CN:61-1281/TN]

卷:
46
期数:
2026年01期
页码:
53-61
栏目:
地震与地质灾害
出版日期:
2026-01-31

文章信息/Info

Title:
Research on the Application of Geological Hazard Monitoring and Early Warning Based on Multi Source Data
文章编号:
1001-8662（2026）01-0053-09
作者:
薛洪文; 苏俊武; 孙银锁; 冯待飞; 王永成
中国冶金地质总局第三地质勘查院，太原 030000
Author(s):
XUE Hongwen; SU Junwu; SUN Yinsuo; FENG Daifei; WANG Yongcheng
The Third Geological Exploration Institute ， China Metallurgical Geology Bureau ， Taiyuan 030000， China
关键词:
多源数据融合; 预警模型; DKSVM; 地质监测; 地质灾害; 监测预警
Keywords:
Multi-source data fusion;  Early warning model;  DKSVM;  Geological monitoring;  Geological haz?ards; Monitoring and early warning
分类号:
P627；P694
DOI:
10.13512/j.hndz.2026.01.07
文献标志码:
A
摘要:
为提升多源数据在地质灾害监测预警中的应用能力，此研究构建了融合无人机摄影、地质传感器、卫星遥感等多源数据的监测预警系统。通过计算数据相似度并设定0.8的融合阈值，对未达标的数据采用5×5卷积核的三层卷积神经网络提取特征并二次融合，解决了多源异构数据的一致性问题。同时，提出深度核支持向量机（DKSVM）模型，利用深度学习自动提取地形坡度、土壤湿度等高阶特征关联，结合支持向量机的结构化风险最小化原理实现分类预测。试验选取滑坡、泥石流、地面塌陷等9类地质灾害与文献[3]~[4]的预警模型进行对比，结果表明：在滑坡、泥石流、地面塌陷等9类地质灾害中本研究系统的灾害预测准确率达98.7%，相较于对比文献效果显著提升，其中滑坡、泥石流等灾害类型的F1值均超过97.6%。数据融合后有效信息占比从65%提升至92%，平均相似度达0.89，验证了模型在复杂地质环境下的鲁棒性与泛化能力，为智能化地质灾害预警提供了技术参考。
Abstract:
To enhance the application capability of multi-source data in geological hazard monitoring and early warning， this study constructed a monitoring and early warning system that integrates multi-source data such as UAV photography， geological sensors， satellite remote sensing and other multi-source data. By calculating data similarity and setting a fusion threshold of 0.8，the system employs a three-layer convolutional neural network with 5×5 convolutional kernel to extract features and performs secondary fusion on data that does not meet the standard， addressing the consistency issue of multi-source heterogeneous data. Additionally，a deep kernel support vector ma chine（DKSVM）model is proposed，which utilizes deep learning to automatically extract high-order feature associa tions such as terrain slope and soil moisture， and combines the structured risk minimization principle of support vector machine to achieve classification prediction. The study selected nine types of geological hazards，including landslides，debris flows，and ground subsidence，and compared them with the early warning models in referenc es [3]to[4]. The results indicate that among the nine types of geological disasters such as landslide，debris flow and ground subsidence， the accuracy of disaster prediction of this system reached 98.7%， which is significantly im proved compared with the comparison literature，with F1 values for landslide，debris flow and other disaster types exceeding 97.6%. After data fusion，the proportion of effective information increased from 65 % to 92 %，with an average similarity of 0.89，verifying the robustness and generalization ability of the model in complex geological en vironments，and providing a technical reference for intelligent geological disaster early warning.

参考文献/References:

[1]李晓萌,陈天,徐玮铎,等.基于数字孪生的海底地质灾害监测预警技术研究[J].中国海洋大学学报(自然科学版), 2024,54(05):102-114.
[2]王新龙,车子杰,马飞,等.基于PS-InSAR技术的晋城矿区地表形变监测及地质灾害风险预警[J].安全与环境工程,2024,31(02):173-179+212.
[3] Zhang G,Liu X,Zheng F,et al. Geological disaster informa?tion sharing based on Internet of Things standardization[J/OL].Environmental Earth Sciences,2024,148(83).
[4] Ding X,Hu W. Advancements in geological disaster monitor?ing and early warning systems:A deep learning and comput?er vision approach[J]. Traitement du Signal,2023,40(3):1195-1202.
[5]蔡嘉伦.面向滑坡动态监测预警的星地InSAR时序建模与解算方法[J].测绘学报,2024,53(01):201.
[6]左小清,张荐铭,李勇发,等.典型山区InSAR地表形变监测与滑坡灾害识别[J].昆明理工大学学报(自然科学版), 2024,49(04):89-104.
[7]李龙,苗程广,李响,等.高精度BDS+GPS变形监测技术在特高压线路地质害监测中的应用[J].测绘通报,2024(03):140-144.
[8]杨豹,赵瑞志,王海波,等.遥感技术对地质灾害早期识别和动态监测——以昌波乡至羊拉乡段为例[J].科学技术与工程,2024,24(05):1823-1836.
[9]曾宪海.铁路地质灾害防控面临的挑战与对策[J].中国铁路,2024(01):7-14.
[10]覃事河,段斌,周相,等.水电工程地质灾害实时监测预警系统设计及应用[J].人民长江,2023,54(10):105-112.
[11]朱万成,徐晓冬,李磊,等.金属矿山地质灾害风险智能监测预警技术现状与展望[J].金属矿山,2024(01):20-44.
[12]张少鹏,刘晓磊,程光伟,等.海底碳封存环境地质灾害风险及监测技术研究[J].中国工程科学,2023,25(03):122-130.
[13]刘金沧,王欢欢,李云,等.基于支持向量机的华南斜坡类地质灾害易发性评价:以肇庆市怀集县为例[J].时空信息学报,2024,31(06):785-794.
[14]刘金沧,王欢欢,李云,等.基于支持向量机的华南斜坡类地质灾害易发性评价:以肇庆市怀集县为例[J].时空信息学报,2024,31(06):785-794.
[15]朱俊清,赵学儒,马涛,等.基于卫星遥感的路域地质灾害监测方法[J].吉林大学学报(工学版),2023,53(06):1861-1872.
[16]孙琪皓,刘桂卫,王飞,等.铁路地质灾害早期识别与监测预警技术及应用研究[J].铁道标准设计,2024,68(09):24-31.
[17] Shao W,Nie W,Ni J . Research on landslide hydrology and hydrogeological disaster monitoring[J].Water,2023,15(10):1910.
[18] Huang H,Ju S,Duan W,et al. Landslide monitoring along the Dadu River in Sichuan based on Sentinel-1 multi-temporal InSAR.[J]. Sensors(Basel,Switzerland),2023,23 (7):3383.
[19]王周兵,张玮鹏,胡义,等.孤山库区地质灾害自动化监测与信息化防治研究[J].人民长江,2022,53(S2):202-206.

备注/Memo

备注/Memo:
收稿日期：2025-01-11
作者简介：薛洪文（1985-），男，测绘高级工程师，主要从事测绘工程。E-mail：shui8688@126.com
更新日期/Last Update: 2026-02-03