融合时序InSAR与PSO-SVM模型的滑坡易发性评价

doi:10.13474/j.cnki.11-2246.2025.1111

测绘通报 ›› 2025, Vol. 0 ›› Issue (11): 70-77,123.doi: 10.13474/j.cnki.11-2246.2025.1111

融合时序InSAR与PSO-SVM模型的滑坡易发性评价

尚雪巍¹, 杨瑞², 陈裕汉³, 高伏芳⁴

1. 甘肃省张掖市自然资源局, 甘肃张掖 734000;
2. 昆明理工大学国土资源工程学院, 云南昆明 650093;
3. 滇西应用技术大学地球科学与工程学院, 云南大理 671009;
4. 云南南方地勘工程有限公司, 云南大理 671009

收稿日期:2025-05-21 发布日期:2025-12-04
通讯作者: 杨瑞。E-mail:2057638985@qq.com
作者简介:尚雪巍(1974—),男,高级工程师,主要从事自然资源调查、遥感监测、工程测量等工作。E-mail:1363910891@qq.com
基金资助:
国家自然科学基金地区基金项目(41961053)

Evaluation of landslide susceptibility by integrating time-series InSAR and PSO-SVM models

SHANG Xuewei¹, YANG Rui², CHEN Yuhan³, GAO Fufang⁴

1. Zhangye Municipal Bureau of Natural Resources, Zhangye 734000, China;
2. Faculty of land and Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China;
3. School of Earth Science and Engineering, West Yunnan University of Applied Sciences, Dali 671009, China;
4. Yunnan Southern Geological Exploration Engineering Co., Ltd., Dali 671009, China

Received:2025-05-21 Published:2025-12-04

摘要/Abstract

摘要： 针对现有滑坡编目更新不及时,以及滑坡评价过程中缺乏动态因子等问题,本文以云南省弥渡县为例,利用SBAS-InSAR技术获取升降轨地表形变信息,结合高分辨率光学影像、坡度等进行滑坡识别,更新现有滑坡编目。并在坡度、坡向等13个静态因子的基础上,引入地表形变速率作为动态因子,基于PSO-SVM模型开展滑坡易发性评价。结果表明:①研究区升降轨监测结果无论是在形变速率上,还是形变区域上都具有明显差异,而这主要与卫星轨道几何差异及地形特征等因素有关。②联合升降轨数据可有效克服单轨数据带来的局限性,从而提高滑坡识别的全面性和准确性。③融入动态因子的滑坡评价结果精度更高,其AUC、精确率、召回率和F1分数分别为0.886、0.847、0.851和0.855。该方法可为弥渡县滑坡防控预警提供一定参考。

关键词: 滑坡易发性评价, SBAS-InSAR, PSO-SVM模型, 弥渡县

Abstract: To address the issues of outdated landslide inventories and the lack of dynamic factors in the landslide susceptibility assessment process,this study takes Midu county,Yunnan province,as a case study.Surface deformation information from ascending and descending orbits was retrieved using the SBAS-InSAR technique.Combined with high-resolution optical imagery and slope data,landslides were identified to update the existing landslide inventory.In addition,based on 13 static conditioning factors such as slope and aspect,surface deformation rate was introduced as a dynamic factor,and a PSO-SVM model was employed to conduct landslide susceptibility assessment.The results indicate that:①The monitoring results from ascending and descending orbit in the study area exhibit significant differences both in deformation rates and in the spatial extent of deformation.These discrepancies are primarily attributed to variations in satellite orbit geometry as well as local topographic characteristics;②Integrating ascending and descending orbit datasets effectively overcomes the limitations of single-orbit observations,thereby improving the comprehensiveness and accuracy of landslide identification;③Incorporating dynamic factors yields higher assessment accuracy,with AUC,precision,recall,and F1-score reaching 0.886,0.847,0.851,and 0.855,respectively.This approach provides valuable reference for landslide prevention and early warning in Midu county.

Key words: landslide susceptibility assessment, SBAS-InSAR, PSO-SVM model, Midu county

中图分类号:

P237

尚雪巍, 杨瑞, 陈裕汉, 高伏芳. 融合时序InSAR与PSO-SVM模型的滑坡易发性评价[J]. 测绘通报, 2025, 0(11): 70-77,123.

SHANG Xuewei, YANG Rui, CHEN Yuhan, GAO Fufang. Evaluation of landslide susceptibility by integrating time-series InSAR and PSO-SVM models[J]. Bulletin of Surveying and Mapping, 2025, 0(11): 70-77,123.

参考文献

[1] 许强,陆会燕,李为乐,等.滑坡隐患类型与对应识别方法[J].武汉大学学报(信息科学版),2022,47(3): 377-387.
[2] 翁铭锴,肖桂荣.训练样本采样优化与机器学习结合的滑坡易发性评价方法[J].地球信息科学学报,2025,27(5): 1113-1128.
[3] 朱阿兴,裴韬,乔建平,等.基于专家知识的滑坡危险性模糊评估方法[J].地理科学进展,2006,25(4): 1-12,137.
[4] REICHENBACH P,ROSSI M,MALAMUD B D,et al.A review of statistically-based landslide susceptibility models[J].Earth-Science Reviews,2018,180: 60-91.
[5] ACHU A L,AJU C D,DI NAPOLI M,et al.Machine-learning based landslide susceptibility modelling with emphasis on uncertainty analysis[J].Geoscience Frontiers,2023,14(6): 101657.
[6] 宋雨洋,郝利娜,严丽华,等.支持向量机在滑坡识别中的应用[J].兰州大学学报(自然科学版),2022,58(6): 727-734.
[7] FREITAS D,LOPES L G,MORGADO-DIAS F.Particle swarm optimisation: a historical review up to the current developments[J].Entropy,2020,22(3): 362.
[8] ZHAO Shuai,ZHAO Zhou.A comparative study of landslide susceptibility mapping using SVM and PSO-SVM models based on grid and slope units[J].Mathematical Problems in Engineering,2021,2021(1): 8854606.
[9] KONG Chunfang,TIAN Yiping,MA Xiaogang,et al.Landslide susceptibility assessment based on different MaChine learning methods in Zhaoping County of eastern Guangxi[J].Remote Sensing,2021,13(18): 3573.
[10] OSMANO㊣LU B,SUNAR F,WDOWINSKI S,et al.Time series analysis of InSAR data: methods and trends[J].ISPRS Journal of Photogrammetry and Remote Sensing,2016,115: 90-102.
[11] 郭瑞,李素敏,陈娅男,等.基于SBAS-InSAR的矿区采空区潜在滑坡综合识别方法[J].地球信息科学学报,2019,21(7): 1109-1120.
[12] 张诗茄,蒋建军,缪亚敏,等.基于SBAS技术的岷江流域潜在滑坡识别[J].山地学报,2018,36(1): 91-97.
[13] 黄小龙,吴中海,吴坤罡.滇西北弥渡地区主要断裂晚新生代发育特征及其动力学机制[J].地质力学学报,2021,27(6): 913-927.
[14] BERARDINO P,FORNARO G,LANAR㊣I R,et al.A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(11): 2375-2383.
[15] CASU F,MANZO M,LANARI R.A quantitative assessment of the SBAS algorithm performance for surface deformation retrieval from DInSAR data[J].Remote Sensing of Environment,2006,102(3/4): 195-210.
[16] YU Haihua,CAI Guolin,GAN Quan,et al.Early identification of the jiangdingya landslide of Zhouqu based on SBAS-InSAR technology[J].Earthquake Research in China,2020,34(4): 510-522.
[17] 郭乐萍,岳建平,岳顺.基于SARscape的InSAR数据相位解缠方法研究[J].地理空间信息,2018,16(3): 20-22,8.
[18] 安雪莲,密长林,孙德亮,等.基于不同评价单元的三峡库区滑坡易发性对比: 以重庆市云阳县为例[J].吉林大学学报(地球科学版),2024,54(5): 1629-1644.
[19] 周定义,左小清,喜文飞,等.联合SBAS-InSAR和PSO-BP算法的高山峡谷区地质灾害危险性评价[J].农业工程学报,2021,37(23): 108-116.
[20] 喜文飞,成鑫,杨志全,等.基于SBAS-InSAR技术和BP神经网络的高位远程滑坡危险性分析研究[J].昆明理工大学学报(自然科学版),2024,49(3):65-74.
[21] 薛凯凯,熊礼阳,祝士杰,等.基于DEM的黄土崾岘提取及其地形特征分析[J].地球信息科学学报,2018,20(12): 1710-1720.
[22] CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20(3): 273-297.
[23] SEYDI S T,KANANI-SADAT Y,HASANLOU M,et al.Comparison of machine learning algorithms for flood susceptibility mapping[J].Remote Sensing,2023,15(1): 192.
[24] 武雪玲,沈少青,牛瑞卿.GIS支持下应用PSO-SVM模型预测滑坡易发性[J].武汉大学学报(信息科学版),2016,41(5): 665-671.
[25] 张雪,魏云杰,杨成生,等.云南昭通地区滑坡隐患InSAR广域识别与监测[J].地球科学与环境学报,2025,47(1): 128-142.
[26] 陈兴珍,蒋楠,周家文.基于时序InSAR的理县清流村滑坡二维变形特征与影响因素研究[J].水利水电技术(中英文),2024,55(8): 127-140.
[27] 万灿.结合SBAS-InSAR与机器学习的滑坡易发性评价[D].重庆: 重庆交通大学,2023.
[28] HE Yi,WANG Wenhui,ZHANG Lifeng,et al.An identification method of potential landslide zones using InSAR data and landslide susceptibility[J].Geomatics,Natural Hazards and Risk,2023,14(1):2185120.
[29] 孙焱焱,朱纪朋,郭国,等.考虑InSAR形变速率的区域滑坡易发性评价[J].自然灾害学报,2024,33(3): 178-190.
[30] 肖波,赵良军,郑莉萍,等.融合时序InSAR与多因子耦合模型的长宁县滑坡灾害易发性评价[J].自然灾害学报,2025,34(1): 117-126.

融合时序InSAR与PSO-SVM模型的滑坡易发性评价

Evaluation of landslide susceptibility by integrating time-series InSAR and PSO-SVM models

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	莫丹丹, 火久元. 基于SBAS-InSAR技术的喀喇昆仑公路盖孜河谷段形变监测与影响因子分析[J]. 测绘通报, 2025, 0(8): 32-42.
[2]	李若凡, 李勇发, 左小清, 黄成, 邢明泽, 李永宁, 张荐铭, 石超, 顾晓娜. 兰坪县InSAR形变监测与滑坡灾害早期识别[J]. 测绘通报, 2025, 0(7): 40-45.
[3]	李文东, 叶禹, 李霞, 魏伟, 辛存林. 融合SBAS-InSAR形变与机器学习模型的滑坡易发性评价[J]. 测绘通报, 2025, 0(7): 126-131,146.
[4]	王身丽, 刘毅, 韩昊, 杜勇. 联合SBAS-InSAR和DS-InSAR的特高压输电通道形变监测与预测[J]. 测绘通报, 2025, 0(6): 130-135,141.
[5]	汪晨煜, 彭军还, 薛跃明, 李旭, 张炎. 融合InSAR与信息量-逻辑回归耦合模型的滑坡动态危险性评价[J]. 测绘通报, 2025, 0(6): 43-48.
[6]	尚依炜, 熊俊楠, 贾倩, 罗思远, 王启盛, 曹依帆. 融合升降轨SBAS-InSAR技术的冕宁县滑坡隐患识别与分析[J]. 测绘通报, 2025, 0(4): 58-62.
[7]	杨洋, 贾洪果, 柏铮航, 刘宇辰. 联合机器学习与SBAS-InSAR的青藏高原冻土形变监测[J]. 测绘通报, 2025, 0(4): 45-50.
[8]	周天翔, 董景龙, 沈强. 基于SBAS-InSAR技术的济南市地铁沿线地表沉降时空分析[J]. 测绘通报, 2025, 0(4): 109-113.
[9]	邵亚璇, 马晶, 韩莉莉, 姚冠宇. 基于SBAS-InSAR技术的地表沉降时间序列分析与预测[J]. 测绘通报, 2025, 0(4): 51-57,62.
[10]	张昱鑫, 袁希平, 甘淑, 彭翔, 王松. 时序InSAR技术在矿区地表沉降监测与时空演化分析中的应用[J]. 测绘通报, 2025, 0(3): 15-20.
[11]	彭毅博, 杨维芳, 闫香蓉, 高墨通, 侯宇豪, 张德龙. 基于SMA-CNN-GRU-Attention组合模型的矿区地表三维形变预测[J]. 测绘通报, 2025, 0(3): 8-14,20.
[12]	严胜航, 李素敏, 郭军, 宋昱霏, 沈显名. 基于多源遥感的巨型滑坡四维特征解译——以糯勒滑坡为例[J]. 测绘通报, 2025, 0(2): 48-52,63.
[13]	沈显名, 李素敏, 郭军, 毛嘉骐, 严胜航, 戴祚敏, 彭翔. 基于坡向约束的高寒矿区边坡InSAR三维形变分析[J]. 测绘通报, 2025, 0(2): 77-82.
[14]	李春意, 郭亚星, 丁来中, 崔希民, 郑月松. 特高压输电通道地表形变解译及杆塔受损定量评价[J]. 测绘通报, 2025, 0(11): 8-14.
[15]	颜丙囤, 殷海涛, 杨玉永, 连凯旋, 温丽媛, 郭宗斌. InSAR数据约束的沂沭断裂带闭锁程度及地震危险性分析[J]. 测绘通报, 2024, 0(7): 129-133.