Landslide susceptibility evaluation based on sample optimization and deep feature extraction

Xu Jinhong; Li Qingquan; Wei Chuntao; Zhao Qin

doi:10.13961/j.cnki.stbctb.2025.02.020

您当前的位置：

首页 >

文章列表页 >

Landslide susceptibility evaluation based on sample optimization and deep feature extraction

- Landslide susceptibility evaluation based on sample optimization and deep feature extraction
- Bulletin of Soiland Water Conservation Vol. 45, Issue 2, Pages: 190-200(2025)
- 作者机构：
  
  重庆交通大学智慧城市学院,重庆,402247
- 作者简介：
- 基金信息：
- DOI：10.13961/j.cnki.stbctb.2025.02.020
  CLC： P642.22
- Online First：16 May 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
Xu Jinhong, Li Qingquan, Wei Chuntao, et al. Landslide susceptibility evaluation based on sample optimization and deep feature extraction[J]. Bulletin of Soiland Water Conservation, 2025, 45(2): 190-200.
DOI：

Xu Jinhong, Li Qingquan, Wei Chuntao, et al. Landslide susceptibility evaluation based on sample optimization and deep feature extraction[J]. Bulletin of Soiland Water Conservation, 2025, 45(2): 190-200. DOI： 10.13961/j.cnki.stbctb.2025.02.020.

摘要

[目的

]

探究滑坡易发性评价中准确的非滑坡样本采样方法和特征提取优异的评价模型，为区域滑坡防控工作提供理论支持和科学指导。[方法

]

在缓冲区采样策略的基础上提出了一种基于卷积自编码器(convolutional auto-encoder，CAE)的非滑坡样本优化方法。该方法通过学习滑坡样本的特征，利用重构误差筛选和优化非滑坡样本。在评价模型方面，引入卷积注意力模块(convolutional block attention module， CBAM)到残差网络(ResNet)中，构建ResNet-CBAM滑坡易发性评价模型，以捕捉更深层次、更复杂且更具代表性的特征。试验以三峡库区重庆市万州区为研究区域，选取高程等12个影响因子，采用SVM，DNN，CNN和ResNet-CBAM 4种模型，对缓冲区采样和基于CAE优化采样的评价精度和结果进行对比分析。[结果

]

在相同评价模型下，基于CAE优化的非滑坡样本采样策略具有更高的可靠性与准确性；在相同采样策略下，ResNet-CBAM模型在准确率、精确率、召回率、F

分数和AUC等指标上均优于其他模型；各模型的评价结果具有相似性，高易发区和极高易发区主要分布在长江沿岸等植被覆盖度低、人类活动频繁的区域，使用了基于CAE优化采样的ResNet-CBAM模型表现出更优的预测效果，更适宜于该区域的滑坡易发性评价研究。[结论

]

万州区滑坡易发性指数较高，区域内存在大量潜在滑坡风险区。基于CAE优化的非滑坡样本采样策略和ResNet-CBAM评价模型能有效提高滑坡易发性评价的精度。

Abstract

[Objective] The efficacy of the non-landslide sampling method and a model with excellent feature extraction in evaluating landslide susceptibility were explored

so as to provide theoretical support and scientific guidance for regional landslide prevention and control work. [Methods] A non-landslide sample optimization method based on Convolutional Auto-Encoder (CAE) was proposed

which was built based on the buffer sampling strategy. This method optimizes non-landslide samples by learning the features of landslide samples and using reconstruction errors. For the evaluation model

the Convolutional Block Attention Module (CBAM) was integrated into the Residual Network (ResNet) to construct the ResNet-CBAM landslide susceptibility model

which captures deeper

and more complex and representative features. Taking the Wanzhou District

Chongqing City in the Three Gorges reservoir area as the study area

12 influencing factors (e.g.

such as elevation) were selected. Four models

namely

SVM

DNN

CNN

and ResNet-CBAM

were used to compare and analyze the evaluation accuracy and results of buffer zone sampling versus CAE-based optimized sampling. [Results] Under the same evaluation model

the CAE-based optimization sampling strategy for non-landslide samples yielded higher reliability and accuracy. Under the same sampling strategy

the ResNet-CBAM model outperformed the other models in terms of accuracy

precision

recall

F1 score

and area under the curve (AUC) values. The evaluation results were similar across models

with higher and very higher susceptibility areas predominantly located in regions with lower vegetation cover and frequent human activity

such as along the Yangtze River. Moreover

the ResNet-CBAM model with CAE-based optimized sampling demonstrated superior prediction results and was more suitable for landslide susceptibility evaluation in this area. [Conclusion] Wanzhou District exhibits a high landslide susceptibility index

with numerous potential landslide risk zones identified within the area. The non-landslide sampling strategy and ResNet-CBAM evaluation model based on CAE optimization can effectively improve the accuracy of landslide susceptibility evaluations.

关键词

Keywords

references

杨延晨,周超,施佳湄.基于卷积神经网络的区域滑坡易发性评价: 以三峡库区万州区为例[J].测绘通报,2023(11):1-6. Yang Yanchen, Zhou Chao, Shi Jiamei. Evaluation of regional landslide susceptibility based on convolutional neural network: A case study of Wanzhou District of Three Gorges reservoir area [J]. Bulletin of Surveying and Mapping, 2023(11):1-6.

Hong Haoyuan, Wang Desheng, Zhu Axing, et al. Landslide susceptibility mapping based on the reliability of landslide and non-landslide sample [J]. Expert Systems with Applications, 2024,243:122933.

胡涛,樊鑫,王硕,等.基于逻辑回归模型和3S技术的思南县滑坡易发性评价[J].地质科技通报,2020,39(2):113-121. Hu Tao, Fan Xin, Wang Shuo, et al. Landslide susceptibility evaluation of Sinan County using logistics regression model and 3S technology [J]. Bulletin of Geological Science and Technology, 2020,39(2):113-121.

Lucchese L V, de Oliveira G G, Pedrollo O C. Investigation of the influence of nonoccurrence sampling on landslide susceptibility assessment using Artificial Neural Networks [J]. CATENA, 2021,198:105067.

周晓亭,黄发明,吴伟成,等.基于耦合信息量法选择负样本的区域滑坡易发性预测[J].工程科学与技术,2022,54(3):25-35. Zhou Xiaoting, Huang Faming, Wu Weicheng, et al. Regional landslide susceptibility prediction based on negative sample selected by coupling information value method [J]. Advanced Engineering Sciences, 2022,54(3):25-35.

Chang Lili, Zhang Rui, Wang Chunsheng. Evaluation and prediction of landslide susceptibility in Yichang section of Yangtze River basin based on integrated deep learning algorithm [J]. Remote Sensing, 2022,14(11):2717.

Kavzoglu T, Sahin E K, Colkesen I. Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression [J]. Landslides, 2014,11(3):425-439.

Okalp K, Akgün H. Landslide susceptibility assessment in medium-scale: Case studies from the major drainage basins of Turkey [J]. Environmental Earth Sciences, 2022,81(8):244.

李达,瞿伟,张勤,等.融合多层感知机和优化支持向量回归的滑坡位移预测模型[J].武汉大学学报(信息科学版),2023,48(08):1380-1388. Li Da,Qu Wei,Zhang Qin,et al. Landslide displacement prediction model by integrating multilayer perceptron and optimized support vector regression [J]. Journal of Wuhan University(Information Science Edition),2023,48(08):1380-1388.

咸利民,季民,刘法军,等.基于CF与优化RF模型耦合的泰山地区地质灾害易发性评价[J].水土保持通报,2024,44(5):134-143. Xian Limin, Ji Min, Liu Fajun, et al. Assessing geological disaster susceptibility in Taishan area by coupling certainty factor model with optimized random forest model [J]. Bulletin of Soil and Water Conservation, 2024,44(5):134-143.

刘伊铭,徐胜华,刘春阳,等.顾及多方法集成特征选择与负样本优化的滑坡易发性评价[J].测绘通报,2024(9):74-79. Liu Yiming, Xu Shenghua, Liu Chunyang, et al. Landslide susceptibility assessment considering multi-method integrated feature selection and negative sample optimization [J]. Bulletin of Surveying and Mapping, 2024(9):74-79.

Sameen M I, Pradhan B, Lee S. Application of con-volutional neural networks featuring Bayesian optimization for landslide susceptibility assessment [J]. Catena, 2020,186:104249.

Thi Ngo P T, Panahi M, Khosravi K, et al. Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran [J]. Geoscience Frontiers, 2021,12(2):505-519.

黄武彪.基于深度学习的大范围滑坡易发性评价: 以青藏高原交通廊道为例[D].陕西西安:长安大学,2023. Huang W B. Deep learning-based assessment of large-scale landslide susceptibility: A case study of transportation corridors on the Tibetan Plateau [D]. Xi’an， Shaanxi: Chang’an University,2023.

鲍帅.基于Vision Transformer的滑坡易发性评价研究[D].辽宁阜新:辽宁工程技术大学, 2023. Bao S. Research on landslide susceptibility evaluation based on Vision Transformer [D]. Fuxin, Liaoning: Liaoning University of Engineering and Technology, 2023.

Nguyen B Q V, Kim Y T. Landslide spatial probability prediction: A comparative assessment of Nave Bayes, ensemble learning, and deep learning approaches [J]. Bulletin of Engineering Geology and the Environment, 2021,80(6):4291-4321.

Karra K, Kontgis C, Statman-Weil Z, et al. Global land use/land cover with Sentinel 2 and deep learning [C]. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium： IEEE, 2021.

Zhang H, Song Y, Xu S, et al. Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: A case study of Wanzhou section of the Three Gorges Reservoir, China[J]. Computers & Geosciences, 2022, 158: 104966.

黄发明,刘科技,曾子强,等.环境因子筛选及组合方法对滑坡易发性预测的影响规律[J].应用基础与工程科学学报,2024,32(1):49-71. Huang Faming, Liu Keji, Zeng Ziqiang, et al. Influence of environmental factor selection and combination on landslide susceptibility prediction modeling [J]. Journal of Basic Science and Engineering, 2024,32(1):49-71.

Yu Lanbing, Cao Ying, Zhou Chao, et al. Landslide susceptibility mapping combining information gain ratio and support vector machines: A case study from Wushan segment in the Three Gorges Reservoir area, China [J]. Applied Sciences, 2019,9(22):4756.

Yang Xin, Liu Rui, Yang Mei, et al. Incorporating landslide spatial information and correlated features among conditioning factors for landslide susceptibility mapping [J]. Remote Sensing, 2021,13(11):2166.

Yi Yaning, Zhang Zhijie, Zhang Wanchang, et al. Landslide susceptibility mapping using multiscale sampling strategy and convolutional neural network: A case study in Jiuzhaigou region [J]. Catena, 2020,195:104851.

Hong Haoyuan, Liu Junzhi, Zhu Axing. Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble [J]. Science of the Total Environment, 2020,718:137231.

田凡凡,薛喜成,郭有金.基于主元分析和信息量模型的滑坡易发性评价: 以丹凤县为例[J].能源与环保,2021,43(8):6-12. Tian Fanfan, Xue Xicheng, Guo Youjin. Evaluation of landslide susceptibility based on principal component analysis and information model: Taking Danfeng County as an example [J]. China Energy and Environmental Protection, 2021,43(8):6-12.

Wang Yi, Fang Zhice, Hong Haoyuan. Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China [J]. Science of the Total Environment, 2019,666:975-993.

Yang Zhiqiang, Xu Chong, Shao Xiaoyi, et al. Landslide susceptibility mapping based on CNN-3D algorithm with attention module embedded [J]. Bulletin of Engineering Geology and the Environment, 2022,81(10):412.

赵会芹.基于不同空间分辨率遥感影像的滑坡提取方法研究[D].广西桂林:桂林电子科技大学,2023. Zhao Huiqin. Research on landslide extraction methods based on remote sensing images with different spatial resolutions [D]. Guilin, Guangxi: Guilin University of Electronic Science and Technology, 2023.

Yang Zhiqiang, Xu Chong, Li Lei. Landslide detection based on ResU-net with transformer and CBAM embedded: Two examples with geologically different environments [J]. Remote Sensing, 2022,14(12):2885.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Effects of land use and climate change on water-related ecosystem services in Hebei Province

Soil-water characteristics and softening constitutive model of lime-stabilized loess

Influence of vegetation blanket coverage on thermal properties of coal gangue substrate in alpine mining areas

Effects of vegetation restoration duration on runoff and sediment yield in slopes of waste dumps in alpine mining areas

Research status and hotspots of plant diversity in desertified areas of China based on CiteSpace

Related Author

No data

Related Institution

No data

⁰