融合多源特征的轻量化深度学习跨场景滑坡智能识别

doi:10.3799/dqkx.2025.255

融合多源特征的轻量化深度学习跨场景滑坡智能识别

doi: 10.3799/dqkx.2025.255

邢珂¹,
窦杰^1,2,3, ,,
何雨健⁴,
晏培修⁵,
杨涛^3,6,
李喜^3,6,
董傲男²

1. 中国地质大学未来技术学院, 湖北武汉 430074;
2. 中国地质大学湖北巴东地质灾害国家野外科学观测研究站, 湖北武汉 430074;
3. 资源与生态环境地质湖北省重点实验室(湖北省地质局), 湖北武汉 430034;
4. 中国电建集团成都勘测设计研究院有限公司, 四川成都 610072;
5. 成都理工大学计算机与网络安全学院, 四川成都 610059;
6. 湖北省地质环境总站, 湖北武汉 430034

基金项目:

国家自然科学基金面上项目(No.42477170)

国家自然科学基金重大项目(No.42090054)

资源与生态环境地质湖北省重点实验室开放基金项目(HBREGKFJJ-202411)

详细信息

作者简介:
邢珂(1999-),男,博士研究生,主要从事地质灾害智能识别与风险评估,E-mail:xingke@cug.edu.cn,ORCID:https://orcid.org/0009-0000-4838-8831

通讯作者:
窦杰(1981-),男,博导,研究员,主要从事地质灾害大数据智能管控及机理演化研究。E-mail:doujie@cug.edu.cn

中图分类号: P642.22
计量
- 文章访问数: 87
- HTML全文浏览量: 0
- PDF下载量: 5
- 被引次数: 0
出版历程
- 收稿日期: 2025-05-01
- 网络出版日期: 2025-12-03

Lightweight Deep Learning for Cross-Scene Landslide Intelligent Recognition with Multi-Source Feature Fusion

XING Ke¹,
DOU Jie^{1,2,3
, ,},
HE Yujian⁴,
YAN Peixiu⁵,
YANG Tao^3,6,
LI Xi^3,6,
DONG Aonan²

1. School of Future Technology, China University of Geosciences, Wuhan 430074, China;
2. Badong National Observation and Research Station of Geohazards, China University of Geosciences, Wuhan 430074, China;
3. Hubei Key Laboratory of Resources and Eco-Environment Geology(Hubei Geological Bureau), Wuhan, 430034, China;
4. Chengdu Engineering Corporation Limited, Power Construction Corporation, Chengdu 610072, China;
5. College of Computers and Cyber Security, Chengdu University of Technology, Chengdu 610059, China;
6. Geological Environmental Center of Hubei Province, Wuhan 430034, China

摘要

摘要: 极端环境因素影响下诱发的区域性滑坡对生命财产安全构成严重威胁。因此，推进区域性滑坡识别的自动化，提升复杂地形下隐患区域的信息透明度，对地质灾害数据库建设和风险管理至关重要。深度学习方法提供了有效的解决方案，克服了传统方法自动化程度不足的问题。然而，现有研究多侧重于模型结构优化与训练策略改进，在多源地形数据的有效融合与跨区域识别能力提升方面仍存在挑战。针对上述瓶颈，本文提出了一种具有跨区域识别能力的深度学习ResU-CBNet模型。该模型将空间和通道混合的注意力机制融入神经网络模型，并采用残差网络替换原有普通网络结构。模型在多尺度特征融合条件下的性能显著优于单一遥感数据，具体表现为PA、CPA、F1＿Score、MIoU分别提升2.1%、2.6%、6.9%、2.9%；同时，模型在不同场景、不同光谱波段和空间分布的区域中验证了其跨场景泛化能力，PA和F1＿Score分别达到了92.8%、91.3%和83.2%、80.0%的性能，识别效果与实际区域高度吻合。本文提出的跨场景的识别方法可为滑坡智能识别和风险评估提供一定的参考。
- 深度学习 /
- 多源数据 /
- 注意力机制 /
- 滑坡识别 /
- 跨场景
Abstract: Regional-scale landslides triggered by extreme environmental factors pose a significant threat to life and property safety. Consequently, advancing the automation of regional landslide identification and enhancing the information transparency of potential hazard zones in complex terrain are paramount for the construction of geological hazard databases and effective risk management. Deep learning methods provide an effective solution, overcoming the problem of insufficient automation in traditional methods. However, existing research primarily focuses on optimizing model architecture and improving training strategies, leaving challenges in the effective fusion of multi-source topographic data and the enhancement of cross-regional identification capability. To address these bottlenecks, this paper proposes ResU-CBNet, a deep learning model with robust cross-regional identification capability. The model integrates a hybrid spatial and channel attention mechanism into the neural network and utilizes a residual network to replace the conventional network structure. The model’s performance under multi-scale feature fusion conditions significantly outperforms that of single remote sensing data, specifically showing improvements of 2.1% in PA, 2.6% in CPA, 6.9% in F1_Score, and 2.9% in MIoU. Furthermore, the model validates its cross-scene generalization capability across regions with different scenarios, spectral bands, and spatial distributions, achieving PA and F1_Score performances of 92.8%, 91.3% and 83.2%, 80.0%, respectively. The identification results demonstrate a high degree of consistency with the actual regions. The cross-scene identification method presented here offers a valuable reference for intelligent landslide recognition and risk assessment.
- Deep Learning /
- Multi-source Data /
- Attention Mechanism /
- Landslide Recognition /
- Cross-scene

HTML全文

参考文献(41)

Dou, J., Yunus, A.P., Bui, D.T., et al., 2019. Assessment of Advanced Random Forest and Decision Tree Algorithms for Modeling Rainfall-Induced Landslide Susceptibility in the Izu-Oshima Volcanic Island, Japan[J]. Science of the Total Environment, 662: 332-346. https://doi.org/10.1016/j.scitotenv.2019.01.221.
Wang, Q.Y., Tang, H.M., An, P.J., et al., 2024. Insight into the Permeability and Microstructure Evolution Mechanism of the Sliding Zone Soil: A Case Study from the Huangtupo Landslide, Three Gorges Reservoir, China[J]. Journal of Earth Science, 35: 941-954. https://doi.org/10.1007/s12583-023-1828-0.
Yang, Y.C., Dou, J., Merghadi, A., et al., 2024. Advanced Prediction of Landslide Deformation Through Temporal Fusion Transformer and Multivariate Time-Series Clustering of InSAR: Insights from the Badui Region, Eastern Tibet[J]. IEEE Transactions on Geoscience and Remote Sensing, 62: 1-19. doi: 10.1109/TGRS.2024.3504241.
何雨健,窦杰,王协康,等,2024. 国内外免像控无人机航测软件在数字滑坡中的应用效果对比--以三峡库区黄土坡滑坡为例[J].中国地质灾害与防治学报, (05): 160-173.
唐辉明,李长冬,胡伟,等,2022. 重大滑坡启滑的物理机制是什么[J]? 地球科学, 47(10): 3902-3903.
许强,董秀军,朱星,等, 2023. 基于实景三维的天-空-地-内滑坡协同观测[J]. 工程地质学报, 31(03): 706-717.
窦杰,向子林,许强,等,2023. 机器学习在滑坡智能防灾减灾中的应用与发展趋势[J]. 地球科学, 48(05): 1657-1674.
Dou, J., Yunus, A.P., Bui, D.T., et al., 2020. Improved Landslide Assessment Using Support Vector Machine with Bagging, Boosting, and Stacking Ensemble Machine Learning Framework in a Mountainous Watershed, Japan[J]. Landslides, 17(3): 641-658. https://doi.org/10.1007/s10346-019-01286-5.
殷跃平,高少华,2024. 高位远程地质灾害研究:回顾与展望[J].中国地质灾害与防治学报, (01): 1-18.
张世殊,李青春,黎昊,等,2025. 融合多源遥感数据和改进后Mask R-CNN深度学习模型的复杂高原地形区冰湖智能识别[J]. 地球科学,50(08): 3132-3143.
Baghbani, A., Choudhury, T., Costa, S., et al., 2022. Application of Artificial Intelligence in Geotechnical Engineering: A State-of-the-art Review[J]. Earth-Science Reviews, 228: 103991. https://doi.org/10.1016/j.earscirev.2022.103991.
范荣双,陈洋,徐启恒,等,2019. 基于深度学习的高分辨率遥感影像建筑物提取方法[J]. 测绘学报, 48(01): 34-41.
Dong, A.N., Dou, J., Li, C.D., et al., 2024. Accelerating Cross-Scene Co-Seismic Landslide Detection Through Progressive Transfer Learning and Lightweight Deep Learning Strategies[J]. IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-13, 2024, Art no. 4410213, doi: 10.1109/TGRS.2024.3424680.
巨袁臻,许强,金时超,等,2020. 使用深度学习方法实现黄土滑坡自动识别[J]. 武汉大学学报(信息科学版), 45(11): 1747-55. (in Chinese with English abstract)
Cheng, L.B., Li, J., Duan, P., et al., 2021. A Small Attentional YOLO Model for Landslide Detection from Satellite Remote Sensing Images[J]. Landslides, 18(8): 2751-2765. https://doi.org/10.1007/s10346-021-01694-6.
毛佳琪,何敬,刘刚,等,2023. 基于改进的DeepLabV3+算法滑坡识别[J]. 自然灾害学报, 32(02): 227-34.
Yang, Z.Q., Xu, C., 2022. Efficient Detection of Earthquake-Triggered Landslides Based on U-Net plus: An Example of the 2018 Hokkaido Eastern Iburi (Japan) Mw=6.6 Earthquake[J]. Remote Sensing, 14(12): 2826. https://doi.org/10.3390/rs14122826.
Liu, X.R., Peng, Y.X., Lu, Z.L., et al., 2023. Feature-Fusion Segmentation Network for Landslide Detection Using High-Resolution Remote Sensing Images and Digital Elevation Model Data[J]. IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-13, 2024, Art no. 4410213, doi: 10.1109/TGRS.2024.3424680.
Guo, Z.Z., Zeng, T.R., Zhang, Y.H., et al., 2025. A Novel Hybrid Model Integrating High Resolution Remote Sensing and Stacking Ensemble Techniques for Landslide Susceptibility Mapping: Application to Event-Based Landslide Inventory[J]. Geomorphology, Volume 486, 109886, ISSN 0169-555X, https://doi.org/10.1016/j.geomorph.2025.109886.
Dou, J., Xing, K., Wang, L.Z., et al., 2025. Air-Space-Ground Synergistic Observations for Rapid Post-Seismic Disaster Assessment of 2025 Ms6.8 Xigazê Earthquake, Xizang[J]. Journal of Earth Science, 36: 1605-1622. https://doi.org/10.1007/s12583-025-0160-2.
邢珂,黎昊,张乐乐,等,2025. 2025年西藏定日MS6.8地震地表破裂与震害特征分析[J]. 安全与环境工程, 32(02): 20-30. DOI: 10.13578/j.cnki.issn.1671-1556.20250133.
Xing, K., Li, H., Zhang, L.L., et al., 2025. Analysis of Surface Rupture and Seismic Damage Characteristics of 2025 Dingri MS 6.8 Earthquake in Xizang[J]. Safety and Environmental Engineering, 32(02): 20-30.
Chen, H., et al., 2024. A Multi-Input Channel U-Net Landslide Detection Method Fusing SAR Multisource Remote Sensing Data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 1215-1232, 2024, doi: 10.1109/JSTARS.2023.3339294.
Yang, Y.H., Miao, Z.L, Zhang, H., et al., 2024. Lightweight Attention-Guided YOLO With Level Set Layer for Landslide Detection From Optical Satellite Images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. PP. 1-19. 10.1109/JSTARS.2024.3351277.
Xiang, X.Y., Gong, W.P., Li, S.L., et al., 2024. TCNet: Multiscale Fusion of Transformer and CNN for Semantic Segmentation of Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. PP. 1-14. 10.1109/JSTARS.2024.3349625.
Xu, Q., Ouyang, C.J., Jiang, T.H., et al., 2022. MFFENet and ADANet: a Robust Deep Transfer Learning Method and Its Application in High Precision and Fast Cross-Scene Recognition of Earthquake-induced Landslides[J]. Landslides, 19: 1617-1647. https://doi.org/10.1007/s10346-022-01847-1.
Woo, S., Park, J., Lee, J.Y., et al., 2018. CBAM: Convolutional Block Attention Module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science(), vol 11211. Springer, Cham. https://doi.org/10.1007/978-3-030-01234-2_1.
Osanai, N., Yamada, T., Hayashi, S., et al., 2019. Characteristics of Landslides Caused by the 2018 Hokkaido Eastern Iburi Earthquake[J]. Landslides, 16: 1517-1528. https://doi.org/10.1007/s10346-019-01206-7.
邢珂,窦杰,陈能成,等,2025. 基于光学-LiDAR协同遥感及三维精细建模的滑坡特征解译与稳定性评价[J].自然灾害学报, (03):119-132.
Wang, X.M., Yin, J., Luo, M.H., et al., 2023. Active High-Locality Landslides in Mao County: Early Identification and Deformational Rules[J]. Journal of Earth Science, 34: 1596-1615. https://doi.org/10.1007/s12583-021-1505-0.
Shafiq, M.; Gu, Z. Deep Residual Learning for Image Recognition: A Survey. Appl. Sci. 2022, 12, 8972. https://doi.org/10.3390/app12188972.
Zhang, Z.X., Liu, Q.J., Wang, Y.H., 2018. Road Extraction by Deep Residual U-net[J]. IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753. doi: 10.1109/LGRS.2018.2802944.
Wang, H.H, Liu, J., Zeng, S.K, et al., 2024. A Novel Landslide Identification Method for Multi-scale and Complex Background Region Based on Multi-model Fusion: YOLO + U-Net[J]. Landslides, 21: 901-917. https://doi.org/10.1007/s10346-023-02184-7.
Wu, Z.B., Li, H., Yuan, S.X., et al., 2023. Mask R-CNN–Based Landslide Hazard Identification for 22.6 Extreme Rainfall Induced Landslides in the Beijiang River Basin, China[J]. Remote Sensing, 15(20): 4898. https://doi.org/10.3390/rs15204898.
Long, J., Shelhamer, E., Darrell, T., 2015. Fully Convolutional Networks for Semantic Segmentation, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 3431-3440, doi: 10.1109/CVPR.2015.7298965.
Chen, L.C., Papandreou, G., Schroff, F., et al., 2017. Rethinking Atrous Convolution for Semantic Image Segmentation. 10.48550/arXiv.1706.05587.
Ronneberger, O., Fischer, P., Brox, T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9351. Springer, Cham. https://doi.org/10.1007/978-3-319-24574-4_28.
Howard, A., Sandler, M., Chu, G., et al., 2019. Searching for MobileNetV3[J].IEEE, 2020.DOI: 10.1109/ICCV.2019.00140.
Selvaraju, R.R., Cogswell, M., Das, A., et al., 2017. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization, 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 618-626, doi: 10.1109/ICCV.2017.74.
Guo, Z.Z., Cheng, M.C., Wang, Y.G, et al., 2025. Landslide hazard prediction under an extreme rainfall scenario by considering multiple timescale rainfalls and effective recharge. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 1–29. https://doi.org/10.1080/17499518.2025.2570863.
[2022]	年中国生态环境状况公报(摘录)[J]. 环境保护, 2023, 51(Z2): 64-81.

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 87
HTML全文浏览量: 0
PDF下载量: 5
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

融合多源特征的轻量化深度学习跨场景滑坡智能识别

doi: 10.3799/dqkx.2025.255

作者简介:
邢珂(1999-),男,博士研究生,主要从事地质灾害智能识别与风险评估,E-mail:xingke@cug.edu.cn,ORCID:https://orcid.org/0009-0000-4838-8831

通讯作者:
窦杰(1981-),男,博导,研究员,主要从事地质灾害大数据智能管控及机理演化研究。E-mail:doujie@cug.edu.cn

计量

Lightweight Deep Learning for Cross-Scene Landslide Intelligent Recognition with Multi-Source Feature Fusion

计量

目录

留言板

融合多源特征的轻量化深度学习跨场景滑坡智能识别

doi: 10.3799/dqkx.2025.255

作者简介: 邢珂(1999-),男,博士研究生,主要从事地质灾害智能识别与风险评估,E-mail:xingke@cug.edu.cn,ORCID:https://orcid.org/0009-0000-4838-8831

通讯作者: 窦杰(1981-),男,博导,研究员,主要从事地质灾害大数据智能管控及机理演化研究。E-mail:doujie@cug.edu.cn

计量

出版历程

Lightweight Deep Learning for Cross-Scene Landslide Intelligent Recognition with Multi-Source Feature Fusion

计量

出版历程

目录

作者简介:
邢珂(1999-),男,博士研究生,主要从事地质灾害智能识别与风险评估,E-mail:xingke@cug.edu.cn,ORCID:https://orcid.org/0009-0000-4838-8831

通讯作者:
窦杰(1981-),男,博导,研究员,主要从事地质灾害大数据智能管控及机理演化研究。E-mail:doujie@cug.edu.cn