Abstract
Accurate and automatic landslide detection plays a vital role in keeping abreast of disaster situations and supporting rescue-related decision-making. Currently, deep learning has brought innovation to landslide detection techniques. However, previous studies did not consider the nested connection between low-level and high-level feature maps, resulting in coarse landslide segmentation boundaries. In addition, due to the instability of processing noise, existing models significantly degrade the performance when faced with complex landslide scenes. In this study, we present a novel robust rainfall-induced landslide detection model guided by contrastive learning. Specifically, we embed the residual block and channel attention module into U-Net+++ to adequately exploit semantic details and focus on vital information. Meanwhile, we implement effective data augmentation strategies to obtain two different image views, and feed them into a dual-branch model to predict landslide locations. Afterwards, we develop contrastive dice similarity coefficient loss to maintain the consistency of landslide region pairs, which stimulates the model to further mine invariance characteristics. We successfully fuse the modified U-Net+++ and contrastive learning to solve the coarse boundary and poor robustness problem. Numerous experiments are implemented to demonstrate that our model generates excellent performance with mean intersect over union over 0.80 and outperforms other classic segmentation methods in crucial criteria.
References
Aleotti P, Chowdhury R (1999) Landslide hazard assessment: summary review and new perspectives. Bull Eng Geol Environ 58(1):21–44
Avelar AS, Netto ALC, Lacerda WA et al (2013) Mechanisms of the recent catastrophic landslides in the mountainous range of Rio de Janeiro, Brazil. Landslide Science and Practice pp 265–270
Bragagnolo L, Rezende L, da Silva R et al (2021) Convolutional neural networks applied to semantic segmentation of landslide scars. Catena 201(105):189
Chen T, Kornblith S, Norouzi M et al (2020) A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning. pp 1597–1607
Dai F, Lee C, Li J et al (2001) Assessment of landslide susceptibility on the natural terrain of Lantau Island, Hong Kong. Environ Geol 40(3):381–391
Fiorucci F, Ardizzone F, Mondini AC et al (2019) Visual interpretation of stereoscopic NDVI satellite images to map rainfall-induced landslides. Landslides 16(1):165–174
Florian L, Adam SH (2017) Rethinking atrous convolution for semantic image segmentation. In: Conference on Computer Vision and Pattern Recognition
Fu J, Liu J, Tian H et al (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 3146–3154
Ghaffarian S, Valente J, Van Der Voort M et al (2021) Effect of attention mechanism in deep learning-based remote sensing image processing: a systematic literature review. Remote Sens 13(15):2965
Ghorbanzadeh O, Meena SR, Abadi HSS et al (2020) Landslide mapping using two main deep-learning convolution neural network streams combined by the Dempster-Shafer model. IEEE J Sel Top Appl Earth Obs Remote Sens 14:452–463
Ghorbanzadeh O, Crivellari A, Ghamisi P et al (2021) A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan). Sci Rep 11(1):1–20
Goodfellow I, Bengio Y, Courville A (2016) Deep learning
Huang R, Li W (2011) Formation, distribution and risk control of landslides in China. J Rock Mech Geotech Eng 3(2):97–116
Huang H, Lin L, Tong R et al (2020) Unet 3+: a full-scale connected Unet for medical image segmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp 1055–1059
Ji S, Yu D, Shen C et al (2020) Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides 17(6):1337–1352
Khosla P, Teterwak P, Wang C et al (2020) Supervised contrastive learning. Adv Neural Inf Proces Syst 33:18661–18673
Knevels R, Petschko H, Leopold P et al (2019) Geographic object-based image analysis for automated landslide detection using open source GIS software. ISPRS Int J Geo Inf 8(12):551
Koppen W (1936) Das geographische system der klimat. Handbuch der Klimatologie. p 46
Lin CW, Liu SH, Lee SY et al (2006) Impacts of the Chi-Chi earthquake on subsequent rainfall-induced landslides in Central Taiwan. Eng Geol 86(2–3):87–101
Lissak C, Bartsch A, De Michele M et al (2020) Remote sensing for assessing landslides and associated hazards. Surv Geophys 41(6):1391–1435
Liu P, Wei Y, Wang Q et al (2020) Research on post-earthquake landslide extraction algorithm based on improved U-net model. Remote Sens 12(5):894
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 3431–3440
Lu P, Stumpf A, Kerle N et al (2011) Object-oriented change detection for landslide rapid mapping. IEEE Geosci Remote Sens Lett 8(4):701–705
Mandal SP, Chakrabarty A (2016) Flash flood risk assessment for upper Teesta river basin: using the hydrological modeling system (HEC-HMS) software. Model Earth Syst Environ 2(2):1–10
Micheletti N, Kanevski M, Bai S et al (2013) Intelligent analysis of landslide data using machine learning algorithms. In: Landslide Science and Practice. pp 161–167
Moosavi V, Talebi A, Shirmohammadi B (2014) Producing a landslide inventory map using pixel-based and object-oriented approaches optimized by Taguchi method. Geomorphology 204:646–656
Oh HJ, Kim YS, Choi JK et al (2011) GIS mapping of regional probabilistic groundwater potential in the area of Pohang City, Korea. J Hydrol 399(3–4):158–172
Pourghasemi HR, Mohammady M, Pradhan B (2012) Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood basin, Iran. Catena 97:71–84
Qin S, Guo X, Sun J et al (2021) Landslide detection from open satellite imagery using distant domain transfer learning. Remote Sens 13(17):3383
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp 234–241
Rosenqvist A, Shimada M, Ito N et al (2007) ALOS PALSAR: a pathfinder mission for global-scale monitoring of the environment. IEEE Trans Geosci Remote Sens 45(11):3307–3316
Si T, He F, Zhang Z et al (2022) Hybrid contrastive learning for unsupervised person re-identification. IEEE Trans Multimedia
Soares LP, Dias HC, Grohmann CH (2020) Landslide segmentation with U-net: evaluating different sampling methods and patch sizes. Preprint at http://arxiv.org/abs/2007.06672
Sobral BS, Oliveira-Júnior JF, Gois G et al (2018) Variabilidade espaço-temporal e interanual da chuva no estado do rio de janeiro. Revista Brasileira de Climatologia 22
Stumpf A, Kerle N (2011) Object-oriented mapping of landslides using random forests. Remote Sens Environ 115(10):2564–2577
Van Den Eeckhaut M, Poesen J, Verstraeten G et al (2005) The effectiveness of hillshade maps and expert knowledge in mapping old deep-seated landslides. Geomorphology 67(3–4):351–363
Xu G, Wang Y, Wang L et al (2022) Feature-based constraint deep CNN method for mapping rainfall-induced landslides in remote regions with mountainous terrain: an application to Brazil. IEEE J Sel Top Appl Earth Obs Remote Sens 15:2644–2659
Yu H, Ma Y, Wang L et al (2017) A landslide intelligent detection method based on CNN and RSG_r. In: IEEE International Conference on Mechatronics and Automation. pp 40–44
Yuan Y, Huang L, Guo J et al (2021) OCNET: object context for semantic segmentation. Int J Comput Vis 129(8):2375–2398
Acknowledgements
Thanks to Lucas Pedrosa Soares Carlos and H. Grohmann of the University of São Paulo for providing remote sensing images. The authors would also like to thank the associate editor and anonymous reviewers for their valuable comments and suggestions, which significantly improved the quality of this article.
Funding
This work was supported by the Joint Funds of the National Natural Science Foundation of China under Grant U21A2013, in part by the National Natural Science Foundation of China under Grant 61271408.
Author information
Authors and Affiliations
Contributions
Penglei Li: conceptualization, methodology, software, investigation, validation, writing—original draft, writing—review. Yi Wang: conceptualization, writing—review, validation, supervision, project administration, funding acquisition. Guosen Xu: writing—review, validation, investigation. Lizhe Wang: writing—review, project administration, funding acquisition.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Li, P., Wang, Y., Xu, G. et al. LandslideCL: towards robust landslide analysis guided by contrastive learning. Landslides 20, 461–474 (2023). https://doi.org/10.1007/s10346-022-01981-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-022-01981-w