Improving Landslide Detection on SAR Data Through Deep Learning

Nava, Lorenzo; Monserrat, Oriol; Catani, Filippo

doi:10.1109/lgrs.2021.3127073

Cited by 40 publications

(33 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the core prerequisite for employing AI models is a reliable dataset to be used for training. Recent studies have only focused on mapping landslides with AI but at scales that are small or regional while also claiming that the proposed models can cater towards rapid mapping of landslides at any given time, location and scale (Liu et al, 2022;Meena et al, 2022a;Nava, Monserrat, et al, 2022;Soares et al, 2022a;Tang et al, 2022;. However, seldom has been the case where truly an approach has been taken to map landslides outside the regions where the models are initially trained on, and also towards actually applying the proposed models in capturing and mapping event-based landslides that has recently occurred.…”

Section: Introductionmentioning

confidence: 99%

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

Meena

Nava²,

Bhuyan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. Multiple landslide events occur often across the world which has the potential to cause significant harm to both human life and property. Although a substantial amount of research has been conducted to address mapping of landslides using Earth Observation (EO) data, several gaps and uncertainties remain when developing models to be operational at the global scale. To address this issue, we present the HR-GLDD, a high resolution (HR) dataset for landslide mapping composed of landslide instances from ten different physiographical regions globally: South and South-East Asia, East Asia, South America, and Central America. The dataset contains five rainfall triggered and five earthquake-triggered multiple landslide events that occurred in varying geomorphological and topographical regions. HR-GLDD is one of the first datasets for landslide detection generated by high-resolution satellite imagery which can be useful for applications in artificial intelligence for landslide segmentation and detection studies. Five state-of-the-art deep learning models were used to test the transferability and robustness of the HR-GLDD. Moreover, two recent landslide events were used for testing the performance and usability of the dataset to comment on the detection of newly occurring significant landslide events. The deep learning models showed similar results for testing the HR-GLDD in individual test sites thereby indicating the robustness of the dataset for such purposes. The HR-GLDD can be accessed open access and it has the potential to calibrate and develop models to produce reliable inventories using high-resolution satellite imagery after the occurrence of new significant landslide events. The HR-GLDD will be updated regularly by integrating data from new landslide events.

show abstract

Section: Introductionmentioning

confidence: 99%

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

Meena

Nava²,

Bhuyan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We divide the Hokkaido datacube into data chips of size 128x128 pixels (each pixel is 10m×10m in spatial resolution). Since the dataset is imbalanced, we reduce negative examples by keeping only data chips with one or more landslide pixels, similar to Nava et al [11]. These chips are split into training, and test sets with 216, and 61 chips respectively.…”

Section: Methodsmentioning

confidence: 99%

“…This has been exploited for multiple use cases such as the detection of volcanic activity [8], floods [9], and landslides [10]. The landslide change detection with DL can be performed in two ways: object-level [11] and pixel-level detection [10]. As per the authors' best knowledge [10,11] are one of the first studies in landslide mapping using DL and SAR images where bi-and tri-temporal images have been used.…”

Section: Introductionmentioning

confidence: 99%

“…The landslide change detection with DL can be performed in two ways: object-level [11] and pixel-level detection [10]. As per the authors' best knowledge [10,11] are one of the first studies in landslide mapping using DL and SAR images where bi-and tri-temporal images have been used. Usage of multi-temporal SAR polarization modes has been demonstrated with traditional approaches, such as thresholding [12], similar conclusion was reported in a DL study [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes

Boehm¹,

Leong²,

Mahesh³

et al. 2022

Preprint

View full text Add to dashboard Cite

With climate change predicted to increase the likelihood of landslide events, there is a growing need for rapid landslide detection technologies that help inform emergency responses. Synthetic Aperture Radar (SAR) is a remote sensing technique that can provide measurements of affected areas independent of weather or lighting conditions. Usage of SAR, however, is hindered by domain knowledge that is necessary for the pre-processing steps and its interpretation requires expert knowledge. We provide simplified, pre-processed, machine-learning ready SAR datacubes for four globally located landslide events obtained from several Sentinel-1 satellite passes before and after a landslide triggering event together with segmentation maps of the landslides. From this dataset, using the Hokkaido, Japan datacube, we study the feasibility of SAR-based landslide detection with supervised deep learning (DL). Our results demonstrate that DL models can be used to detect landslides from SAR data, achieving an Area under the Precision-Recall curve exceeding 0.7. We find that additional satellite visits enhance detection performance, but that early detection is possible when SAR data is combined with terrain information from a digital elevation model. This can be especially useful for time-critical emergency interventions. Code is made publicly available at https://github.com/iprapas/landslide-sar-unet.

show abstract

“…On the other hand, CNN equipped with VGGNet, ResNet, and DenseNet has been widely applied in landslide detection. For example, Cai et al [33] and Liu et al [34] incorporated controlling factors into samples to test the feasibility of Dense-Net in landslide extraction, while Nava et al [35] explored the performance of the network when topographic factors were fused into SAR images. Furthermore, Ghorbanzadeh et al [36] attempted to fuse landslide detection results generated from CNN trained with different datasets through the Dempster-Shafer model.…”

Section: Introductionmentioning

confidence: 99%

Landslide Detection Based on ResU-Net with Transformer and CBAM Embedded: Two Examples with Geologically Different Environments

Xu¹,

2022

Remote Sensing

View full text Add to dashboard Cite

An efficient method of landslide detection can provide basic scientific data for emergency command and landslide susceptibility mapping. Compared to a traditional landslide detection approach, convolutional neural networks (CNN) have been proven to have powerful capabilities in reducing the time consumed for selecting the appropriate features for landslides. Currently, the success of transformers in natural language processing (NLP) demonstrates the strength of self-attention in global semantic information acquisition. How to effectively integrate transformers into CNN, alleviate the limitation of the receptive field, and improve the model generation are hot topics in remote sensing image processing based on deep learning (DL). Inspired by the vision transformer (ViT), this paper first attempts to integrate a transformer into ResU-Net for landslide detection tasks with small datasets, aiming to enhance the network ability in modelling the global context of feature maps and drive the model to recognize landslides with a small dataset. Besides, a spatial and channel attention module was introduced into the decoder to effectually suppress the noise in the feature maps from the convolution and transformer. By selecting two landslide datasets with different geological characteristics, the feasibility of the proposed model was validated. Finally, the standard ResU-Net was chosen as the benchmark to evaluate the proposed model rationality. The results indicated that the proposed model obtained the highest mIoU and F1-score in both datasets, demonstrating that the ResU-Net with a transformer embedded can be used as a robust landslide detection method and thus realize the generation of accurate regional landslide inventory and emergency rescue.

show abstract

Improving Landslide Detection on SAR Data Through Deep Learning

Cited by 40 publications

References 27 publications

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

HR-GLDD: A globally distributed dataset using generalized DL for rapid landslide mapping on HR satellite imagery

Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes

Landslide Detection Based on ResU-Net with Transformer and CBAM Embedded: Two Examples with Geologically Different Environments

Contact Info

Product

Resources

About