Preprints
https://doi.org/10.5194/essd-2022-350
https://doi.org/10.5194/essd-2022-350
17 Oct 2022
 | 17 Oct 2022
Status: a revised version of this preprint is currently under review for the journal ESSD.

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

Sansar Raj Meena, Lorenzo Nava, Kushanav Bhuyan, Silvia Puliero, Lucas Pedrosa Soares, Helen Cristina Dias, Mario Floris, and Filippo Catani

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.

Sansar Raj Meena et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on essd-2022-350', Anonymous Referee #1, 05 Dec 2022
    • AC1: 'Reply on RC1', Sansar Raj Meena, 31 Jan 2023
  • CC1: 'Comment on essd-2022-350', Prafull Singh, 15 Dec 2022
    • RC2: 'Reply on CC1', Anonymous Referee #2, 16 Dec 2022
      • AC3: 'Reply on RC2', Sansar Raj Meena, 31 Jan 2023
    • AC2: 'Reply on CC1', Sansar Raj Meena, 31 Jan 2023
  • RC3: 'Comment on essd-2022-350', Anonymous Referee #3, 16 Jan 2023
    • AC4: 'Reply on RC3', Sansar Raj Meena, 05 Feb 2023
  • RC4: 'Comment on essd-2022-350', Anonymous Referee #3, 09 Feb 2023
    • AC5: 'Reply on RC4', Sansar Raj Meena, 10 Feb 2023

Sansar Raj Meena et al.

Data sets

HR-GLDD Sansar Raj Meena https://doi.org/10.5281/zenodo.7189381

Sansar Raj Meena et al.

Viewed

Total article views: 1,153 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
769 344 40 1,153 11 12
  • HTML: 769
  • PDF: 344
  • XML: 40
  • Total: 1,153
  • BibTeX: 11
  • EndNote: 12
Views and downloads (calculated since 17 Oct 2022)
Cumulative views and downloads (calculated since 17 Oct 2022)

Viewed (geographical distribution)

Total article views: 1,095 (including HTML, PDF, and XML) Thereof 1,095 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 02 Jun 2023
Download
Short summary
Landslide events occur often across the world and have the potential to cause significant damage. Although a substantial amount of research has been conducted on the mapping of landslides using remote sensing 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.