Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
10
datasets available to search
ShareScore release 0.9.0
Dataset results
10 results for “Landslide detection”
CAS Landslide Dataset: A Large-Scale and Multisensor Dataset for Deep Learning-Based Landslide Detection
<p>In this work, we present the CAS Landslide Dataset, a large-scale and multisensor dataset for deep learning-based landslide detection, developed by the Artificial Intelligence Group at the Institute of Mountain Hazards and Environment, Chinese Academy of Sciences (CAS). The dataset aims to address the challenges encountered in landslide recognition. With the increase in landslide occurrences due to climate change and earthquakes, there is a growing need for a precise and comprehensive dataset to support fast and efficient landslide recognition. In contrast to existing datasets with dataset size, coverage, sensor type and resolution limitations, the CAS Landslide Dataset comprises 20,865 images, integrating satellite and unmanned aerial vehicle data from nine regions. To ensure reliability and applicability, we establish a robust methodology to evaluate the dataset quality. We propose the use of the Landslide Dataset as a benchmark for the construction of landslide identification models and to facilitate the development of deep learning techniques. Researchers can leverage this dataset to obtain enhanced prediction, monitoring, and analysis capabilities, thereby advancing automated landslide detection.</p> <p>If you use our data, please cite our work published in Scientific Data.</p> <p>Xu, Y., Ouyang, C., Xu, Q. <em>et al.</em> CAS Landslide Dataset: A Large-Scale and Multisensor Dataset for Deep Learning-Based Landslide Detection. <em>Sci Data</em> <strong>11</strong>, 12 (2024). https://doi.org/10.1038/s41597-023-02847-z</p>
Datacubes for Landslide Detection with SAR Imagery
<p>Four analysis-ready datacubes with multiple layers of SAR time-series data and interferometric products (coherence, InSAR) and auxiliary topographic information (elevation, slope, aspect, curvature) for multiple landslide events along with the corresponding landslide labels.</p> <p> </p> <table> <tbody> <tr> <td>Area</td> <td>Cause</td> <td>Date of event</td> <td>Dimensions</td> <td>Label Type</td> <td>Label Source</td> </tr> <tr> <td>Hokkaido, Japan</td> <td>Earthquake</td> <td>06-Sep-18</td> <td>{'y': 5382, 'x': 4398, 'timestep': 26, 'timepair': 16}</td> <td>Segmentation</td> <td><a href="https://zenodo.org/record/2577300">link</a></td> </tr> <tr> <td>Puerto Rico</td> <td>Hurricane Maria</td> <td>16-09-2017 - 02-10-2017</td> <td>{'y': 7134, 'x': 19251, 'timestep': 6, 'timepair': 4}</td> <td>Landslide heads</td> <td><a href="https://www.geosociety.org/gsatoday/science/G383A/GSATG383A.pdf">link</a></td> </tr> <tr> <td>Mt Talakmau, Indonesia</td> <td>Earthquake</td> <td>25-Feb-22</td> <td>{'y': 4313, 'x': 3006, 'timestep': 20, 'timepair': 12}</td> <td>Segmentation</td> <td><a href="https://www.unosat.org/products/3064">link</a></td> </tr> <tr> <td>Kaikoura, New Zealand</td> <td>Earthquake</td> <td>14-Nov-16</td> <td>{'y': 16973, 'x': 15930, 'timestep': 5, 'timepair': 9}</td> <td>Landslide centroids</td> <td><a href="https://data.gns.cri.nz/landslides/wms.html">link</a></td> </tr> </tbody> </table> <p> </p> <p><strong>Acknowledgements</strong><br> This work has been enabled by the Frontier Development Lab Program (FDL). FDL is a collaboration between SETI Institute and Trillium Technologies Inc., in partnership with the Department of Energy (DOE) , National Aeronautics and Space Administration (NASA), and U.S. Geological Survey (USGS).The material is based upon work supported by NASA under award No(s) NNX14AT27A.<br> </p>
Detection of slow-moving landslides from Sentinel-2 optical satellite imagery
<p>Datasets and code associated with recent ESPL publication</p> <p>"Detection of slow-moving landslides through automated satellite monitoring of surface deformation"</p> <p>The three imagery folders are zipped for convenience. The full code is included in the one .m file.</p> <p>Please get in touch with any questions.</p>
Data from: Forecasting landslides using community detection on geophysical satellite data
<p>As a result of extreme weather conditions, such as heavy precipitation, natural hillslopes can fail dramatically; these slope failures can occur on a dry day due to time lags between rainfall and pore-water pressure change at depth, or even after days to years of slow-motion. While the pre-failure deformation is sometimes apparent in retrospect, it remains challenging to predict the sudden transition from gradual deformation (creep) to runaway failure. We use a network science method–multilayer modularity optimization–to investigate the spatiotemporal patterns of deformation in a region near the 2017 Mud Creek, California landslide. We transform satellite radar data from the study site into a spatially-embedded network in which the nodes are patches of ground and the edges connect the nearest neighbors, with a series of layers representing consecutive transits of the satellite. Each edge is weighted by the product of the local slope (susceptibility to failure) measured from a digital elevation model and ground surface deformation (current rheological state) from interferometric synthetic aperture radar (InSAR). We use multilayer modularity optimization to identify strongly-connected clusters of nodes (communities) and are able to identify both the location of Mud Creek and nearby creeping landslides which have not yet failed. We develop a metric, community persistence, to quantify patterns of ground deformation leading up to failure, and find that this metric increases from a baseline value in the weeks leading up to Mud Creek's failure. These methods promise as a technique for highlighting regions at risk of catastrophic failure.</p>
Data from: Forecasting landslides using community detection on geophysical satellite data
Open the record for dataset details and reuse information.
GLaD4CD: Global Landslide Dataset for Change Detection
<p>This dataset constitutes one of the outcomes of the Master's Thesis titled 'Landslide identification using deep learning-based change detection and the DeepESDL collaborative cloud platform,' authored by Julia Anna Leonardi, conducted under the supervision of Prof. Maria Antonia Brovelli and Dr. Vasil Yordanov at Politecnico di Milano. The authors extracted the image patches through the DeepESDL platform, which the ESA NoR sponsorship provided access to. </p> <p>The resource contains the .csv database containing landslide information of 174 events, such as the date, location, source, and the dates of the Sentinel-2 images from before and after the event. The sources of the data included in this inventory are:</p> <ul> <li><a href="progettoiffi.isprambiente.it" target="_blank" rel="noopener">Inventario dei Fenomeni Franosi in Italia (IFFI) compiled by ISPRA</a></li> <li>NASA <a href="https://gpm.nasa.gov/landslides/projects.html#GLC" target="_blank" rel="noopener">Global Landslide Catalog (GLC)</a> [1],[2].</li> <li><a href="https://emergency.copernicus.eu/">Copernicus Emergency Management Service</a> (© European Union, 2012-2024) [3]</li> <li>Geological Survey Ireland | <a href="https://www.gsi.ie/en-ie/data-and-maps/Pages/Geohazards.aspx">Geohazards</a> | <a href="https://www.gsi.ie/en-ie/publications/Pages/National-Landslide-Susceptibility-Map.aspx" target="_blank" rel="noopener">National Landslide Susceptibility Map</a></li> <li><a href="../records/7970874" target="_blank" rel="noopener">Monsoon triggered landslides in Nepal timed with Sentinel-1 for 2015, 2017, 2018, and 2019</a>, courtesy of Katy Burrows [4] </li> <li><a href="https://maps.disasters.nasa.gov/download/gis_products/event_specific/2023/turkiye_earthquakes_202302/landslides/">Landslides after 2023 earthquakes in Turkey</a> compiled by the NASA GSFC team</li> <li><a href="https://www.itc.nl/about-itc/centres-of-expertise/centre-for-disaster-resilience/what-we-do/education-training/Landslides-Course-21-25-November/" target="_blank" rel="noopener">University of Twente online landslide course</a></li> <li>Manually extracted sources from [5], [6], [7], [8].</li> </ul> <p>The .zip file contains the TRAIN dataset with the pre-event Sentinel-2 image patches in folder PRE and the post-event Sentinel-2 image patches in folder POST, and the TEST set with 17 bi-temporal pairs in the PRE and POST folders following the above convention and the labels in the form of change maps in the CM folder. In this updated version the full 13-band Sentinel-2 images are published. (In the previous version only 5 bands (B02, B03, B04, B08, and CLM) were available). All the image patches and the ground truth annotations are in the GeoTIFF format. </p> <p>The authors developed the dataset for change detection workflows.</p> <p>Project supported by the ESA Network of Resources Initiative.</p> <p>This work is funded by the Italian Ministry of Foreign Affairs and International Cooperation within the project “Geoinformatics and Earth Observation for Landslide Monitoring” CUP D19C21000480001</p> <p> </p> <p>[1] Kirschbaum, D.B., Stanley, T., & Zhou, Y. (2015). Spatial and temporal analysis of a global landslide catalog. Geomorphology, 249, 4-15. doi:<a href="https://doi.org/10.1016/j.geomorph.2015.03.016">10.1016/j.geomorph.2015.03.016</a></p> <p>[2] Kirschbaum, D.B., Adler, R., Hong, Y., Hill, S., & Lerner-Lam, A. (2010). A global landslide catalog for hazard applications: method, results, and limitations. Natural Hazards, 52, 561-575. doi:<a href="https://doi.org/10.1007/s11069-009-9401-4">10.1007/s11069-009-9401-4</a></p> <p>[3] Copernicus Emergency Management Service. (n.d.). Retrieved March 12, 2024 from <a href="https://emergency.copernicus.eu/">https://emergency.copernicus.eu/</a></p> <p>[4] K. Burrows, O. Marcand C. Andermann, “Monsoon triggered landslides in Nepal timed with Sentinel-1 for 2015, 2017, 2018 and 2019”. Zenodo, May 25, 2023. doi: <a href="10.5281/zenodo.7970874.">10.5281/zenodo.7970874.</a></p> <p>[5] F. Wang et al., ‘Coseismic landslides triggered by the 2018 Hokkaido, Japan (Mw 6.6), earthquake: spatial distribution, controlling factors, and possible failure mechanism’, Landslides, vol. 16, no. 8, pp. 1551–1566, Aug. 2019, doi: <a href="10.1007/s10346-019-01187-7">10.1007/s10346-019-01187-7</a>.</p> <p>[6] P. Amatya, D. Kirschbaum, and T. Stanley, ‘Rainfall-induced landslide inventories for Lower Mekong based on Planet imagery and a semi-automatic mapping method’, Geoscience Data Journal, vol. 9, no. 2, pp. 315–327, 2022, doi: <a href="10.1002/gdj3.145">10.1002/gdj3.145</a>.</p> <p>[7] ]‘Vietnam – At Least 12 Killed in Flash Floods and Landslides in North – FloodList’. Accessed: Feb. 18, 2024. [Online]. Available: <a href="https://floodlist.com/asia/vietnam-floods-landslides-yen-baison-la-august-2017" target="_blank" rel="noopener">https://floodlist.com/asia/vietnam-floods-landslides-yen-baison-la-august-2017</a></p> <p>[8] L. Colombo, ‘Crollata, causa frana, la volta di una galleria lungo la SP72 a Fiumelatte a Varenna - GLI AGGIORNAMENTI’, Lecco Notizie. Accessed: Feb. 18, 2024. [Online]. Available: <a href="https://lecconotizie.com/cronaca/crollata-la-volta-di-una-galleria-lungo-la-sp72-a-fiumelatte-avarenna/" target="_blank" rel="noopener">https://lecconotizie.com/cronaca/crollata-la-volta-di-una-galleria-lungo-la-sp72-a-fiumelatte-avarenna/</a></p>
Landslide Detection: Faster-RCNN
<p>Our dataset comprises a collection of high-resolution satellite imagery annotated for landslide detection using the Fast RCNN (Region-based Convolutional Neural Network) model. Each image in the dataset is meticulously labeled to identify regions prone to landslides, providing crucial insights for disaster prevention and mitigation efforts. Leveraging the Fast RCNN architecture, which excels in accurately delineating object boundaries, our dataset offers precise localization of landslide-prone areas, aiding researchers and policymakers in proactive risk assessment and management strategies. By sharing this dataset with the ISPRS community, we aim to foster collaboration and facilitate advancements in landslide detection methodologies for enhanced disaster resilience.</p>
Dataset, models and code for "Automating global landslide detection with heterogeneous ensemble deep-learning classification"
Open the record for dataset details and reuse information.
Multimodal Remote Sensing Dataset for Landslide Change Detection in Haiti
<p>The detection of the collapse of landslides trigerred by intense natural hazards, such as earthquakes and rainfall, allows rapid response to hazards which turned into disasters. The use of remote sensing imagery is mostly considered to cover wide areas and assess even more rapidly the threats. Yet, since optical images are sensitive to cloud coverage, their use is limited in case of emergency response. The proposed dataset is thus multimodal and targets the early detection of landslides following the disastrous earthquake which occurred in Haiti in 2021. It consists of SAR-optical pairs from Sentinel-1 and Sentinel-2 acquired shortly before and after the event. To encourage for machine and deep learning algorithms, the images are cropped into 1713 patches. Since Sentinel-1 SAR images are acquired both in ascending and descending passes, twice more patches are available in this modality. Due to the mountainous nature of the terrain, the images are provided together with a layover-shadow mask computed as described in [Meier <em>et al</em>, 1993]. This mask is destined to limit the impact of geometrical distortions on the algorithm. Similarly, Sentinel-2 optical images are provided with a cloud and cloud shadow mask. Landslide annotations are extracted from the TODO database from NASA, rasterized and croped similarly to the images. The dataset is aimed to be used whether for monomodal or multimodal approaches, and whether for monotemporal or bitemporal approaches.</p> <p>[Meier et al., 1993] Meier, E., Frei, U., and Nüesch, D. (1993). Precise Terrain Corrected Geocoded Images. SAR Geocoding: Data and Systems, pages 173–185. Publisher: Karlsruhe, Germany: Herbert Wichmann Verlag GmbH.</p>
LMHLD: A Large-scale Multi-source High-resolution Landslide Dataset for Landslide Detection based on Deep Learning
<p>LMHLD collects remote sensing images of five satellite sensors in seven areas of the world: Wenchuan, China (2008); Rio de Janeiro, Brazil (2011); Gorkha, Nepal (2015); Jiuzhaigou, China (2015); Taiwan, China (2018); Hokkaido, Japan (2018); Emilia-Romagna, Italy (2023), a total of 25,365 patches by setting different patch sizes according to different landslide scale.</p> <p>Specifically, patch sizes vary across different areas: 32 for image segmentation in Emilia-Romagna, Italy and Gorkha, Nepal; 64 in Rio de Janeiro, Brazil; 128 in Jiuzhaigou, China and Hokkaido, Japan; and 224 in Wenchuan and Taiwan, China. All the above patches constitute LMHLD, a large-scale multi-source high-resolution heterogeneous landslide dataset.</p> <p><strong><em>LMHLD.rar</em></strong> includes all the Train, Validation, Test data used for the experiments.</p> <p>If you use our data, please cite our work published in <strong><em>IEEE Transactions on Geoscience and Remote Sensing</em></strong>. Or if you have any other questions about LMHLD, please contact us: <strong>guan.ting.liu2000@gmail.com</strong>.</p> <p><strong>Paper:</strong> Liu G, Wang Y, Chen X, et al. LMHLD: A Large-scale Multi-Source High-Resolution Landslide Dataset for Landslide Detection based on Deep Learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025. (<strong>DOI: </strong><a href="https://doi.org/10.1109/TGRS.2025.3619062" target="_blank" rel="noopener">10.1109/TGRS.2025.3619062</a>)</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.