A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence

Pennington, Catherine; Bossu, Rémy; Ofli, Ferda; Imran, Muhammad; Qazi, Umair; Roch, Julien; Banks, Vanessa

doi:10.1016/j.ijdrr.2022.103089

Cited by 15 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We envisage that additional improvements can be reached in the short term involving topics beyond the field of EO and landslide research, such as Citizen Science. Data mining from news and social media is indeed a promising support to constrain time and spatial location where satellite data can be analysed (Pennington et al 2022). Having rapid information on landslide events is a key factor, especially during disaster response activities when emergency responders need information on safe/unsafe areas and where support needs to focus.…”

Section: Discussionmentioning

confidence: 99%

Mapping landslides from space: A review

Novellino,

Pennington,

Leeming

et al. 2024

Landslides

View full text Add to dashboard Cite

Landslide hazards have significant social, economic, and environmental impact. This work provides a critical review of the main existing literature using satellite data for mapping landslides. We created and examined an extensive bibliographic database from Web of Science (WoS) consisting in 291 outputs from > 1,000 authors who studied almost 700,000 landslides across all continents, for a total of 52 countries represented with China and Italy on top of the list with more authors. The outputs are equivalent to ~ 5% of the whole landslide-related production for the period 1996–2022, with a 600% increase in the number of papers after 2014 driven by the availability of Sentinel-1 and Sentinel-2 data. Analysis of the geographical location across the 66 different countries analysed shows that, within the total number of contributions, the satellite imagery was used to detect and map two main types of landslides: flows and slides. When specified in the manuscripts, the events have been triggered by rainfall (104 cases), earthquakes (32 cases), or both (17 cases). Slope instabilities in these areas were predominantly identified through manual detection (40%); but since 2020, the advent of artificial intelligence is suppressing all other techniques. Despite the undisputed progress of EO-based landslide mapping over the last 26 years, which makes it a consolidated tool for many landslide-related applications, challenges still remain for an effective and operational use of EO images for landslide detection and mapping, and we provide a perspective for future applications considering the existing and the planned SAR satellite missions.

show abstract

Section: Discussionmentioning

confidence: 99%

Mapping landslides from space: A review

Novellino,

Pennington,

Leeming

et al. 2024

Landslides

View full text Add to dashboard Cite

show abstract

“…Also, the combination of automatic analysis of images contained in posts and the collaboration of human-based computing has been discussed by several authors in the literature [5]- [7]. For automatic analysis of images, many recent approaches are based on AI and, in particular, neural networks [8], [9]. Hybrid deeplearning and crowdsourcing approaches were analyzed as well [10].…”

Section: Related Workmentioning

confidence: 99%

“…Social media presents a huge potential to provide key information for monitoring SDGs and supporting decision makers. Thanks to their ability to provide timely information about ongoing events [9], [11], [12], their role has been studied in several contexts, e.g., earthquakes [13], demonstrating how this timeliness can help prevent further losses. The EU Crowd4SDG project has explored the potential of social media to provide key statistics and local indicators [14] based on lessons learned from case studies for SDG monitoring.…”

Section: Related Workmentioning

confidence: 99%

“…Some of the provided classifiers are off-the-shelf, while others are custom. In VisualCit, state-of-the-art object classifiers are available 9 so that queries can be made about the presence of an object (e.g. a person, automobile, etc.)…”

Section: Selecting and Filtering Data: Visualcit 1) Filteringmentioning

confidence: 99%

“…FIGURE 5: VisualCit architecture for selecting filters and annotating geolocations. 9 Currently, DETR and YOLOv5 10 PlacesCNN, trained on the Places365 database 11 NSFW means "not suitable for viewing at most places of employment" according to the Merriam-Webster online dictionary.…”

Section: Selecting and Filtering Data: Visualcit 1) Filteringmentioning

confidence: 99%

See 2 more Smart Citations

A Citizen Science Approach for Analyzing Social Media With Crowdsourcing

et al. 2023

View full text Add to dashboard Cite

Social media have the potential to provide timely information about emergency situations and sudden events. However, finding relevant information among the millions of posts being added every day can be difficult, and in current approaches developing an automatic data analysis project requires time and technical skills. This work presents a new approach for the analysis of social media posts, based on configurable automatic classification combined with Citizen Science methodologies. The process is facilitated by a set of flexible, automatic and open-source data processing tools called the Citizen Science Solution Kit. The kit provides a comprehensive set of tools that can be used and personalized in different situations, particularly during natural emergencies, starting from images and text contained in the posts. The tools can be employed by citizen scientists for filtering, classifying, and geolocating the content with a human-in-the-loop approach to support the data analyst, including feedback and suggestions on how to configure the automated tools, and techniques to gather inputs from citizens. Using flooding scenario as a guiding example, this paper illustrates the structure and functioning of the different tools proposed to support citizens scientists in their projects, and a methodological approach to their use. The process is then validated by discussing three case studies based on the Albania earthquake of 2019, the Covid-19 pandemic, and the Thailand floods of 2021. The results suggest that a flexible approach to tools composition and configuration can support a timely setup of an analysis project by citizen scientists, especially in case of emergencies in unexpected locations.

show abstract

Community-Based Landslide Disaster Mitigation on the Northern Slope of “Telaga Lele” Hill, Banjarnegara Regency, Indonesia

Setiawan,

Tanjung

2024

Advances in Natural and Technological Hazards Research

View full text Add to dashboard Cite

A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence

Cited by 15 publications

References 50 publications

Mapping landslides from space: A review

Mapping landslides from space: A review

A Citizen Science Approach for Analyzing Social Media With Crowdsourcing

Community-Based Landslide Disaster Mitigation on the Northern Slope of “Telaga Lele” Hill, Banjarnegara Regency, Indonesia

Contact Info

Product

Resources

About