Landslide Detection in Real-Time Social Media Image Streams
This addresses the need for timely and accurate landslide information for disaster response and management, though it is incremental as it builds on existing AI and social media trends.
The paper tackled the problem of lacking global landslide data by developing a computer vision model to detect landslides in real-time social media image streams, achieving deployment capability for supporting global susceptibility maps and emergency response.
Lack of global data inventories obstructs scientific modeling of and response to landslide hazards which are oftentimes deadly and costly. To remedy this limitation, new approaches suggest solutions based on citizen science that requires active participation. However, as a non-traditional data source, social media has been increasingly used in many disaster response and management studies in recent years. Inspired by this trend, we propose to capitalize on social media data to mine landslide-related information automatically with the help of artificial intelligence (AI) techniques. Specifically, we develop a state-of-the-art computer vision model to detect landslides in social media image streams in real time. To that end, we create a large landslide image dataset labeled by experts and conduct extensive model training experiments. The experimental results indicate that the proposed model can be deployed in an online fashion to support global landslide susceptibility maps and emergency response.