Can you create an AI model to identify landslides? Join the Landslide Detection Challenge
Dal 21.05.2025 al 04.08.2025
Landslides, triggered by natural events like heavy rainfall and earthquakes, pose significant risks to lives, infrastructure, and the environment. Effective monitoring and mapping of landslides are crucial for mitigating these risks, guiding emergency responses, and supporting resilient infrastructure planning.
New satellite technologies, combined with the frontiers opened by machine learning and artificial intelligence, are revolutionizing our ability to detect landslides. Creating an accurate detection model that leverages these innovations and is capable of being precise even in challenging conditions can radically transform emergency management. This cutting-edge approach not only allows for more timely interventions but also becomes fundamental for planning resilient infrastructure, opening up new possibilities in the prevention and mitigation of geological risks.
A groundbreaking challenge has been launched on the Zindi platform, bringing together global powerhouses in space and technology. ESA, WMO, ITU, AIforGood, the University of Cambridge, and the University of Padua have joined forces to push the boundaries of landslide detection. The goal? To develop a cutting-edge model that seamlessly integrates SAR and optical data, ensuring accurate landslide identification even in cloud-covered areas. The University of Padua's Department of Geosciences is at the forefront of this initiative, with the Machine Intelligence and
Slope Stability Laboratory, led by Prof. Filippo Catani, playing a key role in the challenge.
The challenge is open to all and it is possible to participate as an individual or in a team of up to four people. Starter notebooks and learning resources included.
The deadline for submitting your AI model is on August, 04. First, second, and third place winners will be awarded by prizes (500 CHF, 300 CHF and 200 CHF).
Don’t miss out! Learn more and register here: https://zindi.africa/competitions/classification-for-landslide-detection
