fbpx Identifying anomalies on Mars Surface

Challenge solved! Mars surface anomalies detection

A group of 36 engineers and enthusiasts collaborated for two months to build and end-to-end pipeline capable of downloading images directly from the Mars Orbital Data Explorer and analyzing them using our trained U-Net model with precision scores of up to 99%.

Results and technical articles

The Martian Chronicles — Where Deep Learning meets Global Collaboration

Anomaly detection in Martian Surface — Searching for needles in a haystack!

MarsiAn-omaly Detection Through Deep Adversarial Training

A Journey from Martian Orbiters to Terrestrial Neural Networks