A global rockfall map of the Moon powered by AI and Big Data

Under certain conditions, meter to house-sized boulders fall, jump, and roll from topographic highs to topographic lows, a landslide type termed rockfall. On the Moon, these features have first been observed in Lunar Orbiter photographs taken during the pre-Apollo era. Understanding the drivers of lunar rockfall can provide unique information about the seismicity and erosional state of the lunar surface, however this requires high resolution mapping of the spatial distribution and size of these features. Currently, it is believed that lunar rockfalls are driven by moonquakes, impact-induced shaking, and thermal fatigue. Since the Lunar Orbiter and Apollo programs, NASA’s Lunar Reconnaissance Orbiter Narrow Angle Camera (NAC) returned more than 2 million high-resolution (NAC) images from the lunar surface. As the manual extraction of rockfall size and location from image data is time intensive, the vast majority of NAC images have not yet been analyzed, and the distribution and number of rockfalls on the Moon remains unknown. Demonstrating the potential of AI for planetary science applications, we deployed a Convolutional Neural Network in combination with Google Cloud’s advanced computing capabilities to scan through the entire NAC image archive. We identified 136,610 rockfalls between 85°N and 85°S and created the first global, consistent rockfall map of the Moon. This map enabled us to analyze the spatial distribution and density of rockfalls across lunar terranes and geomorphic regions, as well as across the near- and farside, and the northern and southern hemisphere. The derived global rockfall map might also allow for the identification and localization of recent seismic activity on or underneath the surface of the Moon and could inform landing site selection for future geophysical surface payloads of Artemis, CLPS, or other missions. The used CNN will soon be available as a tool on NASA JPL’s Moon Trek platform that is part of NASA’s Solar System Treks (trek.nasa.gov/moon/).