Using an advanced machine-learning algorithm, researchers in the UK and Japan have identified several promising candidate locations for the long-lost landing site of the Soviet Luna 9 spacecraft. Publishing their results in npj Space Exploration, the team, led by Lewis Pinault at University College London, hope that their model’s predictions could soon be tested using new observations from India’s Chandrayaan-2 orbiter.
In 1966, the USSR’s Luna 9 mission became the first human-made object to land safely on the moon’s surface and to transmit photographs from another celestial body. Compared with modern missions, the landing was dramatic: shortly before the main spacecraft itself struck the lunar surface, it deployed a 58-cm-wide, roughly 100-kg spherical landing capsule from above, then maneuvered away to crash at a safe distance.
Equipped with inflatable shock absorbers, the capsule bounced several times before coming to rest, stabilizing itself by unfurling four petal-like panels. Although Luna 9 operated for just three days, it transmitted a wealth of valuable data back to Earth, helping to inspire confidence in crewed space exploration, that would see humanity take its first steps on the moon just three years later.









