Science

Forecasting air drag with deep learning helps predict when uncontrolled satellites and rocket stages fall to Earth

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 16/10/2026, 14:55:25 UTC.

Briefings

A Soviet spacecraft Cosmos-482 launched in 1972 failed to reach Venus and remained in orbit for 53 years before crashing in the Indian Ocean in 2025. Space agencies and research groups forecasted its fall location, and Roscosmos confirmed it landed west of Jakarta. The study demonstrates how deep learning can predict uncontrolled satellite impacts, though the specific model details are not provided.

Key points

• Cosmos-482 was launched in 1972 and remained in orbit for 53 years before crashing in the Indian Ocean in 2025.
• Space agencies and research groups forecasted the crash location, and Roscosmos confirmed the landing site west of Jakarta.

Context

This case study illustrates how deep learning models can forecast uncontrolled satellite impacts, providing a method for predicting where objects like Cosmos-482 will fall to Earth.

Limitations

The evidence is limited to the specific case of Cosmos-482. The study does not provide details on the deep learning model used, nor does it include data on other similar events or long-term trends.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 16/10/2026, 19:55:36 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeifnizri35hdda5kdv7kmlfw4mqxtw7zc5ihi4ztgtdqmpwmzyww2e