AWS machine learning software on D-Orbit's ION SCV-004

Ran inference on Earth observation data in orbit, and had its model settings changed in flight.

L3 Launched: confirmed by a party with no stake, or by public data. Rests on c5.
R2 Ran: own technical account. Rests on c1, c3.

Operator	D-Orbit (the satellite)
Developer	Amazon Web Services, with D-Orbit and Unibap
Host	ION SCV-004, Elysian Eleonora
Where	Earth orbit
Class	perception
Hardware	Unibap SpaceCloud iX5
Model or software	AWS edge computing and machine learning software; the models are not named in what was read
Launched	13 Jan 2022
Ran	during 2022, after first contact on 21 January
Catalogue	ION SCV-004, number 50993; matched by name: the team's paper names the carrier SCV-004

What was said, and by whom

“successfully ran a suite of AWS compute and machine learning (ML) software on an orbiting satellite, in a first-of-its-kind space experiment”

Amazon Web Services: the developer. AWS successfully runs AWS compute and machine learning services on an orbiting satellite in a first-of-its kind space experiment, Amazon Web Services. Published 29 Nov 2022 (date given in search results). Read 4 Oct 2026, in part: about six sentences of 7,900 characters.
“On January 21, 2022, the team made its first successful contact with the payload, and executed the first remote command from Earth to space.”

Amazon Web Services: the developer. AWS successfully runs AWS compute and machine learning services on an orbiting satellite in a first-of-its kind space experiment, Amazon Web Services. Published 29 Nov 2022 (date given in search results). Read 4 Oct 2026, in part: about six sentences of 7,900 characters.
“We successfully achieved the two primary goals of our experiment: perform inference and processing on data while in orbit using AWS edge capabilities, and change model configurations in flight using AWS edge service APIs.”

O'Donnell et al., the experiment's team: the experimenter. Extension of Cloud Computing to Small Satellites, Small Satellite Conference 2023 (O'Donnell and five co-authors at Amazon Web Services, the experiment's team). Published 2023 (the paper's number, SSC23-XIII-04). Read 4 Oct 2026, in part: about ten sentences of 22,800 characters, from an Internet Archive copy. Read from an Internet Archive capture of the page.
“the D-Orbit ION Satellite Carrier SCV-004, Elysian Elenora”

O'Donnell et al., the experiment's team: the experimenter. Extension of Cloud Computing to Small Satellites, Small Satellite Conference 2023 (O'Donnell and five co-authors at Amazon Web Services, the experiment's team). Published 2023 (the paper's number, SSC23-XIII-04). Read 4 Oct 2026, in part: about ten sentences of 22,800 characters, from an Internet Archive copy. Read from an Internet Archive capture of the page.
OBJECT_NAME: ION SCV-004; LAUNCH_DATE: 2022-01-13

CelesTrak satellite catalogue: a public catalogue. Satellite catalogue record 50993 (ION SCV-004), CelesTrak. Published undated (a live catalogue record; dated by when it was read). Read 4 Oct 2026, in full.

Claims to a first

First cloud company's machine learning software run on a satellite: unchecked. Worded as "first-of-its-kind", and scoped to the company's own software. Recorded as made.

Notes

The claim to a first is scoped to the company's own software. What the models detected, and how well, is not in the parts read.

Changed

Added on 4 October 2026, in the second round of reading.

Cite or share

AWS machine learning software on D-Orbit's ION SCV-004. Every AI that has run above the Kármán line, graded by evidence. Reviewed 4 Oct 2026. https://karman-si.pages.dev/r/aws-ion-scv004/

Address: https://karman-si.pages.dev/r/aws-ion-scv004/

A badge with this record's marks, at /badge/aws-ion-scv004.svg. This record as data.