NASA · NASA-917 · record R0512

SAS Vision

National Aeronautics and Space Administration · GSFC: Goddard Space Flight Center

Overview

Development stage: In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: Not reported
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Science
Operational functions: No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

SAS VISION is a convolutional neural network (CNN)-based computer vision model designed to identify previously undocumented astronomical objects such as AGNs, NGCs, and stellar sources using large volumes of XMM-Newton observational data. This system fine-tunes open source CNN through transfer learning using XMM-Newton raw FITS files and their corresponding SAS pipeline-processed outputs. It performs a two-stage process: Denoising & Enhancement (using DnCNN, AutoEncoders, U-Net/W-Net, or DDPMs to preprocess and enhance noisy X-ray data), and Object Identification (through CNNs with instance segmentation (Mask R-CNN), enabling detection and classification of celestial objects. In addition to this, cross-observations will enable spatial matching of object features to confirm repeat detections. This model could enable large-scale automated cataloging of undocumented objects not present in SIMBAD, Vizier, or the databases queried by Aladin.

Expected benefits

Discovery of New Objects, Accelerates Identification tasks, Improved Catalogs

System outputs

Denoised Images, Segmentation Masks, Object Classifications, Multi-Observation Object Tracker

Technology

AI classification: Computer visionSource: Computer Vision: AI that processes and interprets visual data (e.g., images and videos).
System name(s): Not reported
Custom-developed code: Not reported
Public source code: Not reported

Sourcing

How it was built: Not reported
Vendor (as reported): Not reported
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: Not reported
Privacy Impact Assessment: Not reported
Authorization to Operate: Not reported
Demographic features: Not reported
Training and evaluation data: Not reported
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported