Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites

Nanosatellites increasingly produce more data than can be downlinked within a reasonable time due to their limited bandwidth and power. Therefore, an on-board system is required to prioritize scientifically significant data for downlinking, as described by scientists. This paper determines whether n...

Full description

Saved in:
Bibliographic Details
Main Authors: Ezra Fielding, Akitoshi Hanazawa
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/11/11/888
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154828895485952
author Ezra Fielding
Akitoshi Hanazawa
author_facet Ezra Fielding
Akitoshi Hanazawa
author_sort Ezra Fielding
collection DOAJ
description Nanosatellites increasingly produce more data than can be downlinked within a reasonable time due to their limited bandwidth and power. Therefore, an on-board system is required to prioritize scientifically significant data for downlinking, as described by scientists. This paper determines whether natural language processing can be used to prioritize remote sensing images on CubeSats with more flexibility compared to existing methods. Two approaches implementing the same conceptual prioritization pipeline are compared. The first uses YOLOv8 and Llama2 to extract image features and compare them with text descriptions via cosine similarity. The second approach employs CLIP, fine-tuned on remote sensing data, to achieve the same. Both approaches are evaluated on real nanosatellite hardware, the VERTECS Camera Control Board. The CLIP approach, particularly the ResNet50-based model, shows the best performance in prioritizing and sequencing remote sensing images. This paper demonstrates that on-orbit prioritization using natural language descriptions is viable and allows for more flexibility than existing methods.
format Article
id doaj-art-29bd95484a5a4e85bcd712f69231662b
institution Kabale University
issn 2226-4310
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj-art-29bd95484a5a4e85bcd712f69231662b2024-11-26T17:42:49ZengMDPI AGAerospace2226-43102024-10-01111188810.3390/aerospace11110888Flexible Natural Language-Based Image Data Downlink Prioritization for NanosatellitesEzra Fielding0Akitoshi Hanazawa1Department of Space Systems Engineering, Kyushu Institute of Technology, Kitakyushu 804-8550, JapanDepartment of Space Systems Engineering, Kyushu Institute of Technology, Kitakyushu 804-8550, JapanNanosatellites increasingly produce more data than can be downlinked within a reasonable time due to their limited bandwidth and power. Therefore, an on-board system is required to prioritize scientifically significant data for downlinking, as described by scientists. This paper determines whether natural language processing can be used to prioritize remote sensing images on CubeSats with more flexibility compared to existing methods. Two approaches implementing the same conceptual prioritization pipeline are compared. The first uses YOLOv8 and Llama2 to extract image features and compare them with text descriptions via cosine similarity. The second approach employs CLIP, fine-tuned on remote sensing data, to achieve the same. Both approaches are evaluated on real nanosatellite hardware, the VERTECS Camera Control Board. The CLIP approach, particularly the ResNet50-based model, shows the best performance in prioritizing and sequencing remote sensing images. This paper demonstrates that on-orbit prioritization using natural language descriptions is viable and allows for more flexibility than existing methods.https://www.mdpi.com/2226-4310/11/11/888orbital edge computingartificial intelligencemachine learningnanosatelliteCubeSatprioritization
spellingShingle Ezra Fielding
Akitoshi Hanazawa
Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites
Aerospace
orbital edge computing
artificial intelligence
machine learning
nanosatellite
CubeSat
prioritization
title Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites
title_full Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites
title_fullStr Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites
title_full_unstemmed Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites
title_short Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites
title_sort flexible natural language based image data downlink prioritization for nanosatellites
topic orbital edge computing
artificial intelligence
machine learning
nanosatellite
CubeSat
prioritization
url https://www.mdpi.com/2226-4310/11/11/888
work_keys_str_mv AT ezrafielding flexiblenaturallanguagebasedimagedatadownlinkprioritizationfornanosatellites
AT akitoshihanazawa flexiblenaturallanguagebasedimagedatadownlinkprioritizationfornanosatellites