In-orbit demonstration of artificial intelligence applied to hyperspectral and thermal sensing from space
The DOI matches its Crossref record.
Abstract
cosine Remote Sensing is leading the first ever demonstration of on-board Artificial Intelligence (AI) applied to the combination of hyperspectral and thermal imaging. The sensing device is a miniaturized reflective optical instrument equipped with unprecedented processing capabilities. The European Space Agency (ESA) has contracted cosine Remote Sensing to highly integrate Thermal Infrared (TIR) technologies into a miniaturized Visible-Near-InfraRed (VNIR) hyperspectral imager and to fit the combined spectral channels in a volume of less than two litres. The imager is named HyperScout-2 as it will use the HyperScout-1 platform, that has flight heritage, as building block to further integrate spectral channels. HyperScout-2 is equipped with a hybrid processing platform composed of a CPU, GPU and VPU. The VPU is a state of art vision processing unit developed by Intel and is for the first time flew in space as part of HyperScout-2. HyperScout-2 will enable experimental programs to investigate the use of Artificial Intelligence for a variety of applications in the field of object detection and data inference. The first application that will be run on is cloud screening. HyperScout-2 will be used as in-orbit test-bed to benchmark the performance of such a miniaturized class of systems as well as to perform hands-on investigations to forecast the benefits of combining frequent coregistrated measurements in the VNIR and TIR from nanosatellites, with less frequent but very accurate measurements performed by institutional satellites such as the Copernicus fleet. This initiative is named PhiSat-1 and is part of the ESA EOP initiative to leverage small satellites to foster technology breakthrough developments. This contribution reports on a general description of HyperScout-2 as well as about the fast track program in which is implemented. We will also highlight the way the space asset will be exploited especially regarding the understanding of the potential of small systems deployed within small satellites constellation if integrated into ecosystems made of small and large systems. The PhiSat-1 is implemented as an enhancement of the FSSCat mission in a 6U cubesat based on Tyvak International platform integrating cosine Remote Sensing hyperspectral/thermal system. The cloud screening application is led by cosine Remote Sensing and supported by Sinergise, Ubotica and University of Pisa.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cited by
Furano, G., Meoni, G., Dunne, A., Moloney, D., Ferlet-Cavrois, V., Tavoularis, A., Byrne, J., Buckley, L., Psarakis, M., Voss, K.-O., et al. (2020) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2020.3008468 · Cited by 259
“[43] M.”
MethodTowards global flood mapping onboard low cost satellites with machine learning
Mateo-Garcia, G., Veitch-Michaelis, J., Smith, L., Oprea, S. V., Schumann, G., Gal, Y., Baydin, A. G., & Backes, D. (2021) · Scientific Reports · doi:10.1038/s41598-021-86650-z · Cited by 202
“Tens of CubeSats similar to ESA’s FSSCat mission 12 could be launched for the cost of a single conventional Earth observation satellite, with 30 CubeSats reducing the nominal revisit time from five days to around eight hours for a similar cost.”
MethodCloudscout: a deep neural network for on-board cloud detection on hyperspectral images
Giuffrida, G., Diana, L., de Gioia, F., Benelli, G., Meoni, G., Donati, M., & Fanucci, L. (2020) · Remote Sensing · doi:10.3390/rs12142205 · Cited by 176
“The aim of this mission is to demonstrate the feasibility and the usefulness in bringing AI on-board Hyperscout-2 satellite [12].”
BackgroundMethod
Metadata
- Authors
- Esposito, M., Conticello, S. S., Pastena, M., & Carnicero Dominguez, B.
- Venue
- CubeSats and SmallSats for Remote Sensing III
- Publisher
- SPIE
- Published
- 2019-08-30
- Pages
- 11
- OpenAlex
- W2970532173
- Cited by
- 42
- References
- 0
- FWCI
- 9.73
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.