Life detection on Mars from orbit
Lead Research Organisation:
University College London
Department Name: Mullard Space Science Laboratory
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Organisations
People |
ORCID iD |
| Company Name | OXIA PALUS LTD |
| Description | Summary: Oxia Palus an artificial intelligence art collective. Our mission is to accelerate the adoption of artificial intelligence by artists and art conservators, so as to reconstruct the world's lost art and push the boundaries of creativity. Oxia Palus primarily produces lost artwork, by applying neural style transfer (NST) to modified x-radiographs of artwork with secondary interior artwork painted beneath a primary exterior painting. Extended: Our work is about applying a new technique in machine learning, called neural style transfer (NST), so as to create possible reconstructions of lost artwork. NST was developed by Gatys et al. in 2015, and can be used to create novel artistic work by rendering one image in the style of another. NST uses a previously trained convolutional neural network (CNN) called the VGG-19 network; a 19 layer neural network that has been trained on a large dataset of ImageNet images. Training on this large dataset of images allows the VGG-19 neural network to recognise low and high level features in images. A key part of the NST algorithm is defining and minimising the content and style cost functions (also known as error functions). The content cost function is an error between the content image and the generated image, similarly, the style cost function is an error between the style image and the generated image. Minimising the content cost function will make the generated image follow the style of the style image and minimising the style cost function will make the generated image follow the content of the content image. Once these functions are defined, we add them together to create a total cost function. We then use an optimisation algorithm to minimise the total cost function, which makes the generated image follow the content of the content image and the style of the style image simultaneously, which after several iterations creates stylised images. We use NST as a novel method of reconstructing lost artwork, by applying neural style transfer (NST) to modified x-radiographs of artwork with secondary interior artwork painted beneath a primary exterior painting. The significance of this work is that, to our knowledge, it's the first application of style transfer to x-radiographed imagery of artwork, known to have a hidden interior piece, with the aim to create a possible reconstruction of the underlying original. We believe the emergence of AI in art will significantly expand our creative horizon. We think that we're at the creative shoreline taking our first steps on land. In the field of art history, we believe AI will help by making it easier and cheaper to and reveal what lies beneath historical artwork. There are potentially thousands of underpaintings and underdrawings, each with their own story, that are hidden from world. This hidden art may hold important information about how art has developed throughout history. |
| Year Established | 2019 |
| Impact | In September 2019 Oxia Palus featured in MIT Technology Review, https://www.technologyreview.com/s/614333/this-picasso-painting-had-never-been-seen-before-until-a-neural-network-painted-it/, for reconstructing a lost Picasso, La Femme Perdue and subsequently gained worldwide press coverage, for more details see: https://www.oxia-palus.com/press. This research titled 'Raiders of the Lost Art', arXiv: https://arxiv.org/pdf/1909.05677.pdf, was recently presented at NeurIPS 2019, the world's largest AI conference, in Vancouver and achieved 3rd in NVIDIA's Top 10 AI Developer Stories of 2019, https://news.developer.nvidia.com/nvidias-top-10-ai-developer-stories-of-2019/. |
| Website | https://www.oxia-palus.com/ |
| Description | AbGradE 2018, 'Development of a Mars modified Tau-REx retrieval framework for ExoMars TGO NOMAD' talk. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | I presented the outcomes of my PhD research at the AbGradE 2018, Berlin, Germany. In this talk I presented the work of 'Development of a modified Tau-REx retrieval framework for processing the ExoMars TGO NOMAD data'. This graduate-early researcher talk was the first large talk I had given on my PhD research and acted as a stepping stone to larger more advanced audiences, e.g. established researchers. This presentation was given on 23rd September 2018. |
| Year(s) Of Engagement Activity | 2018 |
| URL | http://www.eana-net.eu/index.php?page=Abgrade/abgrade2018 |
| Description | European Planetary Science Congress 2018, 'Development of a Mars modified Tau-REx retrieval framework for ExoMars TGO NOMAD' poster presentation. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | I presented the outcomes of my PhD research at the European Planetary Science Congress 2018, Berlin, Germany. In this poster presentation I showed the work of 'Development of a modified Tau-REx retrieval framework for processing the ExoMars TGO NOMAD data'. This work was the precursor the methods paper 'Ares: A retrieval framework Mars model for ExoMars Trace Gas Orbiter NOMAD solar occultation measurements' Cann et al. (In Prep.). This poster presentation was given on 19th September 2018. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://meetingorganizer.copernicus.org/EPSC2018/EPSC2018-1018.pdf |
| Description | Foster and Partners, '2033: a Mars odyssey' talk. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | I presented the outcomes of my PhD research and Oxia Palus startup work to the group at Foster and Partners involved in the development of the Mars habitat project at Foster and Partners London Headquarters. This talk was given on 30th January 2020. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://www.fosterandpartners.com/projects/mars-habitat/ |
| Description | NASA-ESA 2018 International Summer School in Astrobiology: Biomarkers: Signs of Life Through Space, Universidad Internacional Menéndez Pelayo (UIMP), Santander, Spain. |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | I was one of 7 students selected in Europe to receive ESA Education sponsorship to attend the NASA/ESA 2018 International Summer School in Astrobiology: Biomarkers: Signs of Life Through Space and Time at Universidad Internacional Menéndez Pelayo (UIMP), Santander, Spain. The intended purpose of the summer school was to investigate biomarkers, morphologic, chemical and isotopical, that permit the discovery of biological processes. Attending this summer school enabled me to connect with NASA/ESA researchers and graduate-early career astrobiology researchers from the US and Europe. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://nai.nasa.gov/funding-and-careers/conferences-and-schools/international-summer-school/2018-in... |
| Description | NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems, NeurIPS Workshop on Machine Learning for Creativity, 'Lost Picasso' La Femme Perdue artwork presentation. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | I and my Co-founder presented the outcomes of our paper 'Raiders of the Lost Art', https://arxiv.org/pdf/1909.05677.pdf, as an artwork presentation to the machine learning community at NeurIPS 2019, Vancouver, Canada, as part of the Workshop on Machine Learning for Creativity. This work gained international media coverage, for further details see, https://www.oxia-palus.com/press. Concealed beneath Pablo Picasso's The Old Guitarist (1903-1904), hides the portrait of a woman. In 1986, through x-radiography, art conservationists made the underlying piece apparent. In 2019, by combining the techniques of neural style transfer and x-radiography, we reconstructed the lost artwork. Using a manually edited x-radiographed image of The Old Guitarist as the content image and La Vie as the style image, we applied neural style transfer to reconstruct the lost artwork; creating the lost woman, 'La Femme Perdue'. |
| Year(s) Of Engagement Activity | 2019 |
| URL | http://www.aiartonline.com/community-2019/george-cann-and-anthony-bourached/ |
| Description | Royal Astronomical Society, UK Planetary Atmospheres Meeting 2020, 'Ares - An atmospheric retrieval system for the ExoMars Trace Gas Orbiter' talk. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | I presented the outcomes of my PhD research to the planetary atmospheric sciences community at the UK Planetary Atmospheres Meeting 2020 at the Royal Astronomical Society, Burlington House, London. In this talk I present the work of a methods paper 'Ares: A retrieval framework Mars model for ExoMars Trace Gas Orbiter NOMAD solar occultation measurements' Cann et al. (In Prep.), that will be used to evaluate the sensitivity of NOMAD to trace gas species and to interpretation of solar occultation measurements, once the data is publicly released. This talk was given on 14th February 2020. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://www2.le.ac.uk/departments/physics/research/projects/uk-planetary-atmospheres-meeting-2020 |
| Description | UCL/Birkbeck, Astrobiology and Planetary Exploration (APEX) Programme, 'An atmospheric retrieval system for the ExoMars Trace Gas Orbiter' talk. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | I presented the outcomes of my PhD research as part of UCL/Birkbeck's Astrobiology and Planetary Exploration (APEX) Programme, where approximately 50 researchers, postgraduates, undergraduates and members of the general public were in attendance. In this talk, titled 'An atmospheric retrieval system for the ExoMars Trace Gas Orbiter', I presented the search for methane on Mars and the development of Ares, an atmospheric retrieval framework Mars model, that will be used to evaluate the sensitivity of the Trace Gas Orbiter NOMAD instrument to trace gas species and to the interpretation of solar occultation measurements. Two APEX talk were given, the first on 13th December 2018, the second on 17th October 2019. |
| Year(s) Of Engagement Activity | 2018,2019 |
| URL | http://www.homepages.ucl.ac.uk/~ucfbiac/APEX.htm |