Apply to the BigSkyEarth Training School 2017: Visualization for large scale analytics

Apply to the BigSkyEarth Training School 2017: Visualization for large scale analytics

BigSkyEarth is organizing a Training School on “Visualization for large scale analytics” to be held at the University of Central Lancashire, UK, on April 3-8, 2017. A diverse set of key practitioners from the astronomy, the Earth observation and the computer science domains will be participating in the School, contributing the perspectives of both the academic and the industrial sector. Grants will be made available by the Action for a number of students.

The objective of COST Action TD1403 BigSkyEarth is to bridge gaps in available methodologies for scalable ‘big data’ analytics and to frame a common long term agenda between astronomy and Earth observation. Effective visualization constitutes a key component of analytical workflows, since it allows producing rich characterizations of both the large scale statistics and the fine details of a dataset by leveraging the strengths of human vision together with those of large scale computing systems.

Past editions of the Training School

The first edition of the BigSkyEarth Training School took place at the German Aerospace Center facilities in Oberpfaffenhofen, Germany, from the 4th to the 9th of April 2016. It gathered 30 researchers for hands-on training on Big Data analytics in astronomy and Earth observation with six expert instructors from the EU and the USA. The training material from the school has been published and is freely available online.

Eligibility Rules

Applicants can be PhD students or PhD holders from any country.
Only applicants from BigSkyEarth countries and institutions will be eligible for the financial support provided by BigSkyEarth (see the list of countries and institutions below). Special considerations will be given to supporting COST policies on promoting gender balance, enabling Early Career Investigators (ECI) and broadening geographical inclusiveness.

Costs and Fees, Financial Support

  • No registration fee is considered for participation in the school.
  • Participants should anticipate costs of travel, accommodation and meals. The estimated costs, besides travel, are ~80EUR/night for bed&breakfast accommodation and ~10EUR/day for dinner. Vouchers will be given out by the organizer to Training School participants to enable everyone to purchase food from the various University of Central Lancashire on campus canteens during lunchtimes.
  • Recommended hotels close to the venue and the Railway Station.:
    Legacy Hotels – Preston: Next door to University of Central Lancashire (UCLAN)  (Mention the BigSkyEarth training school and   Nuala Jones from UCLAN as a contact person to get the rate of £67.00 Bed and Breakfast per night)
    Premier Inn – Preston: 8 minute walk from UCLAN
    Holiday Inn – Preston: 20 minute walk from UCLAN.
  • The BigSkyEarth COST Action will provide 20 grants for selected participants who are coming from institutions in: Austria, Belgium, Bulgaria, Bosnia and Herzegovina, Croatia, Czech Republic, Denmark, Estonia, Finland, France, fYR Macedonia, Germany, Greece, Hungary, Ireland, Israel, Italy, Lithuania, Malta, the Netherlands, Poland, Portugal, Romania, Serbia, Slovakia, Slovenia, Spain, United Kingdom. Members of the Byurakan Astrophysical Observatory from Armenia are also eligible for grants.
    Grants do not necessarily cover all expenses related to attending the Training School, but they should cover the majority of the overall costs of travel, accommodation and meal expenses.

Venue / How to reach the venue

The Jeremiah Horrocks institute (JHI) is based in Preston, UK. It is part of the University of Central Lancashire, which has developed and evolved over time to become the fifth largest university in the UK. The Institute was established in 1993 as the Centre for Astrophysics and grew in 2012 to become the Jeremiah Horrocks Institute for Mathematics, Physics and Astronomy. The JHI exists to carry out teaching in all of these areas, as well as to pursue research into analytical acoustics, non associative algebras, model theory and its applications, theoretical and laboratory-based physics, and the astrophysics of stars, galaxies and the Universe.

How to reach the venue:

  • By plane: the best airport to fly into would be Manchester as there is a direct train from Manchester airport to Preston.
  • By train:  the Railway Station in Preston is about 15 minute walk from the UCLAN campus. Walk out of the main entrance to the train station, go to the top of the road and turn right were you will see a Swintons shop in the distance, cross over the road to Reeds Rains shop and then go down Corporation Street. You will see a Staples and Wynsors shop in the distance, partially covered by trees. Walk up the road past Wynsors to the traffic lights, walk across the road and keep walking straight until you come to the 2nd side road to your left, turn left and you will see Foster Building in front of you. This is the main entrance for UCLAN.
  • Campus map: download here the map.

List of important dates

  • Deadline for applications: March 6, 2017.
  • Candidate selection: days after their submission, until the quota is filled or the deadline expires.
  • Training School: April 3-8, 2017.

Selection Criteria

Candidates will be evaluated based on their proposed research project and their motivation letter. Again, special considerations will be given to supporting COST policies on promoting gender balance, enabling Early Career Investigators (ECI) and broadening geographical inclusiveness.

How to Apply and Acceptance Process

  • Applicants should prepare:
    • A short CV.
    • A list of publications.
    • A short (maximum one page) description of the applicant’s research project that would benefit from this Training School.
    • A short (maximum one page) description of the background knowledge of topics covered by this Training School and motivation for participating at the school.
  • Students applying for a grant support from BigSkyEarth will be requested to specify the travel route and an estimate of the travel costs.
  • Applicants will be evaluated based on their own project proposals.
  • Organizers will cluster, adapt and merge student proposals into manageable units.
  • Students are expected to extensively study online material prior to attending.

The application documents should be sent to Marco Quartulli at <[email protected]>.

Short description of objectives

Challenges are similar in astronomy and Earth Observation, with signal processing, statistics, machine learning, and computer science as the common denominator. The Training School aims at boosting the communication within and between disciplines and applications areas by propagating and advancing relevant common solutions developed within Big Data analysis and management research and industrial environments.

The goal is to contribute with a valuable know-how encompassing from sensor and data modelling, features extraction and metadata, information representation, data structures, pattern recognition, statistical/machine learning, data analytics, advanced visualisation, to data mining and KDD. Besides, specific computer science topics will be addressed as particular programming techniques, data structures in large databases, cloud computing, and related topics. The key aspect will be addressing all these topics in synergy to set in a logical interdisciplinary framework building bridges between diverse areas.

Topics and general programme

The general structure of the material will be as follows:

  • Introduction and objectives
  • Basics
    – Basics of perception
    – Grammars of graphics
    – Animation and interaction
    – The visualization pipeline
    – Quantitative performance evaluation and benchmarking for visualization
    – Open source frameworks for large scale visualization
  • Data warehousing for visualization
    – Pre-processing and data cubes
    – Key data structures
    – Indexing and trees for higher dimensionalities
    – Data bases for analytic and visualization
    – Visual and SQL algebras: mappings visual queries to DBs
  • Processing for visualization
    – Real time big data analytics for visualization
    – Performance optimization and VLOD from the sample to the semantic space
    – Parallel architectures and GPGPUs
    – Deep learning interpretability and visualization
  • Interaction and immersive environments
    – Virtual reality advancements from gaming to data science
  • Applications and examples
    – Visual analytics of diverse attribute sets in multiple cohorts: an example from medicine
    – Visual analytics of big geospatial and geo-temporal data
    – CBIR VR caves

Current list of instructors and speakers

Laurent Noel, University of Central Lancashire, UK

Laurent Noel is a specialist in high performance 3D visualisation and GPU techniques, with a background as the technical director of a games development studio. He is a senior lecturer for games development courses at the University of Central Lancashire and a member of the European Space Agency Gaia mission CU9 visualisation team.

Maarten Breddels, University of Groningen, the Netherlands

Maarten Breddels is a postdoctoral researcher at the Kapteyn Astronomical Institute at the University of Groningen. He is an astrophysicist and  the author of vaex – a python visualization library for exploration of big tabular data, which can process more than a billion objects per second on a single computer.

Dimitris Marmanis, German Aerospace Center (DLR), Germany

Dimitris is a doctoral researcher at DLR working on machine learning in image analysis , urban extent modelling, building detection, and DEM Processing.

Deepak Mahtani, Pivigo, UK
Deepak has recently finished his PhD in astronomy where he was exploring exoplanet atmospheres. He then took part in the Science to Data Science program run by Pivigo, from which he went onto work for a leading gambling company as an insight analyst. After moving on from that role, he is now the community manager at Pivigo. His role is to talk to graduate students about roles in data science, how to make the transition and how Pivigo can help make the transition.
Victor Debattista, University of Central Lancashire, UK

Victor is a computational astrophysicist interested in the formation and evolution of galaxies. He leads the Galaxy Dynamics Group at the Jeremiah Horrocks Institute of the University of Central Lancashire. His current main research interests are related to the Milky Way, learning how the disc evolves, how the bulge formed, and how well the stellar halo can be used to understand the shape of the dark matter halo.

 Arne-Jørgen Berre, SINTEF, Norway

Arne-Jørgen Berre is chief research scientist at SINTEF and associate professor II in Informatics at the University of Oslo.

Riccardo Ferrara, Advanced Computer Systems ACS, Italy

Riccardo Ferrara works since 2001 on SAR and Optical Earth Observation applications, such as the development of in house SAR multi-mission SAR processor (Generic ACS SAR Processor, GASP) and Optical Processors for LANDSAT and the Algerian ALSAT-1B at Advanced Computer Systems ACS in Rome.

Davide Critico, Advanced Computer Systems ACS, Italy

Davide Tiriticco works at Advanced Computer Systems ACS on the design and the development of high performance parallel/concurrent algorithms. Since 2013 he has worked on several EO projects such as the design and development of a Real-Time Multi-GPU Accelerated ωK-Algorithm for Stripmap SAR data, based on the in-house CPU-based SAR processor (Generic ACS SAR Processor, GASP).

Marco Tartaglia, Advanced Computer Systems ACS, Italy

Marco was born in Rome (Italy) in 1966. He got his master degree in Computer Science from the University of Pisa in 1990. He has a long experience in the management and development of innovative real-time graphics projects. He has applied his know how in different fields, including real-time visualization of satellite data, very large virtual reality theatre installations (ESA-Esrin VRT – http://vrt.esrin.esa.int/tiki-index.php), mobile environment with applications like Cryosat for iPhone/iPad (https://itunes.apple.com/it/app/esa-cryosat/id484020380?mt=8), virtual reality and augmented reality experiences. He is currently the head of the Virtual Reality Division at Advanced Computer Systems (http://acsstudio.acsys.it).

quartulli_smallMarco Quartulli, Vicomtech-IK4, Spain
Marco has worked at Advanced Computer Systems, Italy from 1997 to 2010 on remote sensing ground segment engineering, image analysis and archive mining for ESA and national space agencies. From 2000 to 2003, he was with the Image Analysis Group at the Remote Sensing Technology Institute of the German Aerospace Center (DLR) in Germany, working on metric resolution synthetic aperture radar image understanding in urban environments and content-based image retrieval. Since 2010, he has joined the TV & Media department of Vicomtech-IK4 in Spain. He is the co–chair of the Big Sky Earth EU COST Action dedicated to Big Data management and analytics methodologies in remote sensing and astronomy.

Scientific Organizing Committee

  • Chair: Marco Quartulli, Vicomtech, Spain
  • Members of the BigSkyEarth Management Committee: see the list HERE.

WHAT IS BIGSKYEARTH?

With the current emergence of Terabyte(TB)-scale astronomical and Earth observation systems, the traditional approach to basic functions such as data searching, analytics or visualization are becoming increasingly difficult to handle. Simple database queries can result now in data subsets so large that they are incomprehensible, slow (or even impossible) to handle, and impossible to visualize with commodity visualization tools. Astronomy and remote sensing complement each other, as they are on the quest for new Big Data interpretation capabilities: both disciplines have peculiar data, typical data processing and analysis chains, and specific models to be fed with data. However, both disciplines lack the capabilities for easily accessible semantics-oriented browsing (usage of higher level descriptive expressions) in large data archives. Therefore, joint efforts to design and develop innovative Big Data tools should help users in many different fields and set new standards for many communities. This has identified several broad challenges to this line of reasoning that need multidisciplinary approach through international networking of experts and professionals. These challenges are then channelled into Action Objectives:

  • Challenge A: Digital curation and data access
  • Challenge B: New frontiers in visualization
  • Challenge C: Adaptation to new high performance computing (HPC) technologies
  • Challenge D: New generation of scientists in the age of interdisciplinarity

For further details, please see the description of the Action in its Memorandum of Understanding.