Skip to main content
The search returned 3 results
Now showing 1 - 3 of 3
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: Open Access ,

    DARE: A Reflective Platform Designed to Enable Agile Data-Driven Research on the Cloud

    The DARE platform has been designed to help research developers deliver user-facing applications and solutions over diverse underlying e-infrastructures, data and computational contexts. The platform is Cloud-ready, and relies on the exposure of APIs, which are suitable for raising the abstraction level and hiding complexity. At its core, the platform implements the cataloguing and execution of fine-grained and Python-based dispel4py workflows as services. Reflection is achieved via a logical knowledge base, comprising multiple internal catalogues, registries and semantics, while it supports persistent and pervasive data provenance. This paper presents design and implementation aspects of the DARE platform, as well as it provides directions for future development.
      76  206
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: Open Access ,

    DARE to Perform Seismological Workflows

    The DARE e-science platform (http://project-dare.eu) offers innovative tools to ease scientific workflow development and execution exploiting efficient Cloud resources. It aims to enable on-demand numerical computations and analyses, fast large dataset handling, flexible and customisable workflow pipelines and complete provenance tracking. It also integrates available e-infrastructure services (e.g. EUDAT, EIDA) and can be linked to user developed interfaces. DARE is validated via two domain-specific pilots, one from the climate modelling community and one from the seismological research field. Focusing on the latter, the EPOS Use Case is driven by urgent issues and general user needs of solid Earth Science community, following developments and application standards in the computational seismology research society. This Use Case also benefits from the pioneering experience of previous European projects (e.g. VERCE, EPOS-IP) in this framework. We present here the development of a scientific workflow to perform a quick calculation of seismic source parameters after an earthquake. The workflow requirements include HPC calculations (on local-institutional or Cloud resources), fast data-intensive processing, provenance exploitation and seismic source inverse modelling tools. The DARE platform automatically conducts the required actions optimally mapped to computational resources, linking them together by managing intermediate data. It automatically deploys the necessary environment to perform on-demand transparent computations executing a dockerised version of the numerical simulation code on a Kubernetes cluster via a web API. Other API calls allow for remote, distributed execution of dispel4py workflows, used to describe the steps for data analysis and download of seismic recorded data via EIDA Research Infrastructure services. Well established scientific python codes, such as those for waveform misfit calculation and source inversion, are thus easily implemented in this flexible and modular structure, and executed at scale. Moreover, the pilot requirement of searching and reusing multiple simulations for the same earthquake strongly benefits from customisable management of metadata and lineage through the DARE platform exploiting the integration of S-ProvFlow with dispel4py.
      85  121
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: Open Access ,

    Comprehensible Control for Researchers and Developers Facing Data Challenges

    The DARE platform enables researchers and their developers to exploit more capabilities to handle complexity and scale in data, computation and collaboration. Today’s challenges pose increasing and urgent demands for this combination of capabilities. To meet technical, economic and governance constraints, application communities must use use shared digital infrastructure principally via virtualisation and mapping. This requires precise abstractions that retain their meaning while their implementations and infrastructures change. Giving specialists direct control over these capabilities with detail relevant to each discipline is necessary for adoption. Research agility, improved power and retained return on intellectual investment incentivise that adoption. We report on an architecture for establishing and sustaining the necessary optimised mappings and early evaluations of its feasibility with two application communities.
      67  133