The technology case of ExtremeEarth expresses the conviction that the entire European Earth-system modelling and prediction community, targeting both fluid and solid Earth, can achieve unprecedented skill levels through a unified and concerted development of advanced information technology. These advances will transform existing, and create wholly new user communities in areas that have not yet realized the potential of such information.
The scale of data and computing needs required to realise this vision is orders of magnitudes larger than current capabilities and this requires a radical re-design of current software frameworks and hardware systems. A full integration of computing, data and connectivity is envisaged where HPC and cloud technology will converge, becoming a unique challenge and opportunity building upon current institutional, industrial as well as transnational initiatives as the EOSC and EuroHPC . To meet that challenge we will adopt a contemporary approach to software with components that are widely supported in the ICT industry and that are part of the main roadmaps of digital technology development. This way, ExtremeEarth will bring an entirely new quality to the European HPC programme, one that is fundamentally different from current exascale computing developments in East Asia and the USA. The latter are driven by a race for leadership in the Top500  list, which results in powerful supercomputers that perform extremely well on computing benchmarks, but can be very inefficient for real Earth-system applications. ExtremeEarth on the other hand, will motivate technology development that is focused on the science case and on achieving its grand challenges, thus producing tangible and significant socio-economic benefit.
ExtremeEarth will deliver a new system design of extreme-scale HPC, data and connectivity. Taking the European exascale and institutional digital infrastructures as a baseline, ExtremeEarth will co-design HPC-based platforms that are driven by our applications. It will capitalise on the convergence of HPC and cloud technologies and it will develop optimised hardware-software linkages  that make a new way of working possible for all users.
Preparing for the future requires a very different approach – one that can only be realised by a concerted effort that a technology Flagship makes possible – as it requires a focused technical development over a very long timescale exploiting application-driven co-design of both software and hardware. Furthermore this must take place in ways that integrate input from diverse communities to produce systems that effectively address their needs, yet remain agile enough to allow efficient adaptation to changing computational architectures in the future.
Data handling in ExtremeEarth represents a similarly extreme challenge in terms of both data volume and diversity. Current technologies and workflows dealing with the kind of data ExtremeEarth envisions are either unavailable or very limited in their scope and flexibility. ExtremeEarth must therefore also embark on the co-design of information and communication technology solutions for the efficient and timely handling of diverse data being produced at an unprecedented rate by both high-definition models and observational sensor networks.
Empowering new and existing user communities
To fully exploit this model-data fusion ExtremeEarth introduces the idea of the ExtremeEarthScienceCloud (EEsC). The EEsC will take full advantage of modern software technologies and exploit extreme-scale computing and big data capabilities to unburden users and communities from excessive technological challenges. The EEsC will provide the programming interface for users to interact and even steer high-definition Earth-system simulations, observational data, applications and analysis systems. This capability goes well beyond current cloud technologies. ExtremeEarth will thus realize value chains as a collaborative space, one which allows for interactions between domain scientists and application communities at all levels. This will be the ultimate technological and scientific game changer as it requires ground-breaking developments in extreme computing and data technology and a radically different way of interacting with simulations and data for scientists and users of scientific information.
To meet this objective, ExtremeEarth will perform a true end-to-end, application-driven co-design of rapidly developing digital technology with applied and computational scientists, software engineers and hardware architects based on the Earth-system application-specific requirements. Through its EEsC, ExtremeEarth will be a major driver of extreme-scale computing beyond the current European exascale programmes, and it will provide the digital innovations for future European infrastructure projects in the Earth-science domain.
 Schulthess, 2015: Programming revisited. Nature Physics, 11, 369–373.