Filters

Settings

Now showing1 - 10 of 11
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
    NeuralPinT
    Parallel-in-time integration (PinT) algorithms, such as Parareal, PFASST, or MGRIT, have demonstrated significant prowess in addressing time-dependent problems. However, the construction of coarse level models for these algorithms is a challenge, demanding expertise numerics, domain science, and a profound understanding of high-performance computing (HPC). The research done in this study is focussing on advancements in leveraging machine learning (ML) techniques, specifically neural operators (NOs), to offer a more generic and efficient approach to the development of effective coarse models. The established PinT algorithms necessitate the creation of coarse level models, introducing complexities that require substantial expertise and time for implementation and tuning. In contrast, the integration of ML techniques, particularly neural operators, presents an adequate way to do this. Neural operators, in their most general form, model the solution operator of partial differential equations (PDEs), mapping a set of inputs (initial conditions, boundary conditions, forcing terms, parameters). NeuralPint formulates the solution operator as a high-dimensional neural network, with parameters learned through a training procedure. The ML-based solution operators enable the iterative construction of solutions to time-dependent problems on extended time scales. By treating the solution obtained in each iteration as the initial condition for the subsequent iteration, the ML-based approach provides a versatile and efficient strategy for solving complex PDEs over extended temporal domains. While ML-based solvers may exhibit limitations in terms of accuracy when considered in isolation, their rapid evaluation times post-training present a compelling advantage. Notably, their computing patterns align seamlessly with GPU architectures, enabling efficient utilization of accelerators. This is in contrast to traditional mesh-based numerical models, which often struggle to exploit the full potential of GPU accelerators. The combination of swift execution times and reasonable accuracy positions ML-based solvers as ideal candidates for constructing effective PinT coarse models. The comonation of ML techniques with PinT algorithms not only simplifies the construction of coarse models but also addresses the computational challenges inherent in high-performance computing environments. The inherent efficiency of ML-based solvers on GPUs aligns well with the demands of PinT coarse models, providing an optimal balance between speed and accuracy. The integration of machine learning, particularly neural operators, into the realm of PinT algorithms represents a transformative approach to constructing efficient coarse models. By capitalizing on the speed and adaptability of ML-based solvers, this methodology offers a generic solution that reduces the dependence on intricate numerical expertise and accelerates the implementation and tuning process.
      44
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
      56
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
    Developing Research and InnoVation CapacitiEs in Albania and Kosovo
    The Erasmus+ CBHE DRIVE project (2020-2023) aims to strengthen the research and innovation capacities of partner universities in Albania and Kosovo. As the driving forces for innovation transformation, universities remain the most important institutions to boost the research and innovation potential and wealth of the region. Therefore, the availability of the necessary innovation environment, including institutional capabilities and academic networks, as well as the necessary knowledge and skills of university staff, is essential to ensure innovation growth and social and economic well-being in the WBC region. The DRIVE project aims to improve the research and innovation landscape of the partner universities by expanding mentoring capacities, strengthening management structures and intensifying multidisciplinary cooperation between the universities.
      55
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
    Sustainable soils by quality compost with defined properties
    The North Sea region is an area of intensive farming characterised by rapid soil degradation. Therefore, the demand for soilimprovers such as quality composts for these intensively utilised soils exist. Barriers to meet this urgent need of soil improvement are a lack of suitable and stabilized soil amendments, the absence of an alignment in demands and risks in European and national regulations, and a lack of information. The project involves researchers, compost and horticultural producers and regional authorities from five North Sea Region countries—Belgium, Denmark, Germany, Netherlands, and United Kingdom—to study local, regional, and trans-European needs and barriers. SOILCOM aims to improve the transformation of waste to quality compost, and its application to support carbon storage, water and nutrient use efficiency, productivity of horticultural and compost enterprises, and pesticide reduction. Furthermore it aims to support EU policy on circular economy.
      181
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
      85
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
      91
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
    Blue Green Infrastructure through Social Innovation
    Cities cannot cope with more frequent and intense rainfall due to climate change without rethinking their existing concepts for storm water management. Technically it means that in addition to the conventional grey infrastructure, they need blue-green solutions and infrastructure such as green corridors, permeable paving, bio-retentions or rainwater harvesting. Recent researches show that BGI benefits outweigh costs x2-x10 times (TEEB, 2015). Most cities envisage the implementation of the BGI but multiple barriers persist and implementation is hampered by the issues such as: who benefits, pays or maintains solutions. The overall objective of BEGIN is to demonstrate at target sites how cities can improve climate resilience with Blue Green Infrastructure involving stakeholders in a value-based decision- making process to overcome its current implementation barriers. The Hamburg University of Technology (TUHH) is working in close cooperation with the Agency for roads, bridges and waters (LSBG) in Hamburg. TUHH will support the LSBG to quantify the benefits of the selected BGI elements utilising numerical and physical models and tools.
      102
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
      125
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
      155
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Project, Access status: without files ,
      67