Refine
Document Type
- Preprint (2) (remove)
Language
- English (2)
Has Fulltext
- no (2) (remove)
Keywords
- Building with earth (1)
- Circular economy (1)
- Compressed earth (1)
- Decarbonization (1)
- Demolition wastes (1)
- Low-carbon construction (1)
- Machine learning (1)
- Rammed earth (1)
- Recycled materials (1)
- Sustainable construction (1)
Institute
An inter- and transdisciplinary concept has been developed, focusing on the scaling of industrial circular construction using innovative compacted mineral mixtures (CMM) derived from various soil types (sand, silt, clay) and recycled mineral waste. The concept aims to accelerate the systemic transformation of the construction industry towards carbon neutrality by promoting the large-scale adoption and automation of CMM-based construction materials, which incorporate natural mineral components and recycled aggregates or industrial by-products. In close collaboration with international and domestic stakeholders in the construction sector, the concept explores the integration of various CMM-based construction methods for producing wall elements in conventional building construction. Leveraging a digital urban mining platform, the concept aims to standardize the production process and enable mass-scale production. The ultimate goal is to fully harness the potential of automated CMM-based wall elements as a fast, competitive, emission-free, and recyclable alternative to traditional masonry and concrete construction techniques. To achieve this objective, the concept draws upon the latest advances in soil mechanics, rheology, and automation and incorporates open-source digital platform technologies to enhance data accessibility, processing, and knowledge acquisition. This will bolster confidence in CMM-based technologies and facilitate their widespread adoption. The extraordinary transfer potential of this approach necessitates both basic and applied research. As such, the proposed transformative, inter- and transdisciplinary concept will be conducted and synthesized using a comprehensive, holistic, and transfer-oriented methodology.
The main challenge in Bayesian models is to determine the posterior for the model parameters. Already, in models with only one or few parameters, the analytical posterior can only be determined in special settings. In Bayesian neural networks, variational inference is widely used to approximate difficult-to-compute posteriors by variational distributions. Usually, Gaussians are used as variational distributions (Gaussian-VI) which limits the quality of the approximation due to their limited flexibility. Transformation models on the other hand are flexible enough to fit any distribution. Here we present transformation model-based variational inference (TM-VI) and demonstrate that it allows to accurately approximate complex posteriors in models with one parameter and also works in a mean-field fashion for multi-parameter models like neural networks.