Deepika Raghu


Last Name

Raghu

First Name

Deepika

ORCID

0000-0003-0725-6415

Organisational unit

09750 - De Wolf, Catherine / De Wolf, Catherine

Filters

2022 - 202512
Reset filters

Search Results

Publications 1 - 10 of 12
  • India’s Informal Reuse Ecosystem Towards Circular Construction
    Item type: Conference Paper
    Raghu, Deepika; De Wolf, Catherine (2024)
    Sustainable Development Goals Series ~ Design for Rethinking Resources
    As countries continue to develop, the amount of construction and demolition waste generated is exponentially increasing. There is an urgent need to move from linear, take-make-waste systems to more circular systems that extend materials lifespans. India is known for its material reuse and recycling businesses. Currently, most of these businesses are run locally and do not involve any government registration but they significantly contribute to the economic growth of the country. Despite the importance of this informal sector, there is still not enough understanding of how they operate. This paper examines the processes and people involved in reusing construction elements in Mumbai and Bangalore, and their current models of resource procurement and trade. Field visits and interviews were conducted to understand through whom materials are transferred in the informal ecosystem, what types of materials and quantities can be currently procured in informal supply chains, what the storage practices are, and how reusable construction elements are retrieved and processed. A qualitative content analysis method helped to understand the informal material reclamation processes in India. Findings show that although a robust informal material reuse ecosystem exists across India, organisation and governmental policies are needed for effective contribution towards sustainable development goals and a circular economy.
  • Predicting recoverable material stock in buildings: using machine learning with demolition audit data as a case study
    Item type: Conference Paper
    Kobylinska, Natalia; Raghu, Deepika; Gordon, Matthew; et al. (2023)
    Computing in Construction ~ Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference
    Early specification of materials in buildings before their demolition could foster reuse in the construction industry. Studies have already shown the usefulness of machine learning in demolition waste estimation; however, application to real-world datasets is still limited. This study tests the feasibility of predicting recoverable material stock in the local context of the city of Zurich. The results show promise for the overall approach, although training models by using a small and heterogeneous dataset poses challenges. Therefore, we conceptualized an improved demolition data collection, processing, and dissemination. The resulting framework could help researchers and authorities in urban material stock estimation.
  • Enabling Component Reuse From Existing Buildings Using Machine Learning - Using Google Street View to Enhance Building Databases
    Item type: Conference Paper
    Raghu, Deepika; Markopoulou, Areti; Marengo, Mathilde; et al. (2022)
    CAADRIA ~ Proceedings of the 27th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2022)
    Intense urbanization has led us to rethink construction and demolition practices on a global scale. There is an opportunity to respond to the climate crisis by moving towards a circular built environment. Such a paradigm shift can be achieved by critically examining the possibility of reusing components from existing buildings. This study investigates approaches and tools needed to analyse the existing building stock and methods to enable component reuse. Ocular observations were conducted in Google Street View to analyse two building-specific characteristics: (1) façade material and (2) reusable components (window, doors, and shutters) found on building facades in two cities: Barcelona and Zurich. Not all products are equally suitable for reuse and require an evaluation metric to understand which components can be reused effectively. Consequently, tailored reuse strategies that are defined by a priority order of waste prevention are put forth. Machine learning shows promising potential to visually collect building-specific characteristics that are relevant for component reuse. The data collected is used to create classification maps that can help define protocols and for urban planning. This research can upscale limited information in countries where available data about the existing building stock is insufficient.
  • D5 digital circular workflow: five digital steps towards matchmaking for material reuse in construction
    Item type: Journal Article
    De Wolf, Catherine; Byers, Brandon S.; Raghu, Deepika; et al. (2024)
    npj Materials Sustainability
    The intersection of digital transformation and circular construction practices presents significant potential to mitigate environmental impacts through optimised material reuse. We propose a five-step (D5) digital circular workflow that integrates these digital innovations towards reuse, validated through real-world case studies. We assessed a variety of digital tools for enhancing the reuse of construction materials, including digital product passports, material classification assisted by artificial intelligence (AI), reality capture, computational design, design inspired by generative AI, digital fabrication techniques, extended reality, and blockchain technology. Using action research through a multiple case study approach, we disassembled several buildings that were set for demolition and subsequently designed and executed construction projects using the salvaged materials. Our findings indicate that digital transformation for detection, disassembly, distribution, design, and finally deployment significantly support the application of circular economy principles. We demonstrate the potential of the proposed workflow for industry implementation and scalability.
  • Assessing the Repair and Reuse Potential of Postwar, System Based Concrete Buildings in Switzerland
    Item type: Conference Paper
    Önalan, Beril; Raghu, Deepika; De Wolf, Catherine; et al. (2025)
    Lecture Notes in Civil Engineering ~ 4th fib International Conference on Concrete Sustainability (ICCS2024)
    In Switzerland, many postwar concrete buildings constructed using system based methods face premature demolition. Comprehensive knowledge gap on these prefabricated buildings hinders informed decision-making on repair and reuse strategies, which seek to preserve or re-purpose building components to minimize the need for raw materials. This paper introduces an assessment matrix that considers structural, environmental, historical and economic values for a multi-faceted evaluation of the repair and reuse potential of these structures. The matrix was applied to eight representative buildings in Zurich. The findings highlight the effectiveness and limitations of the assessment criteria for evaluating system based buildings and can guide researchers, practitioners, and governmental authorities. The proposed matrix seeks to extend the lifespan of postwar concrete buildings through repair and reuse while advancing the principles of a circular economy within the built environment.
  • Data requirements and availabilities for material passports: A digitally enabled framework for improving the circularity of existing buildings
    Item type: Journal Article
    Çetin, Sultan; Raghu, Deepika; Honic-Eser, Meliha; et al. (2023)
    Sustainable Production and Consumption
    Passports for circularity, e.g., digital product passports and material passports (MPs), have gained recognition as essential policy instruments for the Circular Economy goals of the European Union. Despite the growing number of approaches, there is a lack of knowledge about the data requirements and availabilities to create MPs for existing buildings. By deploying a mixed-method research design, this study identified the potential users and their data needs within the context of European social housing organisations. Three rounds of validation interviews with a total of 38 participants were conducted to create a data template for an MP covering maintenance, renovation, and demolition stages. This data template was then tested in a case study from the Netherlands to determine critical data gaps in creating MPs, including, but not limited to the composition of materials, presence of toxic or hazardous contents, condition assessment, and reuse and recycling potential of a product. Finally, an MP framework is proposed to address these data gaps by utilising the capabilities of enabling digital technologies (e.g., artificial intelligence and scanning systems) and supportive knowledge of human actors. This framework supports further research and innovation in data provision in creating MPs to narrow, slow, close, and regenerate the loops.
  • Innovations Practitioners Need for Circularity in the Swiss Architecture, Engineering, and Construction Sector
    Item type: Monograph
    De Wolf, Catherine; Raghu, Deepika; Sentic, Anton; et al. (2023)
    Cirkla
    Although widely recognized as imperative for reducing global emissions and the amount of waste generated by the architecture, engineering, and construction (AEC) sector, a large-scale shift from a linear to a circular economy has not yet happened in practice. This paper highlights practitioners’ needs for implementing circularity in the AEC sector in Switzerland, and how digital platforms could support it. We hosted two workshops with industry practitioners in the Swiss AEC sector to find out their needs from academia, government, and industry to implement such a shift. The first workshop revealed a need for digital reuse platforms, so we focused a second workshop specifically on digital platforms. Results from the second workshop made clear the need for better practices of gathering data and integrating platforms. Financial incentives, social innovation, policy measures, and digital tools were also identified as necessary to increasing circularity in the sector. Our findings reveal the promising potential of digital technologies and stakeholders’ networks to better capture data on building products and methods for extending their life cycle.
  • Digitalizing Existing Buildings: Moving Towards Circularity using Big Data and Machine Learning
    Item type: Other Conference Item
    Raghu, Deepika; De Wolf, Catherine (2022)
  • Towards a ‘resource cadastre’ for a circular economy – urban-scale building material detection using street view imagery and computer vision
    Item type: Journal Article
    Raghu, Deepika; Bucher, Martin; De Wolf, Catherine (2023)
    Resources, Conservation and Recycling
    The lack of data on existing buildings hinders efforts towards repair, reuse, and recycling of materials, which are crucial for mitigating the climate crisis. Manual acquisition of building data is complex and time-consuming, but combining street-level imagery with computer vision could significantly scale-up building materials documentation. We formulate the problem of building facade material detection as a multi-label classification task and present a method using GIS and street view imagery with just a few hundred annotated samples and a fine-tuned image classification model. Our method shows strong performance with macro-averaged F1 scores of 0.91 for Tokyo, 0.91 for NYC, 0.96 for Zurich, and 0.93 for the merged dataset. By utilizing open-access and non-proprietary data, our method can be scaled-up step by step to a global level. We make our in the wild dataset publicly available as the Urban Resource Cadastre Repository to encourage future work on automatic building material detection.
Publications 1 - 10 of 12