error
Kurzer Serviceunterbruch am Donnerstag, 3. März 2026, 12 bis 13 Uhr. Sie können in diesem Zeitraum keine neuen Dokumente hochladen oder bestehende Einträge bearbeiten. Das Login wird in diesem Zeitraum deaktiviert. Grund: Wartungsarbeiten // Short service interruption on Thursday, March 3, 2026, 12.00 – 13.00. During this time, you won’t be able to upload new documents or edit existing records. The login will be deactivated during this time. Reason: maintenance work
 

Ayça Duran


Last Name

Duran

First Name

Ayça

ORCID

0000-0001-6027-2962

Organisational unit

03902 - Schlüter, Arno / Schlüter, Arno

Filters

2025 - 20262
Reset filters

Search Results

Publications 1 - 2 of 2
  • Project-Based Learning for Systemic Urban Decarbonization Through Urban Building Energy Modelling
    Item type: Conference Paper
    Schlueter, Arno; Shi, Zhongming; Meskinkiya, Maryam; et al. (2025)
    IOP Conference Series: Earth and Environmental Science
    Effective urban decarbonisation requires a systemic perspective at the intersection of technical, societal and economic challenges. Real-world problem sets are increasingly being introduced into curricula to educate future professionals and develop and strengthen the competencies needed to address such challenges. This paper discusses integrated project-based learning (PBL) designed to equip students from different academic backgrounds with the necessary competencies to address systemic urban decarbonisation. Focusing on Urban Building Energy Modelling (UBEM) using the City Energy Analyst (CEA) tool, students worked on district-scale case studies in Zürich and Shanghai. In the 13 week Integrated Design Project course (IDP), students developed subject- and method-specific skills on sustainable urban design and UBEM while honing their social and personal skills through group work, organisation and presentation. Tutor coaching, expert feedback and stakeholder interaction guided their project development. Key findings from a survey of participating students show that their self-reported understanding of urban sustainability concepts increased significantly (from an mean value of 2.95 to 4.05 on a 5-point scale), that they were able to relatively quickly apply UBEM with CEA to their use case, and that they found the approach and tool effective in addressing critical trade-offs and relationships between qualitative and quantitative factors. As we demonstrate through exemplary student work, in just six weeks, the students developed integrated urban densification strategies for the case studies that addressed urban morphology, green space development, energy demand assessment, urban renewable energy generation and district-scale supply systems. This enabled them to investigate critical trade-offs such as between solar energy generation, urban form and programme, and opportunities to further guide their design. Finally, we reflect on the strengths and weaknesses of PBL using UBEM as an approach and CEA as a tool and consider the implications and potential for wider scalability in teaching and practice.
  • Deep learning for BIPV segmentation on facades: Comparison with human annotations across facade designs
    Item type: Journal Article
    Duran, Ayça; Mirabian, Pedram; Karapiperis, Panagiotis; et al. (2026)
    Building and Environment
    Building-integrated photovoltaics (BIPV) on facades are a significant but underutilized source of solar energy in urban environments. Automating the recognition of BIPV on facades through vision based systems can help guide design recommendations and extend solar asset maps. Unlike rooftop photovoltaic (PV) systems, facade BIPV recognition is difficult due to limited visibility in overhead imagery, high visual variability, and the absence of structured datasets. This study proposes a method based on deep learning (DL) for automated segmentation of BIPV panels on building facades using street-level and web images. A new dataset comprising 400 annotated BIPV projects was created, including detailed pixel-level masks and project attributes. Two model architectures, Mask Region-based Convolutional Neural Network (Mask R-CNN) and SegFormer, as well as human baselines are evaluated. The SegFormer model outperforms Mask R-CNN in pixel-level metrics. A user study conducted with human annotators without domain-specific expertise provides comparative insight into human performance, revealing common challenges in recognizing facade BIPV. The results demonstrate that DL models, trained specifically for this task, can segment BIPV panels more accurately than mean of human annotators, with SegFormer achieving an IoU of 0.69 compared to 0.42. The user study suggests that BIPV with satin finishes, invisible cells, and a PV-to-facade ratio of more than half challenge human recognition and therefore can be prioritized in visually sensitive areas. The outputs of the segmentation model are also utilized to estimate the BIPV energy yield. The annotated dataset and models are made available to facilitate future research.
Publications 1 - 2 of 2