Abstract. This study presents a semi-automated Level of Detail (LoD) 2 building modelling and analysis framework, implemented using fully open-source geographic information system (GIS) software, for the high-accuracy identification of rooftop photovoltaic (PV) potential in smart city digital twins. The LoD 1 building model, traditionally based on two-dimensional building footprint data used in large-scale building modelling, systematically overestimates solar energy potential as it neglects roof pitch, orientation and shading from the immediate surroundings. In this study, analyses were conducted in a high-density urban area of Birmingham, UK, using 1-metre resolution aerial LiDAR point clouds provided by the UK Department for Environment, Food and Rural Affairs (DEFRA). Throughout the process, reliance on proprietary software was completely eliminated; point cloud pre-processing, building boundary extraction using DBSCAN clustering and Concave Hull algorithms, and orthogonalisation filters were carried out entirely within the QGIS environment. Dynamic solar radiation simulations were performed using the SAGA ‘Potential Incoming Solar Radiation’ algorithm. The findings of the study provide a scalable framework for sustainable urban planning by enhancing LoD of modelled buildings and laying the groundwork for the semantic enrichment of urban digital twins. Furthermore, it generates outputs that provide concrete support to end-users, thereby helping achieve global net-zero targets.
Muhammed Yahya Bıyık, M. Mete· The International Archives o...· 0 citations
Abstract. Natural and technological disasters continue to threaten communities, infrastructure, and the environment, and the cascading nature of contemporary risks complicates their assessment. This study presents a disaster risk analysis model coupling Geographic Information Systems (GIS), ensemble machine learning, and AI-driven interpretation tools, collectively termed GeoAI, to support multi-hazard risk assessment, resilience planning, and citizen-oriented risk communication. Rather than building isolated models per hazard, the framework applies a single, modular pipeline consistently across flood, wildfire, earthquake, landslide, drought, and urban heat island hazards. Hazard, vulnerability, and exposure layers are derived from open geospatial datasets and processed in QGIS, after which Random Forest and XGBoost classifiers generate hazard and vulnerability maps validated using AUC-ROC, F1-score, and Cohen's Kappa. A distinctive component is an AI agent built on Large Language Models (LLMs) and the Model Context Protocol (MCP), which queries structured risk databases and produces region-specific narrative risk reports in natural language. Outputs are delivered through a web-based platform with an MCP-connected chatbot, lowering the barrier to understanding complex risk information for experts and the public. The model was tested in Türkiye's Marmara Region, which is important due to its dense population, heavy industry, and earthquake risk along the North Anatolian Fault. The pilot showed good results: XGBoost performed better than the baseline models, and the LLM-based interpretation layer gave clear, well-grounded outputs. The framework offers a scalable, open, interoperable approach linking spatial analytics, machine learning, and generative AI for evidence-based disaster risk reduction.
M. Mete, Muhammed Yahya Bıyık, Zeynep Ceyda Karakaya· The International Archives o...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
