EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GeoCivic-Agent: A Multimodal Agentic GeoAI Framework for Spatial Understanding and Decision Support of Public Participation Data in Smart Cities

Wenfang Lu, Pinghao Luo

Fundamental Scientific Reports in Multidisciplinary Areas · 31.10.2026 · 2 (3) · 297-312

DOI: 10.66238/fsrma142 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fundamental Scientific Reports in Multidisciplinary Areas, online erschienen am 31.10.2026. Verfasst von Wenfang Lu und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of smart cities has increased the demand for intelligent and participatory urban governance, where public opinions provide valuable insights into transportation safety, environmental quality, housing conditions, and public service deficiencies. However, massive civic feedback collected from online platforms, social media, and mobile applications is often presented as heterogeneous and unstructured data, including texts, images, and geographic information, which limits the ability of existing urban analysis systems to discover spatial patterns and support planning decisions. This study proposes GeoCivic-Agent (Multimodal Agentic Geographic Artificial Intelligence Framework for Spatial Understanding and Decision Support of Public Participation Data), a novel framework that integrates Geographic Artificial Intelligence (GeoAI), Large Language Models (LLMs), Vision-Language Models (VLMs), and multi-agent reasoning for intelligent civic data analysis. The proposed framework employs a multimodal perception module, a GeoFusion Transformer for spatial-semantic representation learning, and a GIS-enhanced Retrieval-Augmented Generation (RAG) module to identify urban issues, detect spatial hotspots, and generate explainable planning recommendations. Experimental results on the multimodal urban participation dataset demonstrate that GeoCivic-Agent achieves an F1-score of 94.6% for urban issue classification, outperforming the GPT-based single-agent baseline by 2.8 percentage points. For spatial hotspot detection, the proposed framework obtains an AUC of 96.2% and reduces MAE to 0.087, showing superior capability in discovering urban concern patterns and generating reliable spatial intelligence compared with existing GeoAI and LLM-based approaches.

Zitieren

APA

Lu, W., & Luo, P. (2026). GeoCivic-Agent: A Multimodal Agentic GeoAI Framework for Spatial Understanding and Decision Support of Public Participation Data in Smart Cities. Fundamental Scientific Reports in Multidisciplinary Areas, 2(3), 297-312. https://doi.org/10.66238/fsrma142

Vancouver

Lu W, Luo P. GeoCivic-Agent: A Multimodal Agentic GeoAI Framework for Spatial Understanding and Decision Support of Public Participation Data in Smart Cities. Fundamental Scientific Reports in Multidisciplinary Areas. 2026;2(3):297-312. doi:10.66238/fsrma142

BibTeX
@article{Lu2026,
  author = {Lu, Wenfang and Luo, Pinghao},
  title = {GeoCivic-Agent: A Multimodal Agentic GeoAI Framework for Spatial Understanding and Decision Support of Public Participation Data in Smart Cities},
  journal = {Fundamental Scientific Reports in Multidisciplinary Areas},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {297--312},
  doi = {10.66238/fsrma142}
}
Kostenlos starten →