Agentic and Generative AI for Spatial Data Science: Toward Intelligent, Interactive, and Predictive Urban Systems

Topic Information

Dear Colleagues,

This Topic aims to bring together cutting-edge research on the integration of agentic artificial intelligence and generative AI to enable next-generation urban systems that are intelligent, interactive, and predictive.

With the rapid advancement of large language models (LLMs), Foundation models (FMs), multimodal generative models, and autonomous AI agents are evolving from static data representations into dynamic, decision-support systems capable of simulation, reasoning, and real-time adaptation.

This Topic seeks to explore how these emerging AI paradigms can enhance the automation, scalability, and usability of spatial data science across complex urban environments, including infrastructure systems, transportation networks, environmental monitoring, and disaster management. We invite original research articles, reviews, and case studies that address, but are not limited to, the following topics:

1. Agentic AI for Digital Twins

• Autonomous AI agents for simulation orchestration and workflow automation;
• LLM-based planning, reasoning, and decision-making in digital twin systems;
• Multi-agent systems for urban operations and infrastructure management;
• Human–AI collaboration and interactive decision support systems.

2. Generative AI in Urban Modelling and Simulation

• Generative models for synthetic urban data, scenarios, and environments;
• AI-driven simulation of complex urban processes (e.g., mobility, energy, fire spread, climate impacts);
• Surrogate modelling and hybrid physics–AI approaches for scalable simulations;
• Multimodal generation (text, image, 3D, spatiotemporal data) for urban systems.

3. AI-Enhanced 3D modelling and geovisualization

• Integration of LLMs, retrieval-augmented generation (RAG), and knowledge graphs in cartographic applications;
• Scalable and distributed architectures for urban digital twins;
• Automated and interoperable data pipelines for heterogeneous urban data sources;
• Geospatial AI frameworks and advanced 3D city modelling.

4. Interaction and Immersive Analytics

• Interactive digital twins using web-based platforms, VR/AR, and mixed reality;
• Conversational interfaces for digital twin systems;
• Visual analytics and decision-making support tools;
• Community engagement and participatory GIS.

5. Reliability, Validation, and Decision Support

• Integration of optimization and operations research for decision grounding;
• Model validation, uncertainty quantification, and robustness;
• Ethical considerations, transparency, and trust in AI-driven digital twins;
• Benchmarking and evaluation frameworks.

6. Applications in Smart Cities and Urban Systems

• Intelligent transportation systems and mobility digital twins;
• Environmental monitoring, climate resilience, and sustainability;
• Disaster management (e.g., wildfire, flood, and emergency response simulations);
• Infrastructure resilience and urban planning.

This Topic aims to foster interdisciplinary collaboration across AI, geospatial science, urban informatics, and engineering, and to establish a foundation for next-generation digital twin systems that move beyond data representation toward autonomous, intelligent, and actionable urban decision support.

Dr. Haowen Xu
Dr. Zhe (Sarina) Zhang
Dr. Di Zhu
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Geomatics geomatics	3.7	4.6	2021	21.6 Days	CHF 1200	Submit
ISPRS International Journal of Geo-Information ijgi	3.2	6.7	2012	34.9 Days	CHF 1900	Submit
Remote Sensing remotesensing	4.3	9.4	2009	22 Days	CHF 2700	Submit
Smart Cities smartcities	6.6	13.0	2018	25.1 Days	CHF 2000	Submit
Urban Science urbansci	3.2	3.7	2017	20.8 Days	CHF 1800	Submit

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (1 paper)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All Geomatics IJGI Remote Sensing Smart Cities Urban Science

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

35 pages, 8467 KB  

Open AccessArticle

ST-PaveCLIP: A Spatio-Temporal Vision–Language Framework for Road Anomaly Segmentation in Images and Videos

by Siyuan He, Yuchun Huang, Chen Wang, Feng Yang and Yifan Li

Remote Sens. 2026, 18(17), 2922; https://doi.org/10.3390/rs18172922 - 1 Sep 2026

Viewed by 238

Abstract

Static images and vehicle-mounted video are the two primary data sources for road inspection. Since cracks, potholes, and patched areas can all be considered anomalies on the road surface, Contrastive Language–Image Pre-training (CLIP)-based anomaly segmentation provides a promising approach under limited labeled data. [...] Read more.

Static images and vehicle-mounted video are the two primary data sources for road inspection. Since cracks, potholes, and patched areas can all be considered anomalies on the road surface, Contrastive Language–Image Pre-training (CLIP)-based anomaly segmentation provides a promising approach under limited labeled data. However, two challenges remain in practical applications: whole-image resizing may weaken fine anomalous structures, while weak and irregular damage regions can exhibit spatially varying prediction difficulty; for video input, frame-wise prediction often produces inter-frame flickering. This paper proposes ST-PaveCLIP for road anomaly segmentation in images and videos. For single images, we introduce a training-time residual-scale auxiliary supervision based on heteroscedastic negative log-likelihood and adopt a local–global dual-scale inference scheme to preserve global road context and fine anomaly structures. For video input, a temporal alignment module based on RoMa v2 dense matching and homography estimation warps the previous fused probability map to the current frame before temporal fusion, without additional video-level training. Multi-seed experiments on public and self-collected datasets show that ST-PaveCLIP improves the principal segmentation metrics over the AA-CLIP baseline and remains competitive with supervised baselines under the same limited annotation budget. Video experiments further show reduced inter-frame inconsistency in Aligned Temporal Consistency Error (TCE) and Aligned Threshold-Crossing Rate (ATCR), with a modest additional improvement in key-frame segmentation. Full article

(This article belongs to the Topic Agentic and Generative AI for Spatial Data Science: Toward Intelligent, Interactive, and Predictive Urban Systems)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-1