Skip to main content
SpringerLink
Log in
Springer

Computational Urban Science - Call for papers: Urban Artificial Intelligence Synergy: Fusing Urban Science with Cutting-Edge AI Innovations

The following special issue in Computational Urban Science is open for submissions. 

Call for papers: 

Urban Artificial Intelligence Synergy: Fusing Urban Science with Cutting-Edge AI Innovations

Guest Editors:

Dr. Gengchen Mai; Department of Geography, University of Georgia, gengchen.mai25@uga.edu

Dr. Xinyue Ye; Department of Landscape Architecture and Urban Planning, Texas A&M University, xinyue.ye@tamu.edu

Dr. Tianbao Yang; Department of Computer Science and Engineering, Texas A&M University, tianbao-yang@tamu.edu

Dr. Ni Lao; Google LLC, nlao@google.com

Dr. Yanjie Fu; School of Computing and Augmented Intelligence, Arizona State University, yanjie.fu@asu.edu

Aims and Scope:

Thanks to the significant advancements in deep learning, with particular emphasis on recent foundation models developments, such as, ChatGPT, CLIP, and SAM, there has been a prevalent surge in the integration of artificial intelligence technologies within a multitude of scientific and social science domains such as biology, physics, chemistry, earth system science, geography, transportation, geoinformatics, communication, history, and even archaeology. The convergence of available large datasets and computational resources has a progressively larger impact on the milieu and the routines of human existence in urban areas. This symbiotic integration is expected to precipitate a pronounced upswing in the realm of Urban Artificial Intelligence research and its corresponding practical implementations. This special issue of Computational Urban Science solicits submissions of novel manuscripts that focus on developing artificial intelligence models to tackle various urban problems. Numerous geospatial artificial intelligence (GeoAI) studies have mainly focused on applying existing state-of-the-art AI models to specific geospatial or urban problems, e.g., applying pre-trained ResNet or Vision Transformer  to street view/remote sensing images.  While these studies are welcomed, we are specifically interested in soliciting urban artificial intelligence research that is characterized by the formulation of innovative AI algorithms catered to urban issues. This entails a deliberate consideration of the distinctiveness inherent to the given task and the associated data modalities. Simultaneously, it is imperative to recognize and address the constraints and prospective concerns inherent in the development and application of AI within the realm of urban science. 

Topic includes but is not limited to the following themes:

  • transportation and human mobility challenges such as traffic prediction, ridesharing optimization, and trajectory generation/synthesis; 
  • urban planning issues such as land use classification, urban functional region discovery, streetview image-based urban greenness estimation, urban point-of-interest recommendation, building pattern recognition, and urban design generation; 
  • human-building interaction such as language-instruction-based indoor environment exploration and indoor environment point cloud classification;  
  • geospatial knowledge graph and symbolic AI application and development on urban data such as urban knowledge graph construction, POI entity alignment, and urban ontology design pattern development; 
  • reproducibility and replicability of urban AI models across space and time; 
  • scalability of training urban AI model that considers reducing the complexity of algorithms due to high-dimensions of data and large sizes of models； 
  • language, vision, or multimodal foundation model development for various urban settings and applications, including methodologies that take the domain-specific issues into account;
  • ethical contemplations and privacy apprehensions within the domain of urban AI such as AI-induced environmental justice predicaments, the emergence of cybersecurity and geoprivacy vulnerabilities, along with the intricate matter of AI model biases, notably those engendered by geographic disparities throughout different modeling phases such as data collection, feature engineering, model pre-training, fine-tuning, and evaluation.


Search

Navigation