A systematic review of geospatial artificial intelligence and machine learning in urban analytics

Engineering notes

Key topics: autonomous driving. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Geospatial artificial intelligence (GeoAI) has emerged as a popular term in geography, particularly among urban geographers to address complex and data-intensive real-world problems. Despite increasing popularity, application, and advancement there remains a lack of comprehensive reviews assessing the impact and challenges of GeoAI in urban analytics. This study seeks to fill this knowledge gap through a combination of bibliometric analysis and a systematic review of 100 journal articles, drawn from two authoritative scientific databases, Web of Science and Scopus. Utilizing the bibliometric tool VOSviewer and systematic review techniques, this research identifies the principal components, methodologies, data types, and applications of GeoAI in urban analytics. Data dependency, limited incorporation of socioeconomic factors, and the lack of interpretability remain major challenges for GeoAI. Data scarcity also restricts the global applicability of GeoAI, especially in developing realm. Our analysis reveals a substantial popularity of GeoAI alongside the expansion of urban data types. However, traditional machine learning and deep learning algorithms continue to dominate the GeoAI approach. To address the challenges, this study suggests interdisciplinary approaches to address urban issues. This research also recommends developing computationally efficient, interpretable, and socially inclusive GeoAI models to foster sustainable urban development.

Links and sources

Comments