UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics

2026-06-14

AI Summary

Existing models struggle to effectively integrate multimodal spatiotemporal data for a comprehensive assessment of urban well-being. To address this gap, this work proposes UrbanWell—the first standardized multimodal spatiotemporal reasoning benchmark tailored for urban well-being analysis. UrbanWell integrates satellite and street-view imagery to construct a multidimensional evaluation framework encompassing environmental quality, accessibility, urban form, vitality, and subjective perception across gridded data spanning multiple years in 38 cities. The benchmark supports zero-shot spatiotemporal reasoning, future forecasting, and trend classification tasks. Experiments on 15 state-of-the-art multimodal large language models reveal that while these models can capture certain spatial and perceptual cues, their performance varies significantly across different well-being dimensions, thereby validating UrbanWell’s effectiveness and necessity as a unified evaluation platform.

Abstract

Understanding urban wellbeing from multimodal data requires integrating heterogeneous spatial and temporal signals, posing significant challenges for current multimodal large language models (MLLMs). We introduce UrbanWell, a large-scale benchmark designed to systematically evaluate the spatio-temporal reasoning capabilities of MLLMs for urban wellbeing analytics through joint modeling of satellite and street view imagery. UrbanWell spans 38 cities across multiple years and includes diverse indicators covering (1) environmental conditions (CO$_2$, NO$_2$, PM${2.5}$, and Normalized Difference Vegetation Index), (2) spatial accessibility (minimum distance to supermarkets and restaurants), (3) urban form (road length, road density, and land use), (4) urban vitality (population, economic activity diversity, and land use diversity), and (5) subjective perception attributes (e.g., safety, beauty, liveliness, wealth, and quietness). All indicators are aligned at grid level to enable standardized evaluation. Beyond static prediction, UrbanWell defines temporal reasoning tasks, including future value forecasting from historical observations and temporal trend classification. We benchmark 15 state-of-the-art representative MLLMs in a zero-shot setting, providing a comprehensive comparative evaluation across spatial and temporal dimensions. Experimental results indicate that while MLLMs capture salient spatial and perceptual cues, their performance varies substantially across heterogeneous urban indicators spanning environment and subjective perception. UrbanWell serves as a unified benchmark for evaluating multimodal spatial and temporal reasoning in urban wellbeing analytics, offering a standardized testbed for systematic assessment and future research on multimodal urban intelligence. Our codes and datasets are accessible via https://github.com/axin1301/UrbanWell-Benchmark.

Problem

• urban wellbeing
• multimodal large language models
• spatio-temporal reasoning
• benchmark
• urban analytics

Innovation

• multimodal large language models
• spatio-temporal reasoning
• urban wellbeing analytics
• benchmark dataset
• zero-shot evaluation