Demographics-Informed Neural Network for Multi-Modal Spatiotemporal forecasting of Urban Growth and Travel Patterns Using Satellite Imagery

2025-06-14

AI Summary

This study addresses the joint prediction of urban spatial evolution—including built-environment expansion and mobility pattern shifts—under multi-modal spatiotemporal data for sustainable urban planning. We propose a demographics-guided generative modeling framework that fuses satellite imagery, sociodemographic statistics, and dynamic mobility behavior data. Our method employs a temporal gated residual encoder-decoder architecture, incorporating demographics-aware generative constraints and a multi-objective semantic loss function to explicitly model the bidirectional co-evolution between built environments and population distributions. We introduce the first multi-modal urban evolution benchmark dataset spanning 2012–2023. Experiments demonstrate an SSIM of 0.8342 and reduce population distribution consistency error to 0.14—substantially improving upon state-of-the-art baselines (0.95/0.96)—validating the model’s dual strengths in physiological plausibility and socioeconomic accuracy.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

This study presents a novel demographics informed deep learning framework designed to forecast urban spatial transformations by jointly modeling geographic satellite imagery, socio-demographics, and travel behavior dynamics. The proposed model employs an encoder-decoder architecture with temporal gated residual connections, integrating satellite imagery and demographic data to accurately forecast future spatial transformations. The study also introduces a demographics prediction component which ensures that predicted satellite imagery are consistent with demographic features, significantly enhancing physiological realism and socioeconomic accuracy. The framework is enhanced by a proposed multi-objective loss function complemented by a semantic loss function that balances visual realism with temporal coherence. The experimental results from this study demonstrate the superior performance of the proposed model compared to state-of-the-art models, achieving higher structural similarity (SSIM: 0.8342) and significantly improved demographic consistency (Demo-loss: 0.14 versus 0.95 and 0.96 for baseline models). Additionally, the study validates co-evolutionary theories of urban development, demonstrating quantifiable bidirectional influences between built environment characteristics and population patterns. The study also contributes a comprehensive multimodal dataset pairing satellite imagery sequences (2012-2023) with corresponding demographic and travel behavior attributes, addressing existing gaps in urban and transportation planning resources by explicitly connecting physical landscape evolution with socio-demographic patterns.

Problem

• Forecast urban growth using satellite and demographic data
• Predict travel patterns with spatiotemporal deep learning
• Ensure demographic consistency in urban development forecasts

Innovation

• Demographics-informed encoder-decoder with residual connections
• Multi-objective loss balancing realism and coherence
• Joint modeling of satellite imagery and demographics