A knowledge-enhanced framework for urban waterlogging prediction based on informed similarity transfer and hybrid spatio-temporal model

Abstract

Extreme weather events exacerbated by global climate change have heightened urban waterlogging risks, particularly in rapidly urbanizing coastal areas such as Shenzhen, China. Traditional predictive models struggle to address these challenges effectively due to incomplete data and the complex, multi-scale spatio-temporal dynamics associated with urban waterlogging. This study proposed a knowledge-enhanced predictive framework that combines Informed Similarity Transfer (IST) with a Hybrid Spatio-Temporal Model (HSTM) to address these issues comprehensively. IST method innovatively constructs a similarity index by integrating spatial proximity, land cover characteristics, and altitude data, which enables precise data imputation across meteorological monitoring stations, thus overcoming limitations in conventional data completion techniques that often fail in diverse urban settings. HSTM is a dual-stage model that leverages multi-source data and combines multi-class classification with regression to provide fine-grained, high-precision predictions of waterlogging risk levels and water depths. By achieving reliable and scalable predictions, this framework not only enhances urban waterlogging risk management but also offers a transferable solution for other cities with similar waterlogging vulnerabilities. This study contributes a robust, large-scale regionally adaptive approach to disaster risk reduction, advancing predictive urban water management amid growing climate-related uncertainties.