A novel attention-enhanced residual ConvLSTM framework for spatiotemporal urban expansion modeling

Unregulated urban sprawl drives environmental degradation, infrastructure stress, and reduced quality of life, making reliable urban expansion modeling (UEM) critical for sustainable planning and evidence-based land-use (LU) governance. However, many cellular automata (CA), machine learning, and shallow deep learning (DL) models rely on fixed spatial windows, simplified neighborhoods, and implicit transition mechanisms, limiting their ability to capture genuine neighborhood effects and transition potential. This study proposes a ResNet+ConvLSTM+Efficient Channel–Position Attention (ECPA) framework that combines deep residual learning for multi-scale spatial feature extraction, ConvLSTM for spatiotemporal dependency modeling, and position-aware attention for adaptive feature recalibration. The framework is evaluated in Colombo and Kandy, Sri Lanka, across two temporal intervals (2005–2015–2025) using two input configurations: eight driving variables and a reduced set of five predictors, enabling sensitivity analysis of transferable transition learning beyond increased input dimensionality. In Colombo, the proposed model achieves 94.75% overall accuracy, a Figure of Merit of 0.5532, and an Intersection over Union of 0.7208, outperforming five DL baselines on both pixel-level and pattern-level metrics. Attention and spatial diagnostics, together with landscape metrics for projected 2035 and 2045 LU maps, demonstrate stable, informative attention distributions and realistic urban growth trajectories, indicating genuine learning of transition processes. The ResNet+ConvLSTM+ECPA framework thus advances interpretable, robust, and policy-relevant UEM to support sustainable urban development in rapidly growing cities.