Position-Aware Graph-CNN Fusion Network: An Integrated Approach Combining Geospatial Information and Graph Attention Network for Multiclass Change Detection
Moyang Wang, Xiang Li, Kun Tan, Joseph Mango, Pan Chen, Di Zhang
Abstract
Urban change detection (CD) is crucial for informed decision-making but faces various challenges, including complex features, rapid changes, and extensive human interventions. These challenges underscore the urgent need for innovative multiclass CD (MCD) techniques that extensively incorporate deep learning (DL). Despite several successes achieved with the DL-based MCD methods, still certain shortcomings persist, including the disregard for spatial principles, which significantly hinders the seamless integration of geoscience-knowledge and artificial-intelligence. In this article, a novel DL model known as the position-aware graph-convolutional neural network (CNN) fusion network (PGCFN) is introduced, integrating spatial position encoding to effectively detect urban changes. The model’s first part encodes geospatial positions following Tobler’s first law (TFL) of geography. It then integrates encoded positions into an MCD model, combining a graph attention network (GAT) with a CNN to enhance performance. The model was tested on 0.5-m resolution remote sensing (RS) images, achieving an impressive minimum mean intersection over union (MIoU) score of 91.20%. Additionally, the model’s position-aware graph attention module exhibited a strong emphasis on geographic proximity when evaluating connections between superpixels. Overall, these findings affirm that our model could effectively addresses urban CD challenges and significantly enhances the integration of geoscience knowledge and artificial intelligence (AI).