A gravity-inspired model integrating geospatial and socioeconomic distances for truck origin–destination flows prediction

Accurately predicting truck origin–destination (OD) flows is essential for optimizing logistics systems and promoting coordinated regional development. Existing methods typically assume a monotonic decrease in truck OD flows with increasing geospatial distance, which oversimplifies the complex non-monotonic distribution patterns observed in practice. Moreover, these methods overlook interregional socioeconomic distances and their interaction with geospatial distances, thereby limiting the prediction accuracy and reliability. This study introduces a gravity-inspired model that integrates both geospatial and socioeconomic distances (GSD-DG) to explicitly represent their combined influence on truck OD flows. Specifically, we 1) develop a geospatial distance relation graph using the Weibull function to model the complex spatial distribution patterns of truck OD flows with varying geospatial distances; 2) propose a gravity-inspired representation learning method based on graph attention mechanism to quantify the influence of socioeconomic distance on truck OD flows; and 3) construct a deep gravity model that integrates these distances and their interactions to capture their non-linear relationship with truck OD flows. Extensive experiments on four datasets with varying spatial scale and economic development levels demonstrate that the GSD-DG model improves the robustness and prediction accuracy across diverse spatial distribution patterns, reducing RMSE by 14.2%–85.8% and MSE by 23.5%–92.5% compared to the six baseline models. Incorporating socioeconomic distance and its interaction with geospatial distance further reduces RMSE by 8.5%–36.0%. Additionally, explainable artificial intelligence techniques highlight how these distances affect truck OD flows, providing valuable policy insights for logistics planning and coordinated regional development.