Improving highway accessibility to tourist attractions is critical for promoting social sustainability and reducing regional disparities in tourism development. However, existing accessibility optimization often ignores the resource scarcity of tourist attractions and lacks fairness considerations, leading to biased investment allocation and perpetuating such disparities. Here, this study introduces a TF-IDF-based scarcity measure of tourist attractions and formulates a fairness-oriented optimization model to reduce these spatial disparities. The results of the case study in Shanxi Province show that after applying the scarcity measure, 77 northern and western counties experience increased travel cost, while 40 southern counties see decreases, revealing a pronounced scarcity penalty. The fairness-oriented optimization allocates over 80% of the budget to counties with high-scarcity attractions and reduces the variance of accessibility by 55.8%. At the county level, the investment–accessibility improvement correlation reaches an R² of 0.85, confirming that fairness-driven investment reliably translates into measurable accessibility improvements. In contrast, the weaker OD-pair level correlation (R² = 0.50) confirms that aggregated county-level indicators are more appropriate for assessing the effectiveness of fairness-driven investment. This study quantifies tourism resource scarcity and demonstrates that fairness-driven optimization effectively reduces spatial disparities, laying a foundation for transport infrastructure planning and investment that enhances accessibility and promotes equity in tourist attractions.

The urban industrial spatial structure is widely recognized as a critical factor shaping public transit travel patterns. However, the relationship between variations in this spatial structure and bus origin-destination (OD) passenger flows remains insufficiently explored. To address this gap, this study proposes two quantitative indicators, namely, Regional Industrial Proximity (RIP) and Regional Industrial Scarcity (RIS), to characterize the differentiation of urban industrial spatial structures. The empirical study is conducted in the core built-up area within Beijing’s 5th Ring Road. The study area is divided into 8.3 km × 8.3 km grids, and a Proximity–Scarcity Relational Graph Convolutional Network (PS-RGCN) model is employed to predict urban bus passenger flows. The dataset primarily comprises approximately 4.21 million smart card transaction records collected over one continuous week, alongside 276,000 Points of Interest (POI) records covering 20 industrial categories. Specifically, the proposed PS-RGCN model achieves the best prediction performance among all benchmark models. The best overall performance is attained when incorporating the RIP of Scenic Spots and Historical Sites as edge relationships, yielding a coefficient of determination R² of 0.888. In comparison, the gravity model yields an R² of 0.858, and the baseline GCN model yields an R² of 0.378, indicating the superior predictive capability of the proposed model. This study verifies that industrial proximity and industrial scarcity exert complementary effects in bus OD flow prediction. Incorporating both factors synergistically into the multi-relational graph neural network framework enables more effective identification of the predictive relationship between urban functions and bus travel demand.

Understanding how urban spatial structure affects commuting distance is critical for optimizing land use and promoting jobs–housing balance. While previous studies have examined this relationship through cross-city comparisons, few have quantitatively separated the main and interaction effects of urban scale, centrality intensity, and residential behavior under controlled conditions. Employing a controlled simulation, we constructed abstract grid-based cities across a broad size spectrum and systematically varied centrality intensity, central function type, and residential pattern. Results show that the designated residential pattern qualitatively alters the scale–commuting relationship. Relative to random residence, proximity-based residence reduces commuting distance by up to approximately 91% under the mixed monocentric structure and by approximately 87% under the employment-only center structure, both at low centrality intensity and large urban scales, reflecting the interaction between the allocation rule and urban form. Simulations further reveal a spatial mismatch trap: without coordinated residential agglomeration, employment centralization lengthens rather than shortens commuting for proximity-seeking residents, with penalties amplifying markedly as urban scale increases. Critically, jobs–housing spatial congruence, not centralization or decentralization per se, determines commuting efficiency. Under proximity-based residence, the mixed monocentric structure achieves shorter commuting distances than employment-only centers; in the proximity-based mixed scenario, the marginal commuting benefit of increasing centrality intensity declines at high intensity. These findings offer implications for land use and transport planning, particularly the need to couple employment centers with housing supply and prioritize residential proximity over morphological decentralization.

Understanding how urban functional structure shapes inter-county daily mobility at fine scales is essential for sustainable polycentric planning. However, existing origin-destination (OD) models often treat regions as independent observations and lack prior policy evaluation capacity. This study proposes a Graph Convolutional Network (GCN) framework that uses 14 Points of Interest (POI) categories as functional proxies for inter-county daily mobility in 50 counties of the Greater Bay Area, China, drawing on over 6.26 million POI records and county-level mobile signaling OD data. The framework constructs a spatial adjacency graph and learns non-linear mappings between functional profiles and mobility through an encoder–decoder architecture. It achieves a test R² of 0.766, outperforming gravity, linear, machine-learning, and graph-only baselines. Perturbation-based sensitivity analysis identifies shopping and consumption venues, catering services, corporations and enterprises, and daily life services as the categories most strongly associated with mobility, with rankings stable across perturbation magnitudes and seeds. Scenario simulations reveal heterogeneous, stage-dependent responses. A 10% increase in transport and corporate facilities in Foshan yields a mean response of 6.18%, positive across all 110 county pairs along the mature Guangzhou-Foshan corridor; corporate expansion in the peripheral Guangzhou-Zhaoqing corridor is positive for nearly all county pairs but elicits a smaller mean response; and tourism expansion in the Shenzhen-Zhongshan corridor elicits a weak, near-symmetric negative response. We propose a stage-dependent planning perspective, with mature corridors prioritizing service optimization and job-housing balance and peripheral ones prioritizing capacity investment, and stress that these responses are model-implied diagnostics requiring validation against independent mobility evidence.