Flight delay serves as a pivotal metric for assessing service quality in the aviation industry. Accurately estimating flight delay duration is increasingly acknowledged as a cornerstone of aviation management, with significant implications for operational efficiency, passenger satisfaction, and economic outcomes. Most existing approaches often focus on single airports or airlines and overlook the complex interdependencies within the broader aviation network, limiting their applicability for system-wide planning. To address this gap, this study proposes a novel integrated framework that combines deep learning and complex network theory to predict flight arrival delay duration from a multi-airport and multi-airline perspective. Leveraging Bayesian optimization, we fine tune hyperparameters in the XGBoost algorithm to extract critical aviation network features at both node (airports) and edge (flight routes) levels. These features, which capture structural properties such as airport congestion and route criticality, are then used as inputs for a deep kernel extreme learning machine to estimate delay duration. Numerical experiment using a high-dimensional flight dataset from the U.S. Bureau of Transportation Statistics reveals that the proposed framework achieves superior accuracy, with an average delay error of 3.36 min and a 7.8% improvement over established benchmark methods. This approach fills gaps in network-level delay prediction, and the findings of this research could provide valuable insights for the aviation administration, aiding in making informed decisions on proactive measures that contribute to the sustainable development of the aviation industry.

Urban passenger hubs, such as airports and railway stations, generate concentrated last-mile demand from arriving passengers to spatially dispersed urban destinations. Fluctuating passenger arrivals and changing vehicle availability can create a mismatch between accepted demand and available service capacity. This paper aims to coordinate zone-level pricing and vehicle dispatching, so that fare-responsive accepted demand can be better aligned with available vehicle resources, while balancing operator financial performance and service reliability. Under the zonal pricing scheme, the transit operator determines a quoted zone-level fare for each service zone at every decision epoch. Newly arriving service requests accept the service when the quoted fare does not exceed their maximum acceptable per-passenger fare, after which the fare is committed. A rolling-horizon optimization model jointly determines zone-level fares and dispatching plans as request states and vehicle states evolve over time. The fare discretization property reduces the continuous pricing decision to a finite candidate zone-level fare selection problem, and a customized Rolling-Horizon Adaptive Large Neighborhood Search (RH-ALNS) algorithm is developed to solve the resulting problem efficiently. Case studies based on Nanjingnan Railway Station in Nanjing, China, demonstrate the operational value of coordinating pricing and dispatching decisions. In the baseline case, the proposed method achieves a passenger service rate of 76.75%, an accepted-passenger fulfillment rate of 96.07%, and an operating surplus of 1.145 CNY per passenger-kilometer. Holding the RH-ALNS dispatching method fixed, dynamic zonal pricing increases the objective value by 4.39%, the operating surplus per passenger-kilometer by 5.46%, and accepted-passenger fulfillment by 3.63 percentage points relative to fixed zonal fares. The findings indicate that coordinating dynamic zonal pricing with vehicle dispatching can better align accepted demand with available vehicle resources and provide practical guidance for designing reliable, resource-efficient, and financially balanced hub-based demand-responsive last-mile transit services.