The rapid development of the low-altitude economy has positioned vertiports as critical heavy-asset hubs in urban logistics networks, where siting decisions affect both delivery access and facility utilization. Existing maximum-coverage models do not explicitly represent station throughput or allocated order volumes. This study therefore retains the original three-stage framework - demand assessment, HFPIPS candidate generation, and capacitated location-allocation - while correcting the demand surface to use area-weighted land-use shares and clarifying that the utilization floor is an application-specific minimum-throughput rule rather than a new algebraic form. In Nanjing, 8,811 demand grids and 10,283 planning candidates produce 2,678,898 radius-feasible pairs, reduced to 374,873 pairs by demand-adaptive pruning. Under a 300 s single-thread budget, the high-coverage CFLP returns a verified feasible incumbent of 195 stations delivering 156,300 orders/day (78.13%), with 66.79% average utilization, 22.50% minimum utilization, and 0.953 km average delivery distance. At the same 195-site budget, a deterministic MCLP-greedy baseline achieves 97.05% nominal geometric coverage but only 63.87% capacity-feasible delivery. Removing the utilization floor delivers only 29 additional orders while opening four extra sites and permitting utilization as low as 1.58%. Land-use coefficient contrast tests change delivery by less than 0.27 percentage points and preserve the selected station set. The results support capacity-aware planning, while building-level engineering data, heterogeneous fleets, temporal demand, and unresolved solver gaps remain limitations.

This study develops a life-cycle techno-economic analysis and optimization framework for hybrid deep ground source heat pump (GSHP) systems, addressing the limitations of existing evaluations that often neglect subsurface thermal attenuation and rely on simplified heat transfer models. A coupled heat transfer model is established by combining the finite difference method for the borehole interior with the segmented finite line-source model for the surrounding ground, enabling long-term simulation of fluid and ground temperature evolution. The energy model is integrated with a life-cycle economic evaluation to calculate net present value, levelized cost of heating/cooling, payback period (PP), and internal rate of return. A Bayesian optimization algorithm is further employed to identify optimal system configurations under multiple objectives. The framework is applied to a hybrid geothermal system in Xi’an, China, incorporating mid-deep boreholes with auxiliary air-source heat pumps or gas boilers. Results show that long-term thermal attenuation significantly affects economic performance, with a 2 °C increase in fluid temperature extending the PP by approximately 0.3 years. User-side load uncertainty also has a substantial impact, as a 10% deviation from the design load can shift the optimal PP by about 2 years. Sensitivity analysis identifies the GSHP installed capacity ratio and borehole number as the most influential parameters. Compared with pure geothermal systems, the hybrid geothermal–gas boiler configuration achieves the shortest PP, demonstrating the framework’s effectiveness for robust low-carbon system design.

Alkali-activated lunar regolith is considered one of the most promising lunar regolith-based construction materials for large-scale lunar construction. This study presents a comprehensive framework integrating machine learning (ML) algorithms to investigate the influence of various features on the mechanical strength of alkali-activated lunar regolith simulant (AALRS), aiming to achieve the strength prediction and optimization design of AALRS. The properties of lunar regolith simulant, mixture proportions, preparation parameters, environmental conditions, and enhancement methods were employed as input features for ML modeling. The compressive and flexural strength predictive models were constructed using eight ML algorithms and evaluated through statistical indicators. Among the models, Extreme Gradient Boosting demonstrated the best performance, yielding an R² of 0.8684, a root mean square error of 6.2007 MPa, and a mean absolute error of 4.0874 MPa on the testing dataset. Using the best prediction models, four design strategies with three objectives, namely, compressive strength, flexural strength, and transport payload (TP), were optimized and evaluated using the non-dominated sorting genetic algorithm II and the technique for order preference by similarity to ideal solution methods. The proposed prediction and optimization framework for the mechanical performance of AALRS, which integrates extreme environmental effects and TP-driven design, provides a robust data-driven approach for the design, prediction, and optimization of AALRS, advancing the development of extraterrestrial construction materials and technologies.