District-level layout planning of UAV takeoff and landing sites based on the NSGA-Ⅱ algorithm: A case study of Nanshan District, Shenzhen

Aiming at the multi-objective coordination challenges in the layout planning of unmanned aerial vehicles (UAV) takeoff and landing sites in high-density urban areas, including coverage efficiency, construction cost, airspace risk, and environmental noise, an optimization model integrating the multi-dimensional objectives above was proposed. An improved non-dominated sorting genetic algorithm (NSGA-Ⅱ) was adopted for the solution. Taking Nanshan District, Shenzhen as an example, a hybrid planning model covering three functions of passenger transport, freight, and urban governance was constructed. In the algorithm design, a hierarchical chromosome encoding scheme was proposed, including latitude and longitude coordinates, functional types, and scale levels. A dynamic constraint handling mechanism was applied to coordinate complex constraints such as airspace safety, land use compatibility, and noise sensitivity. Specifically, for freight takeoff and landing sites, a hierarchical connection rule was introduced to ensure the integrity of the urban logistics network. The analysis of typical schemes shows that, in core business districts, the passenger-oriented scheme has relatively high service coverage efficiency yet with higher airspace management pressure; freight optimization scheme can significantly improve logistics efficiency in logistics hubs, but the noise impact range rises by 25%; the balanced scheme is the most applicable in mixed-function areas like university towns; minimalist scheme provides feasible pathways for areas with budget constraints or ecological sensitivity. Meanwhile, further parameter analysis indicates that reducing the distance between first- and second-level freight hubs from 5 km to 4 km can improve freight efficiency by 12% but increase airspace conflict risks by 18%. The installation of noise barriers can reduce residential area noise by 4 dB yet with an additional cost of 100 000–200 000 RMB per site. A differentiated layout strategy is ultimately proposed: business districts such as the technology park adopt passenger-oriented layouts, and areas such as Mawan Port are equipped with a complete three-level freight network. The areas surrounding the Shenzhen Bay Nature Reserve are restricted to micro takeoff and landing sites. The multi-objective optimization framework and improved solution algorithm constructed in this paper provide a complete and quantifiable decision-support tool for the planning of UAV takeoff and landing sites in high-density urban areas, from modeling, solving, to scheme comparison.