Article: Multi-objective optimisation for sustainable landscape planning using genetic algorithms Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.45 pp.17 - 33 Abstract: Rapid urbanisation intensifies pressures on urban landscapes, driving sustainability challenges like ecological degradation and unequal green space access. This study develops a genetic algorithm (GA)-based multi-objective optimisation (MOO) framework for sustainable landscape planning in Nanchang City's first ring road. The non-dominated sorting genetic algorithm II (NSGA-II) is adopted to simultaneously optimise ecological, social and economic objectives. Spatial data, including land use and population density, are integrated within a grid-based model, with constraints such as ecological protection lines. In the park green space case, optimisation achieves 100% service coverage, reduces residents' total travel time by 28.2%, increases 15-minute accessible population from 70.35% to 94.31%, and enhances efficiency. The Pareto optimal solution set illustrates critical trade-offs, while the optimised spatial layout demonstrates significant accessibility gains. This approach provides a robust decision-making tool for sustainable urban development, balancing ecological integrity, social equity, and economic viability in high-density environments. Inderscience Publishers - linking academia, business and industry through research

Title: Multi-objective optimisation for sustainable landscape planning using genetic algorithms

Authors: Miao Weng

Addresses: College of Art, Henan University of Animal Husbandry and Economy, Zhengzhou 450046, China

Abstract: Rapid urbanisation intensifies pressures on urban landscapes, driving sustainability challenges like ecological degradation and unequal green space access. This study develops a genetic algorithm (GA)-based multi-objective optimisation (MOO) framework for sustainable landscape planning in Nanchang City's first ring road. The non-dominated sorting genetic algorithm II (NSGA-II) is adopted to simultaneously optimise ecological, social and economic objectives. Spatial data, including land use and population density, are integrated within a grid-based model, with constraints such as ecological protection lines. In the park green space case, optimisation achieves 100% service coverage, reduces residents' total travel time by 28.2%, increases 15-minute accessible population from 70.35% to 94.31%, and enhances efficiency. The Pareto optimal solution set illustrates critical trade-offs, while the optimised spatial layout demonstrates significant accessibility gains. This approach provides a robust decision-making tool for sustainable urban development, balancing ecological integrity, social equity, and economic viability in high-density environments.

Keywords: multi-objective optimisation; MOO; non-dominated sorting genetic algorithm II; NSGA-II; sustainable landscape planning; genetic algorithm; GA.

DOI: 10.1504/IJICT.2025.150414

International Journal of Information and Communication Technology, 2025 Vol.26 No.45, pp.17 - 33

Received: 11 Aug 2025
Accepted: 28 Sep 2025
Published online: 12 Dec 2025 *

Title: Multi-objective optimisation for sustainable landscape planning using genetic algorithms

Keep up-to-date