Land Use Spatial Optimization Based on Multi‐Objective Ant Colony Algorithm and FLUS Model: A Case Study of Korla City and Tiemenguan City, China

In southern Xinjiang, China, scarce land and water resources and fragile ecosystems have intensified land use conflicts, making land resource allocation optimization essential for sustainable development in arid oasis areas. Focusing on Korla and Tiemenguan, this study aims to coordinate economic benefits, ecological benefits, and food security. To achieve this optimization, a multi‐objective ant colony (MOACO) algorithm was employed to optimize the quantitative structure of land use, establishing a multi‐objective function system. The future land use simulation (FLUS) model was then used to simulate spatial allocation under four scenarios—economic benefit priority, ecological benefit priority, food production priority, and balanced development—and landscape pattern characteristics were evaluated using Fragstats‐4.2. The spatial simulation achieved an overall accuracy of 90.17%, indicating high prediction reliability. GDP, carbon sequestration, and grain production improved under each scenario, while soil erosion was markedly reduced. Among the four scenarios, the balanced development scenario showed the most coordinated trade‐off among economic development, ecological protection, food security, and landscape pattern stability, representing a more practical and balanced pathway for land use optimization. By integrating quantity optimization, spatial simulation, and landscape pattern evaluation, this study reveals how multi‐objective optimization reshapes spatial patterns and ecological benefits, and examines the synergies and trade‐offs among ecosystem service objectives, land use transitions, and landscape pattern evolution in arid oasis regions of Northwest China, providing theoretical insights and decision support for sustainable land resource allocation in Korla and Tiemenguan.