土地利用
计算机科学
蚁群优化算法
比例(比率)
过程(计算)
环境资源管理
土地覆盖
环境科学
生态学
地理
人工智能
地图学
生物
操作系统
作者
Weilin Wang,Limin Jiao,Qiqi Jia,Jiafeng Liu,Wenjing Mao,Zhibang Xu,Wende Li
标识
DOI:10.1016/j.scs.2020.102575
摘要
Land-use optimization model provides an effective means of finding solutions to mitigate ecological impacts resulting from land use and land cover changes (LUCCs). However, current land-use optimization models usually underestimate the control/ effectiveness of ecological indicators in the model's operation process. How to incorporate ecological indicators into the land-use simulation to optimize multiple land-use patterns is scarce and worth discussing. In our study, we proposed a Future Land use Optimization model for Ecological protection (FLOE) by integrating a cellular automata (CA) model, ant colony optimization (ACO) algorithm, and ecological protection for optimizing land-use patterns from an ecological priority perspective. Firstly, we discuss the coupling pattern in incorporating ecological indicators into models to support the use of models for design and verification in large-scale land-use optimization. Secondly, the proposed FLOE model improves the effectiveness of ecological indicators in the land-use optimization process and better meets the predetermined optimization objectives in a dynamic feedback mechanism. The LUCCs of the Yangtze River Economic Belt (YREB) during 2010–2015 were selected to validate the applicability of the proposed FLOE model. The validation results show that compared to actual LUCCs, the proposed model can significantly reduce ecosystem function loss. Moreover, the proposed model was also applied to the land use optimization from 2010 to 2030 in YREB. The optimization results show a 31.23 % reduction in the total ecosystem function loss than land-use simulation without ecological optimization. The study is expected to provide a reference for land use optimization modelling with ecological conservation in methodology and offers important implications for the formulation and management of large-scale spatial planning.
科研通智能强力驱动
Strongly Powered by AbleSci AI