Scenario simulation and forecast of land use/cover in northern China |
| |
Authors: | YueChen Li ChunYang He |
| |
Institution: | (1) College of Geographical Science, Chongqing Normal University, Chongqing, 400047, China;(2) College of Resources and Environmental Science, Chongqing University, Chongqing, 400044, China;(3) College of Resources Science & Technology, Beijing Normal University, Beijing, 100875, China |
| |
Abstract: | Modeling land use/cover scenario changes and its potential impacts on structure and functions of ecosystem in typical regions
are helpful to understanding the interactive mechanism between land use/cover system and ecosystem. Based on the analysis
of the existing land use/cover simulation and forecast models, a land use/cover scenario dynamics model by the integration
of System Dynamics (SD) model, Back Propagation Neural Network (BPNN) and Cellular Automata (CA) model is developed with land
use/cover scenario changes in northern China in the next 30 years and simulated in this paper. The model is to simulate the
land use/cover scenario demands by using a SD model at first, and then allocating the land use scenario patterns at the local
scale with the considerations of land use/cover suitability, inheritance ability and neighborhood effect by using BPNN-CA
model to satisfy the balance between land use/cover scenario demands and supplies. It integrates the advantages of SD, BPNN
and CA. Macro-driving factors and the micro-spatial pattern are also fully taken into account. The BPNN simplifies the identification
of the factors’ weights used in CA model and improves the reliability of the simulation results. The simulation accuracy of
the model developed in this paper was found to be about 74%. It suggests that the model has the ability to reflect the complexity
of land use/cover system at different scales to some extent and it is a useful tool for assessing the potential impacts of
land use system on ecosystem. The simulated results also indicate that the urban land, water area and forest will increase
significantly, and farmland and unable land will decrease gradually. Obvious land use/cover changes will take place in the
farming-pastoral zone and the southeast area of northern China.
Supported by the Science & Technology Research Project of Chongqing Municipal Education Commission (Grant No. KJ070811), the
Doctor Startup Fund of Chongqing Normal University (Grant No. 06XLB004) and the National Key Project for Basic Sciences of
China (Grant No. 2006CB400505) |
| |
Keywords: | land use/cover change (LUCC) scenario simulation and forecast back propagation neural network cellular automata system dynamics the 13 provinces in northern China |
本文献已被 维普 SpringerLink 等数据库收录! |
| 点击此处可从《中国科学通报(英文版)》浏览原始摘要信息 |
| 点击此处可从《中国科学通报(英文版)》下载免费的PDF全文 |
|