The Scenarios Simulation Analysis of Driving Forces ofWetland Landscape Evolution Using ANN-CA in Yinchuan Plain

  • 1. Institute of Remote Sensing and Digital Earth, Beijing 100094, China;
    2. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;
    3. College of Resources and Environmental Sciences, China Agricultural University, Beijing 100193, China

Received date: 2013-01-29

  Revised date: 2013-11-24

  Online published: 2014-05-10


Wetland landscape spatio-temporal dynamic development process is more important than the ultimate form of its spatial pattern. Only clearly understand wetland dynamic development process, the theory and decision support of wetland resources protection and sustainable utilization can be provided. In this paper, Yinchuan Plain wetland landscape evolution driving force analysis model was established, full considering the causal relationship between the geographical phenomena in space and time. The transform rules of cellular automata (CA) were built with the model of artificial neural network (ANN), which reduced the man-made subjective factors, and improved the accuracy. Comparing the prediction results with actual wetland types, it concludes that the prediction accuracy reaches about 84.24%. Three driving force factors as annual precipitation, population density and agriculture gross output value were selected for the scenarios simulation of wetland landscape pattern. The scenarios simulation results show that, average annual rainfall has more significant driving force to natural wetland, in the process of reduced by 10% to increased by 10%, the area of river and lake wetlands continues to increase, with river wetland increased 26.3844 km2 and lake wetland 22.4100km2. Rice paddies and ponds maintain a steady growth. Population density has more significant driving force to artificial wetland. With the growth rate of population density changing from 8 ‰ to 18.7 ‰, rice paddies and ponds expanded greatly, i.e. 19.4364 km2 and 18.2088 km2, respectively. But the area of natural wetlands (river and lake wetlands) decreased gradually, and the construction land increased markedly. Total agricultural output also has more significant driving force to artificial wetlands, but slow reverse inhibition force to natural wetlands. When the growth rate of total agricultural output changes from 4.5% to 6.5%, artificial wetlands such as rice paddies and ponds expand rapidly, increasing 21.5604 km2 and 19.1880 km2, respectively;river and lake wetlands decrease slowly;and the construction land and the Yellow River washland remain basically unchanged.

Cite this article

ZHANG Meimei, ZHANG Rongqun, HAO Jinmin, AI Dong . The Scenarios Simulation Analysis of Driving Forces ofWetland Landscape Evolution Using ANN-CA in Yinchuan Plain[J]. Journal of Geo-information Science, 2014 , 16(3) : 418 -425 . DOI: 10.3724/SP.J.1047.2014.00418


[1] Yuan H, Zhang R Q. Changes in wetland landscape patterns on Yinchuan Plain, China[J]. International Journal of Sustainable Development & World Ecology, 2010,17 (3):236-243.
[2] 刘振乾,段舜山,李爱芬,等.湿地蓄水量动态SD仿真研究[J].地理与地理信息科学,2004,20(1):54-56.
[3] 李洪,宫兆宁,赵文吉,等.基于Logistic 回归模型的北京市水库湿地演变驱动力分析[J].地理学报,2012,67(3): 357-367.
[4] 郝敬锋,刘红玉,李玉凤,等.基于转移矩阵模型的江苏海滨湿地资源时空演变特征及驱动机制分析[J].自然资源学报,2010,25(11):1918-1929.
[5] 刘红玉,李玉凤,曹晓,等.我国湿地景观研究现状、存在的问题与发展方向[J].地理学报,2009,64(11):1394-1401.
[6] 徐延达,傅伯杰,吕一河.基于模型的景观格局与生态过程研究[J].生态学报,2010,30(1): 212-220.
[7] 王铮,隋文娟,姚梓漩,等.地理计算及其前沿问题[J].地理科学进展,2007,26(4):1-10.
[8] 张荣群,宋乃平,王秀妮,等.盐渍土时空变化信息的图谱可视化分析[J].农业工程学报,2012,28(9): 230-235.
[9] 黎夏,叶嘉安,刘小平,等.地理模拟系统:元胞自动机与多智能体[M].北京:科学出版社,2007.
[10] Almeida C M, Gleriani J M, Castejon E F, el al. Using neural networks and cellular automata for modeling intra-urban land use dynamics[J]. International Journal of Geographical Information Science, 2008,22(9):943-963.
[11] 赵晶,陈华根,许惠平.元胞自动机与神经网络相结合的土地演变模拟[J].同济大学学报(自然科学版),2007,35 (8):1128-1132.
[12] 柯新利,邓祥征.内嵌空间聚类算法的分区地理元胞自动机建模与应用[J]. 地球信息科学学报,2010,12(3): 365-371.
[13] 黎夏,叶嘉安.基于神经网络的元胞自动机及模拟复杂土地利用系统[J].地理研究,2005,24(1):19-27.
[14] 曹敏,史招良.基于遗传神经网络获取元胞自动机的转换规则[J].测绘通报,2010,58(3):24-28.
[15] A-Kheder S, Wang J, Shan J. Fuzzy inference guided cellular automata urban-growth modelling using multi-temporal satellite images[J]. Geographical Information Science, 2008(22):1271-1293.
[16] 马建林,何彤慧. 银川平原湿地的初步研究[J].宁夏大学学报(自然科学版),2002,23(4):377-380.
[17] 王一鸣.宁夏人地关系研究[M].宁夏:宁夏人民出版社, 2005.
[18] Yuan H, Zhang R Q, Song N P, et al. Study on wetland change detection and underlying causes analysis in Yinchuan Plain, China[J]. Journal of Food, Agriculture & Environment, 2010,8(2):132-134.
[19] 宁夏统计年鉴编委会.宁夏统计年鉴[M].北京:中国统计出版社,2010.
[20] 张荣群,袁勘省,袁慧.银川平原湿地空间分布格局图谱[J].湿地科学与管理,2012,8(4):43-44.
[21] 董婷婷,左丽君,张增祥.基于ANN-CA模型的土壤侵蚀时空演化分析[J].地球信息科学学报,2009,11(1):132-138.
[22] 袁慧.银川平原湿地景观格局演化规律研究[D].北京:中国农业大学,2010.