摘要
对城市河道生态护岸景观的面积进行预测,能够实现城市生态系统的稳定。对河道生态景观面积进行预测,需要将生态护岸景观类型的划分状况转变为数字化,并构建马尔科夫模型一步转移概率矩阵。传统方法构建了基于RBF网络的预测模型,同时利用多元线性回归模型进行面积,但忽略了对景观类型划分进行数字化,导致预测精度低的问题,提出基于马尔科夫的城市河道生态护岸景观面积预测方法。将不同时期城市河道生态护岸景观类型的划分状况进行数字化,得到景观现状与平面图;构建马尔科夫模型一步转移概率矩阵,获得某景观为另一种景观类型的概率。将景观面积动态参数代入一步转移概率矩阵和基本方程中,获取城市河道生态护岸景观面积最终的预测结果。实验结果表明,该方法平均预测耗时为3. 2h,预测精度较高、耗时短,具有很强的可行性。
This paper proposes a method to predict the area of ecological revetment landscape in urban river course based on Markov model. At first,the partition status of landscape type of ecological revetment in urban river course at different stages was digitized to obtain the current situation of landscape and plane graph.Then,one-step transition probability matrix of Markov model was built to obtain the probability that a landscape was another landscape type.Finally,dynamic parameter of landscape area was introduced into one-step transition probability matrix and basic equation.Thus,the final prediction result of landscape area of ecological revetment landscape in urban fiver course was obtained.Simulation results show that the average time consumption for prediction is 3.2h in the proposed method.Meanwhile,the prediction accuracy is high and the time consumption is short.It has a strong feasibility.
作者
吴巍
夏健乔
WU Wei;XIA Jian-qiao(College of Civil Engineering and Architecture,Hubei University of Technology, Hubei Wuhan 430068,China;School of Art &Design,Hubei University of Technology,Hubei Wuhan 430068,China)
出处
《计算机仿真》
北大核心
2018年第12期401-405,共5页
Computer Simulation
关键词
城市河道
生态景观
面积
预测
Urban river course
Ecological landscape
Area
Predict
