基于人工神经网络的园林植物配置研究

Garden Plant Configuration Based on Artificial Neural Network

为了适应低碳生态环境要求,将深度学习下的人工神经网络运用于风景园林设计的植物配置中,为风景园林设计的科学性提供依据。根据生态城市下风景园林设计理论,着重分析生态城市和低碳园林的具体内涵和重要性,进而分析人工神经网络与风景园林设计的相关性,以此为基础提出基于人工神经网络的风景园林设计植物配置模型。通过网络爬虫技术进行模型训练数据集的收集,运用AutoCAD形成植物配置图层。随机选取陕西西安地区的10个公园进行植被种类与使用频率的关系分析。结果表明,该地区植物的使用频率越低,植物的种类越多。对于规定种植面积的乔木种植,系统生成的乔木坐标点会控制在种植范围内,最终输出的植物图层都不相同,有乔木、地被以及灌木。获得的植物配置三维效果图可以清晰看到乔灌木和地被的配置情况,说明人工神经网络植物配置模型具有较高可行性。

In order to comply with the requirements of low-carbon ecological environment,the artificial neural network based on in-depth learning was applied to the plant configuration to provide a basis for the scientific landscape architecture design.According to the theory of landscape architecture design,this paper emphatically analyzed the specific connotation and importance of ecological city and low-carbon garden,and the correlation between artificial neural network and landscape architecture design,and proposed the plant configuration model of landscape architecture design based on artificial neural network.The model training data set was collected through network crawler technology,and the application of AutoCAD formed the plant configuration layers.Ten parks in Xi′an,Shaanxi Province were randomly selected to analyze the relationship between vegetation types and the utilization frequency of plants.The results showed that the lower the frequency of plant use,the more plant species.In terms of arbor with specified planting area,the coordinate points generated by the system were controlled within the planting range,and the final output plant layers included arbor,ground cover and shrub.The three-dimensional graph of plant configuration clearly showed the distribution of arbor,shrub and ground cover,which proved that the artificial neural network plant configuration model was feasible.