高级检索
    赵晶, 陈然, 郝慧超, 邵壮. 机器学习技术在风景园林中的应用进展与展望[J]. 北京林业大学学报, 2021, 43(11): 137-156. DOI: 10.12171/j.1000-1522.20200313
    引用本文: 赵晶, 陈然, 郝慧超, 邵壮. 机器学习技术在风景园林中的应用进展与展望[J]. 北京林业大学学报, 2021, 43(11): 137-156. DOI: 10.12171/j.1000-1522.20200313
    Zhao Jing, Chen Ran, Hao Huichao, Shao Zhuang. Application progress and prospect of machine learning technology in landscape architecture[J]. Journal of Beijing Forestry University, 2021, 43(11): 137-156. DOI: 10.12171/j.1000-1522.20200313
    Citation: Zhao Jing, Chen Ran, Hao Huichao, Shao Zhuang. Application progress and prospect of machine learning technology in landscape architecture[J]. Journal of Beijing Forestry University, 2021, 43(11): 137-156. DOI: 10.12171/j.1000-1522.20200313

    机器学习技术在风景园林中的应用进展与展望

    Application progress and prospect of machine learning technology in landscape architecture

    • 摘要: 随着风景园林数字化技术的应用发展,大数据技术和人工智能技术逐渐被应用到风景园林专业,解决了众多问题,机器学习技术同时作为大数据处理工具和人工智能核心技术之一也逐渐成为风景园林研究的热门话题。本文对近年来国内外的相关实践进行系统地总结和分析,先进行应用背景的介绍,分析机器学习在风景园林应用的适用性;再基于机器学习在风景园林中解决问题角度的不同,从场地信息提取,景观分析与评价和基于深度学习的方案自生成系统3个应用角度,对国内外已有实验的方法过程进行举例分析。最后基于对机器学习技术在风景园林应用的不同领域间的关系、同领域间的不同应用的关系的分析对未来的趋势进行了展望。从技术层面上,构建基于多种数据的综合性景观评价模型、景观分析模型是未来较有前景的研究方向;从应用层面上,随着多种智能化技术的整合和多源数据的整合,结合实际规划设计项目构建基于多种人工智能方法的数字化规划设计方法是机器学习在风景园林应用领域未来的重要趋势。

       

      Abstract: With the application and development of digital technology of landscape architecture, big data technology and artificial intelligence technology have been gradually applied to landscape architecture, which have solved many problems. Machine learning technology, as a tool for processing big data and one of the core technologies of artificial intelligence, has gradually become a hot topic in landscape architecture research. In this paper, the relevant practices at home and abroad in recent years have been systematically summarized and analyzed. Firstly, the application background was introduced to analyze the applicability of machine learning in landscape architecture. Secondly, based on different perspectives for machine learning to solve the problem in the fields of landscape architecture, the existing methods and processes of experiments at home and abroad were analyzed with examples from the site information extraction, landscape analysis and evaluation, self-generating system for planning schemes based on the deep learning algorithm. Finally, based on the analysis of relationship between different fields and application in the same field of machine learning technology in landscape architecture, the future trend was prospected. From the technical level, constructing a comprehensive landscape evaluation model and landscpae analysis model based on a variety of data is a promising research direction in the future. On the application level, constructing digital planning and design methods based on various artificial intelligence methods with the integration of various intelligent technologies, the integration of multi-source data and the combination of practical planning and design projects is an important trend of machine learning in the future.

       

    /

    返回文章
    返回