Scholarlink

Background <p>Deep learning (DL) represents an innovative technological approach that provides advanced solutions for land resource management and urban development forecasting by efficiently processing large-scale, heterogeneous data.</p> Methods <p>This study utilizes bibliometric analysis, drawing on data from the Web of Science Core Collection. Tools such as CiteSpace, VOSviewer, and Bibliometrix were employed to investigate the role of deep learning in urban land planning (ULP).</p> Results <p>Since 2014, publications related to deep learning have consistently increased, with China emerging as a global leader in both research and practical application. The study highlights that deep learning techniques, particularly convolutional neural networks (CNNs) and semantic segmentation, offer considerable advantages in land classification, resource optimization, and urban expansion prediction.</p> Significance <p>By automating intricate spatial analyses, deep learning significantly enhances planning precision and flexibility, offering strong technical support for addressing challenges such as inefficient land use, environmental degradation, and social inequality. Future research should prioritize improving model interpretability, enhancing data quality, and addressing ethical concerns to foster the advancement of intelligent and sustainable urban development.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hot keywords, thematic evolution, and emerging trends in the application of deep learning for urban land planning research

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月6日

查看全文
  • Shuman Qiu,
  • Chengfeng Zhang

摘要

Background

Deep learning (DL) represents an innovative technological approach that provides advanced solutions for land resource management and urban development forecasting by efficiently processing large-scale, heterogeneous data.

Methods

This study utilizes bibliometric analysis, drawing on data from the Web of Science Core Collection. Tools such as CiteSpace, VOSviewer, and Bibliometrix were employed to investigate the role of deep learning in urban land planning (ULP).

Results

Since 2014, publications related to deep learning have consistently increased, with China emerging as a global leader in both research and practical application. The study highlights that deep learning techniques, particularly convolutional neural networks (CNNs) and semantic segmentation, offer considerable advantages in land classification, resource optimization, and urban expansion prediction.

Significance

By automating intricate spatial analyses, deep learning significantly enhances planning precision and flexibility, offering strong technical support for addressing challenges such as inefficient land use, environmental degradation, and social inequality. Future research should prioritize improving model interpretability, enhancing data quality, and addressing ethical concerns to foster the advancement of intelligent and sustainable urban development.