The research value of Landscape Character Assessment (LCA) lies in gaining a deeper understanding of the inherent attributes and interrelationships of various landscapes, thereby providing scientific basis for landscape planning, design, conservation, and sustainable utilization. The traditional LCA methods often overlook the inherent connections between various landscape attributes and geographical spatial relationships among data points, which restricts their application in sustainable multi-scale landscape element assessments. Accordingly, this paper proposes a new paradigm for LCA, SwinClustering, built upon the cutting-edge Swin Transformer architecture. This approach employs a visual segmentation method to achieve multi-scale clustering, utilizing nine key attributes of landscape elements: altitude, aspect, geology, landcover, landform, relief, slope, soil, and vegetation. By extracting semantic features through the GIS-aware Swin Transformer backbone network and leveraging the Feature Pyramid Decoder for segmentation clustering, SwinClustering offers a comprehensive analysis of landscape characteristics. Furthermore, we design a specific training strategy that enables coarseness and fineness control of the clustering results. SwinClustering is tested across three distinct scales: the national scale of China, the municipal scale of Beijing Municipality and the district scale of Wuyishan National Park. These experiments yield promising results, validating the method’s effectiveness across diverse geographic scales. Crucially, the proposed SwinClustering paradigm establishes a unified clustering framework to deeply learn the intrinsic connection between various landscape attributes and the spatial relationship between different geographic locations. Furthermore, its strong generalization capabilities enable its seamless application to LCA tasks at arbitrary scales, marking a sustainable development in the field of LCA.

Landscape architects have a responsibility to society, the environment, the client, and other professional organizations. Professionals that undertake landscape-led planning projects need to adopt a comprehensive approach in all the associated aspects. This article summarizes a unique experience in landscape-led planning practice in the UK where most projects are either town planning or architect-led: (1) the housing scarcity problem in towns and villages, land within the Green Belt in the UK is in strict governance by planning policies. In this article, a case study of exceptional infilling villages in East Hertfordshire is used to drive a landscape-led, multi-disciplinary planning process and to analyze all expertise assignments involved; (2) materials were sought from a variety of sources including council official online guidance, public open access materials, project team communication, and consultation results which covered local residents engagement and anonymous comments during the publicity period of the planning decision. Desktop studies, site visits, and the expertise of the multi-disciplinary team were applied throughout the case; (3) with a year of planning teamwork, the proposed development of the study site met the local sustainable growth that planning permission for high-quality residential dwellings was granted by the Local Planning Authority; (4) since known landscape-led planning examples are limited in the UK, the case study formed a good example for scholars and researchers who are interested in planning in the Green Belt.