Cheng Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cheng Wei has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Yan Li
College of Architecture, Nanjing Tech University, Nanjing 211816, China
2 shared publications - Yijing Wang
College of Architecture, Nanjing Tech University, Nanjing 211816, China
2 shared publications - Hao Zou
College of Architecture, Nanjing Tech University, Nanjing 211816, China
1 shared publication - Xinru Huang
College of Architecture, Nanjing Tech University, Nanjing 211816, China
1 shared publication - Yujie Du
College of Architecture, Nanjing Tech University, Nanjing 211816, China
1 shared publication
Latest Publications
- Open Access
A Cross-Stage Human-GenAI Collaborative Workflow for Landscape Architecture Design: A Pocket Park Feasibility Study
Research on generative artificial intelligence (GenAI) in landscape architecture has largely focused on individual design stages. Few studies have examined how selected design information can transfer across design stages and how landscape architecture expertise can be incorporated into a workflow-level process. This study proposes a human–GenAI collaborative workflow that integrates design knowledge at each stage and facilitates information transfer across 2D plan generation, 3D spatial construction, and scene rendering. The workflow is implemented with a Stable Diffusion (v1.5) model fine-tuned with LoRA and conditioned by ControlNet, and comprises three stages. First, professional knowledge is encoded as semantic constraints, and the designer validates the results. Next, the designer translates the selected 2D plan into a 3D spatial model through designer-led spatial interpretation and modeling. Finally, the designer combines multi-condition rendering with professional knowledge and selects the final alternative. A pocket park case study demonstrates the feasibility of the proposed workflow. The generated alternatives were assessed against the stated design criteria in this case, and the results show the designer’s decisions at each stage and how those decisions informed the subsequent stage.
Open AccessA Cross-Stage Human-GenAI Collaborative Workflow for Landscape Architecture Design: A Pocket Park Feasibility Study
Research on generative artificial intelligence (GenAI) in landscape architecture has largely focused on individual design stages. Few studies have examined how selected design information can transfer across design stages and how landscape architecture expertise can be incorporated into a workflow-level process. This study proposes a human–GenAI collaborative workflow that integrates design knowledge at each stage and facilitates information transfer across 2D plan generation, 3D spatial construction, and scene rendering. The workflow is implemented with a Stable Diffusion (v1.5) model fine-tuned with LoRA and conditioned by ControlNet, and comprises three stages. First, professional knowledge is encoded as semantic constraints, and the designer validates the results. Next, the designer translates the selected 2D plan into a 3D spatial model through designer-led spatial interpretation and modeling. Finally, the designer combines multi-condition rendering with professional knowledge and selects the final alternative. A pocket park case study demonstrates the feasibility of the proposed workflow. The generated alternatives were assessed against the stated design criteria in this case, and the results show the designer’s decisions at each stage and how those decisions informed the subsequent stage.
- Open Access
- 3 July 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (13) , 6794
Informal Adaptations by Older Adults as Behavioural Evidence for Age-Friendly and Socially Sustainable Urban Green-Space Renewal: An Exploratory Multiple-Case Study in Nanjing, China
Population ageing is reshaping the use and evaluation of everyday urban green spaces, especially in old urban districts where nearby public spaces support walking, resting, exercise, and social contact. Conventional age-friendly assessments often emphasise whether formal infrastructure is provided, but facility provision alone does not ensure experiential fit with older adults’ functional capacities, daily routines, and social practices. This exploratory multiple-case study examines user-initiated informal adaptations in three neighbourhood-scale green spaces in Gulou District, Nanjing, China. Facility audits, approximately 30 h of non-participant observation, semi-structured interviews with 36 older users, and 220 valid questionnaires were combined through cross-case coding and qualitative triangulation. Three adaptation types were identified: supplementary, modifying, and appropriative adaptations. These practices were interpreted as context-dependent behavioural signals potentially associated with safety and convenience, ergonomic support and material-thermal comfort, social accessibility and spatial accommodation, and social support. Adaptation patterns varied descriptively across sites and age groups in relation to facility conditions, spatial organisation, activity intensity, and user characteristics. The findings suggest that, when interpreted alongside facility audits, interviews, and site context, older adults’ everyday adaptations may help identify possible mismatches between formal provision and actual use, offering a low-cost interpretative perspective for inclusive, incremental, and socially sustainable green-space renewal.
- 3 July 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (13) , 6794
Open AccessInformal Adaptations by Older Adults as Behavioural Evidence for Age-Friendly and Socially Sustainable Urban Green-Space Renewal: An Exploratory Multiple-Case Study in Nanjing, China
Population ageing is reshaping the use and evaluation of everyday urban green spaces, especially in old urban districts where nearby public spaces support walking, resting, exercise, and social contact. Conventional age-friendly assessments often emphasise whether formal infrastructure is provided, but facility provision alone does not ensure experiential fit with older adults’ functional capacities, daily routines, and social practices. This exploratory multiple-case study examines user-initiated informal adaptations in three neighbourhood-scale green spaces in Gulou District, Nanjing, China. Facility audits, approximately 30 h of non-participant observation, semi-structured interviews with 36 older users, and 220 valid questionnaires were combined through cross-case coding and qualitative triangulation. Three adaptation types were identified: supplementary, modifying, and appropriative adaptations. These practices were interpreted as context-dependent behavioural signals potentially associated with safety and convenience, ergonomic support and material-thermal comfort, social accessibility and spatial accommodation, and social support. Adaptation patterns varied descriptively across sites and age groups in relation to facility conditions, spatial organisation, activity intensity, and user characteristics. The findings suggest that, when interpreted alongside facility audits, interviews, and site context, older adults’ everyday adaptations may help identify possible mismatches between formal provision and actual use, offering a low-cost interpretative perspective for inclusive, incremental, and socially sustainable green-space renewal.