Next Article in Journal
Evaluation of Tourism Development Potential and Its Influencing Mechanisms of Traditional Villages Based on Multi-Source Data and Interpretable Machine Learning: A Case Study of Shexian County, Huangshan City, China
Previous Article in Journal
Factor Mobility and Urban–Rural Integration in China: Unpacking Direct, Indirect, and Spatial Spillover Effects at the County Level
Previous Article in Special Issue
Analysis of Factors Influencing Fire Risk in High-Density Urban Areas Based on the CatBoost-SHAP Model
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Land
Volume 15
Issue 6
10.3390/land15060976
land-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Generative Regeneration of Historic Urban Fabric: A Framework Based on Deep Learning and Multi-Objective Optimization

by
Xiaoyu Ying
1,2,3,
Shenbo Ni
1,
Jiajing Wu
1,2,*,
Yujie Zhao
1,3,
Haiqiang Liu
4,
Rongxin Qiu
5,
Te Li
5,
Jiamei Bei
1 and
Hui Zhao
1
1
School of Art and Archaeology, Hangzhou City University, Hangzhou 310015, China
2
Zhejiang Engineering Research Center of Building’s Digital Carbon Neutral Technology, Hangzhou 310015, China
3
Zhejiang Provincial Collaborative Innovation Center for Immovable Cultural Heritage Protection Technology, Hangzhou 310015, China
4
Department of KANSEI Design Engineering, Faculty of Engineering, Yamaguchi University, Yamaguchi 753-8511, Japan
5
College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China
*
Author to whom correspondence should be addressed.
Land 2026, 15(6), 976; https://doi.org/10.3390/land15060976
Submission received: 12 April 2026 / Revised: 27 May 2026 / Accepted: 30 May 2026 / Published: 3 June 2026
(This article belongs to the Special Issue Feature Papers for "Land Innovations—Data and Machine Learning" Section: 3rd Edition)
Browse Figures
Versions Notes

Abstract

Amid China’s rapid urbanization, many historic districts face complex challenges, including fragmented traditional fabrics, disordered spatial morphology, and discontinuous street networks. To tackle these issues, this study proposes a multimodal deep learning framework that combines Generative Adversarial Networks (GANs) and Diffusion Models, establishing an integrated generation-optimization workflow for the renewal of historic districts. The methodology begins by using Pix2PixHD to generate high-precision fabric layouts, followed by fine-tuning a Diffusion Model through Low-Rank Adaptation (LoRA) to achieve diversified morphological expansion. The candidate proposals are quantitatively evaluated using a ten-indicator evaluation matrix that covers both architectural fabric and street network dimensions. Afterwards, these proposals undergo iterative optimization with a multi-objective framework to enhance both urban fabric morphology and network performance. The framework was validated through an empirical study of the Yuehe Historic District in Jiaxing. The results indicate that the generated schemes closely align with the original urban fabric. Compared with the existing expanded area (EA), the weighted comprehensive fitness score of the optimized scheme group improved from 0.66 to 0.89 ± 0.02 (a 34.8% increase), with the standard deviation decreasing from 0.07 to 0.02, indicating significantly enhanced stability. Deep learning balances morphological authenticity, generative diversity, and performance in historic district preservation and renewal.
Keywords: historic district renewal; historic urban fabric; deep learning; generative design; multi-objective optimization historic district renewal; historic urban fabric; deep learning; generative design; multi-objective optimization

Share and Cite

MDPI and ACS Style

Ying, X.; Ni, S.; Wu, J.; Zhao, Y.; Liu, H.; Qiu, R.; Li, T.; Bei, J.; Zhao, H. Generative Regeneration of Historic Urban Fabric: A Framework Based on Deep Learning and Multi-Objective Optimization. Land 2026, 15, 976. https://doi.org/10.3390/land15060976

AMA Style

Ying X, Ni S, Wu J, Zhao Y, Liu H, Qiu R, Li T, Bei J, Zhao H. Generative Regeneration of Historic Urban Fabric: A Framework Based on Deep Learning and Multi-Objective Optimization. Land. 2026; 15(6):976. https://doi.org/10.3390/land15060976

Chicago/Turabian Style

Ying, Xiaoyu, Shenbo Ni, Jiajing Wu, Yujie Zhao, Haiqiang Liu, Rongxin Qiu, Te Li, Jiamei Bei, and Hui Zhao. 2026. "Generative Regeneration of Historic Urban Fabric: A Framework Based on Deep Learning and Multi-Objective Optimization" Land 15, no. 6: 976. https://doi.org/10.3390/land15060976

APA Style

Ying, X., Ni, S., Wu, J., Zhao, Y., Liu, H., Qiu, R., Li, T., Bei, J., & Zhao, H. (2026). Generative Regeneration of Historic Urban Fabric: A Framework Based on Deep Learning and Multi-Objective Optimization. Land, 15(6), 976. https://doi.org/10.3390/land15060976

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop