In this paper, Macau Taipa Village, a historical district in an island-type city, is the research focus, and a parametric design-based method for designing historical districts is proposed. First, the shape and distribution of roads in historical districts is studied through on-the-spot investigation and measurement and data are collected on the width, depth, and area of street blocks, average street length and width, street orientation, building width, depth, acreage, and height, and building orientation. Second, the acquired data are transmitted to the Grasshopper parameterization platform, and an intelligently generated program produces calculations. Through multiple iterations and evaluations of genetic algorithms based on the needs of modern urban design and planning constraints, the building density is further reduced, and more landscape areas are added. The parametric model is optimized to gradually generate the urban spatial design that meets contemporary requirements. The research reveals that (1) the grasshopper algorithm’s generated block design inherits the characteristics of the conventional historical block. (2) The historical block where the data were collected on site and the block where Grasshopper is applied should maintain the consistency of the regional context. (3) This method can be applied to the design of new urban areas, and the scope of application can be further adjusted through collaboration and the needs of the owners at a later stage.

本研究将专业色卡与高效软件色彩识别相结合，提出了一种新的可量化、精细化的城市街道色彩分析方法，解决了城市色彩研究分析量化效率低、难度大的问题。 研究主要利用中国建筑色卡（CBCC）和Python（使用图片的HSV颜色分割程序）等软件对街景进行颜色识别。 本文从街道立面的色彩构成、类型、比例、视觉层次、色彩顺序等方面，对澳门新马路的色彩进行多角度的定量分析。 将色卡比色法与计算机颜色识别相结合的方法，不仅考虑了建筑物固有的颜色，还考虑了环境影响下的颜色情况，可以更完整地表达建筑物的“实际颜色情况”。 本文对建筑色彩和环境色彩进行了全面的量化、梳理、总结和比较。 该方法在实践中具有良好的普适性和易用性，研究结论可为澳门色彩规划提供参考，对城市更新的色彩选择具有参考意义，为城市色彩研究提供新方法 。

The Shanhaiguan Great Wall is a section of the Great Wall of the Ming Dynasty, which is a UNESCO World Heritage Site. Both sides of its basic structure are composed of rammed earth and gray bricks. The surface gray bricks sustain damage from environmental factors, resulting in a decline in their structural quality and even a threat to their safety. Traditional surface damage detection methods rely primarily on manual identification or manual identification following unmanned aerial vehicle (UAV) aerial photography, which is labor-intensive. This paper applies the YOLOv4 machine learning model to the gray surface bricks of the Plain Great Wall of Shanhaiguan as an illustration. By slicing and labeling the photos, creating a training set, and then training the model, the proposed approach automatically detects four types of damage (chalking, plants, ubiquinol, and cracking) on the surface of the Great Wall. This eliminates the need to expend costly human resources for manual identification following aerial photography, thereby accelerating the work. Through research, it is found that (1) compared with manual detection, this method can quickly and efficiently monitor a large number of wall samples in a short period of time and improve the efficiency of brick wall detection in ancient buildings. (2) Compared with previous approaches, the accuracy of the current method is improved. The identifiable types are increased to include chalking and ubiquinol, and the accuracy rate increases by 0.17% (from 85.70% before to 85.87% now). (3) This method can quickly identify the damaged parts of the wall without damaging the appearance of the historical building structure, enabling timely repair measures.

With the rapid growth of global urbanization and the rising demand for sustainable development, it is essential to study the performance and durability of building materials. As a traditional and widely employed building material, Chinese clay tiles play a significant role in traditional Chinese architecture. However, traditional methods for assessing structural surface damage necessitate the time-consuming and labor-intensive assessment and judgment of trained professionals. Consequently, it is crucial to employ machine learning techniques for automatic damage type identification. This study identifies the types of damage to Chinese clay tiles in Macau by employing machine learning techniques and the YOLOv4 object detection model. A total of 363 photographs of on-site Chinese clay tiles were used as training samples, and 200 epochs of the model training were performed. The primary findings of this study are as follows: (1) The machine learning method, based on the YOLOv4 model, provides an effective and precise solution for the automatic identification of Chinese clay tiles damage types, overcoming the human and time-cost constraints of conventional evaluation methods. (2) The detection accuracy of the detection model in this study is 95.42% for the detection of Chinese clay tiles cracks, 80.91% for the detection of stains, and 89.34% for the detection of surface wear, with an overall accuracy of 88.98%, which meets the basic detection requirements. (3) The experimental results demonstrate the viability and efficacy of the proposed method for identifying clay tile damage types and provide a method reference for the preservation and sustainable development of historical buildings.

The COVID-19 epidemic poses a global challenge. Urban wind environments, as integral parts of cities, may contribute to virus spread. Understanding their impact is vital for effective prevention strategies. This study employs a conditional generative confrontation network (CGAN) to train a model using simulated urban wind and COVID-19 distribution data. The model predicts COVID-19 distribution probability under various wind environments, revealing their relationship.

Artificial intelligence (AI) has influenced the design field, offering solutions to urban renewal design problems. This study aims to develop a stylized generation technology for building facade decoration in historic districts using conditional generative adversarial networks (CGANs). The research focuses on Putian, a historic district in Fujian Province. It includes image data acquisition, processing, screening, model training, image generation, and style matching. Findings show CGAN technology effectively generates historical district decorative styles, providing overall or partial facade design schemes. The method adapts to historical district reconstruction, facade renovation, and renovation design, especially for districts with distinct styles. It aids in determining facade decoration styles for specific historical buildings. The method learns internal laws of complex district styles, generating new designs with clear style attributes. It enhances stylized control in historical heritage protection, improving design efficiency.

The COVID-19 pandemic has prompted a reassessment of urban space, including planning and architecture. This study employs a conditional generative adversarial network (CGAN) to derive the distribution of urban texture based on COVID-19 hotspots. It establishes a link between urban form and the pandemic, enabling the machine to predict high-risk urban forms. The study focuses on Macau, conducting model training, image generation, and comparing results for different assumed epidemic distribution degrees. The implications for urban planning are as follows: 1) Urban forms exhibit a correlation with epidemic distribution, allowing CGAN to predict high-risk urban forms; 2) Large-scale and high-density buildings promote COVID-19 transmission; 3) Green public open spaces and squares inhibit COVID-19 spread; and 4) Reducing building volume and density while increasing green public spaces can help mitigate COVID-19 distribution. This research offers valuable insights and potential applications in planning and design.

The paper proposes a method for designing the floor plans of museum exhibition halls using a conditional generative adversarial network (CGAN). The traditional approach of designing exhibition hall floor plans individually for each floor in a multi-story building is time-consuming and inefficient. The CGAN-based method aims to streamline the design process and help architects work more efficiently.

This study proposes using the YOLOv4 machine learning model to automatically detect and classify five types of damage on historic gray-brick buildings, improving efficiency compared to manual assessment. The research focuses on gray- brick wall buildings in Macau’s global cultural heritage buffer zone. A total of 1355 on-site photographs were collected, identifying the five most common types of damage. From these images, a training set of 1000 labeled images was created for model training over 200 generations. The study concludes that gray-brick buildings in Macau sustain damage from the subtropical maritime climate, including missing paint, stains, and cracks. Machine learning aids in identifying damage types, assisting in management and protection. The proposed model accurately detects missing, cracking, erosion, yellowing, and pollution on gray-brick walls, enabling precise evaluation and protection strategies.

This research addresses the challenge of achieving a unified planning of architectural styles in urban expansion and preserving traditional buildings in villages and towns. It uses a conditional generative adversarial network (CGAN) to develop a technique for designing building facades in villages and cities. The results serve as design references, enhancing efficiency. The CGAN-Assisted model is applied to rehabilitate building facades and in visual design for rural tourism products, demonstrating practical usefulness and design potential. Using villages and towns in China’s Wuyishan area as an example, the study involves model training, image generation, and comparing results for different assumed buildings.