Assessing building energy consumption in urban neighborhoods at the early stages of urban planning assists decision-makers in developing detailed urban renewal plans and sustainable development strategies. At the city-level, the use of physical simulation-based urban building energy modeling (UBEM) is too costly, and data-driven approaches often are hampered by a lack of available building energy monitoring data. This paper combines a simulation-based approach with a data-driven approach, using UBEM to provide a dataset for machine learning and deploying the trained model for large-scale urban building energy consumption prediction. Firstly, we collected 18,789 neighborhoods containing 248,938 buildings in the Shanghai central area, of which 2,702 neighborhoods were used for UBEM. Simultaneously, building functions were defined by POI data and land use data. We used 14 impact factors related to land use and building morphology to define each neighborhood. Next, we compared the performance of six ensemble learning methods modeling impact factors with building energy consumption and used SHAP to explain the best model; we also filtered out the features that contributed the most to the model output to reduce the model complexity. Finally, the balanced regressor that had the best prediction accuracy with the minimum number of features was used to predict the remaining urban neighborhoods in the Shanghai central area. The results show that XGBoost achieves the best performance. The balanced regressor, constructed with the 9 most contributing features, predicted the building rooftop photovoltaics potential, total load, cooling load, and heating load with test set accuracies of 0.956, 0.674, 0.608, and 0.762, respectively. Our method offers an 85.5%-time advantage over traditional methods, with only a maximum of 22.75% of error.

Amid the escalating global climatic challenges, hydrological risks significantly influence human settlement patterns, underscoring the imperative for an in-depth comprehension of hydrological change’s ramifications on human migration. However, predominant research has been circumscribed to the national level. The study delves into the nonlinear effects of hydrological risks on migration dynamics in 46,776 global subnational units. Meanwhile, leveraging remote sensing, we procured globally consistent metrics of hydrological intrusion exposure, offering a holistic risk assessment encompassing hazard, exposure, and vulnerability dimensions, thus complementing previous work. Here, we show that exposure is the primary migration driver, surpassing socioeconomic factors. Surrounding disparities further intensified exposure’s impact. Vulnerable groups, especially the economically disadvantaged and elderly, tend to remain in high-risk areas, with the former predominantly migrating within proximate vicinities. The nonlinear analysis delineates an S-shaped trajectory for hydrological exposure, transitioning from resistance to migration and culminating in entrapment, revealing dependence on settlement resilience and adaptability.

The morphological design of urban space affects the quality of the environment. The traditional experience-based design approach was greatly improved by introducing computational design tools. However, the existing urban design tools are mostly developed on pre-set rules or given targets, which have few contributions to enhance creativity or generate inspiring schemes. Therefore, this paper proposes a new computational urban design approach named UDGAN, integrating generative adversarial networks (GANs) and multi-objective optimization algorithms. This model utilizes urban design scheme plans over the past 20 years from a particular designer as training datasets. Four preference models were trained to autonomously generate stylized urban design schemes. Eight morphological parameters were used to analyze the model performance by comparing generated results with the ground truth. This GAN-based surrogate approach is combined with a morphological indicator alignment process using multi-objective optimization model to obtain better results. The result shows that the R² predicted by the improved Pix2Pix model reaches 0.798, and the similarity of the generated results can be stably distributed between 0.7 and 0.8, so the design scheme of this preferred style can be effectively learned. At the same time, the pre-trained model greatly reduces the time consumption of the design scheme generation, taking 5 min approximately to complete a generation process. This approach quickly generated the design scheme with preferred features, supporting the designer with creativity and greatly saving the time of design creation, transforming computational design into an inspiration-driven process.

Visual perception of the urban landscape in a city is complex and dynamic, and it is largely influenced by human vision and the dynamic spatial layout of the attractions. In return, landscape visibility not only affects how people interact with the environment but also promotes regional values and urban resilience. The development of visibility has evolved, and the digital landscape visibility analysis method allows urban researchers to redefine visible space and better quantify human perceptions and observations of the landscape space. In this paper, we first reviewed and compared the theoretical results and measurement tools for spatial visual perception and compared the value of the analytical methods and tools for landscape visualization in multiple dimensions on the principal of urban planning (e.g., complex environment, computational scalability, and interactive intervention between computation and built environment). We found that most of the research was examined in a static environment using simple viewpoints, which can hardly explain the actual complexity and dynamic superposition of the landscape perceptual effect in an urban environment. Thus, those methods cannot effectively solve actual urban planning issues. Aiming at this demand, we proposed a workflow optimization and developed a responsive cross-scale and multilandscape object 3D visibility analysis method, forming our analysis model for testing on the study case. By combining the multilandscape batch scanning method with a refined voxel model, it can be adapted for large-scale complex dynamic urban visual problems. As a result, we obtained accurate spatial visibility calculations that can be conducted across scales from the macro to micro, with large external mountain landscapes and small internal open spaces. Our verified approach not only has a good performance in the analysis of complex visibility problems (e.g., we defined the two most influential spatial variables to maintain good street-based landscape visibility) but also the high efficiency of spatial interventions (e.g., where the four recommended interventions were the most valuable), realizing the improvement of intelligent landscape evaluations and interventions for urban spatial quality and resilience.