The rapid expansion of urban land has altered land use/land cover (LULC) types, affecting land surface temperatures (LSTs) and intensifying the urban heat island (UHI) effect, a prominent consequence of urbanization. This study, which focuses on Harbin, a representative city in a cold region, employs the patch-generating land use simulation (PLUS) model to predict LULC changes and a Bidirectional Long Short-Term Memory (Bi-LSTM) model to predict LST. The PLUS model exhibits a high prediction accuracy, evidenced by its FoM coefficient of 0.15. And the Bi-LSTM model also achieved high accuracy, with an ${\mathrm{R}}^2$ value of 0.995 and 0.950 and a root mean square error (RMSE) of 0.199 and 0.390 for predictions in winter and summer, respectively, surpassing existing methods. This study analyzed the trends in LULC, LST, and the urban thermal field variance index (UTFVI) to assess the relationships among LST, LULC, and UTFVI. The results show that urban land increased by 27.81%, and woodland and grassland decreased by 61.07% from 2005 to 2030. Areas with high temperatures increased by 40.86% in winter and 60.90% in summer. The proportion of the medium UTFVI zone (0.005–0.010) in urban land increased by 50.71%, and the proportion of areas with medium UTFVI values and above (>0.005) decreased at a rate of 84.70%. This finding suggests that the area affected by the UHI has decreased, while the UHI intensity in some regions has increased. This study provides a technical reference for future urban development and thermal environment management in cold regions.

In the context of urban sustainable development and the creation of pedestrian-friendly campus environments, optimizing campus walking spaces has emerged as a central focus in urban planning research. Presently, research in pedestrian environments predominantly adopts a macroscopic perspective, offering limited insights into pedestrians’ subjective experiences and emotional perceptions at a micro level. Therefore, this study conducted on-site experiments in 21 walking spaces across three campuses, utilizing image semantic analysis, multifunctional sound level meter, wearable electrocardiography devices, and the Profile of Mood States (POMS) to collect data separately on audio-visual environmental factors and pedestrians’ emotional states. This study’s findings revealed significant correlations (p < 0.01) among factors such as the Green Visual Index, Spatial Enclosure Index, Sky Visibility Index, Spatial feasibility Index, and Equivalent Continuous A-weighted Sound Pressure Level with physiological and psychological alterations in pedestrians’ emotions. Additionally, the various proportions of audio-visual environmental factors also exerted significant influences on emotions (p < 0.05). The relevant conclusions can provide a reference for optimizing the audio-visual environment of walking space and promoting the sustainable development of the campus. In future research, the effects of audio-visual environments on both emotional and physiological indicators, as well as subjective evaluations, can be explored further.

To strike a trade-off between walking behavior and street resource constraint, extensive research tends to focus on how the urban environment affects walking behavior. However, most of the existing impact measurements focus on the cities in low-latitude temperate environments, which may not truly reflect the situation when assessing high-latitude cities. To address this drawback, in this paper, a general multi-factor framework is introduced to quantify the influence of street-level environmental factors on walking behavior. Specifically, a framework is constructed by comprehensively considering the subjective data and the objective data of Harbin, China, which is mainly composed of multivariate measurement indicators, a multi-source data analysis library, and four-dimensional evaluation paradigm. The results indicate that two main measures can promote the current situation of human-oriented living street environment planning, namely, increasing the distribution of green facilities and life service facilities in the old urban districts living street, and paying attention to the diversity of street greening and street landscape. The proposed framework is conducive to improve the planning status of human-centered street environments and guide the construction of pedestrian-friendly life and healthy streets.

With the continuous development of society and economy, the construction of urbanization has promoted the continuous expansion of the scale of the city. The disorderly and rough land acquisition and construction has brought about the problems of inefficient use of many resources, which are in line with the concept of green and smart construction. Violated. In response to these shortcomings and needs, this article introduces deep learning algorithms and remote sensing image scenes. Based on the business logic of smart city building energy-saving design, the data set is analyzed by category according to different types of supervision and deep learning to realize the smart city. Effective analysis of building energy efficiency, and a simulation quantitative experiment for evaluation, using BIM technology to analyze the energy-saving design of office buildings, to achieve further optimization of energy-saving design. The simulation experiment results show that the deep learning algorithm and remote sensing image scene are effective and can support the energy-saving design of smart city buildings.

At present, the sharp decline in urban biodiversity worldwide is severe. Conducting biological perspective analysis and proposing space construction solutions during urban regeneration can greatly alleviate the contradiction between urban construction and biodiversity conservation. In this study, birds were taken as biological representatives, and a certain area in Shenzhen with strong conservation needs was used as an example. Based on a thorough analysis of bird status, the minimum resistance model was applied to establish a resistance surface describing the real flight movement of the indicator species and to construct a bird conservation pattern from the flight process of birds. The results show that: (1) bird flight resistance is the lowest in the southern green space and northern woodland around the reservoir in the research region, and the resistance is higher in the central part, but the path of least resistance therein has the potential to become a corridor. (2) From the perspective of the community structure of green space vegetation, the sparse woodland and shrubland in the research region have low resistance and high richness, which are the most ideal green space forms for birds; from the perspective of architecture, bird flight resistance shows a negative correlation with building height and a positive correlation with building density. The final urban regeneration design plan is thus derived, and the validity of the method is verified based on the biodiversity index. This study reveals the possibility of applying bird flight resistance analysis based on the minimum resistance model to small and medium-scale urban regeneration areas, and also provides insight into the correlation between flight resistance and spatial design elements, which can assist decision-makers, planners and developers in spatial design and planning from a biological standpoint.

Context The inequality in urban thermal comfort exposure has become a pressing issue in landscape ecology, exacerbated by climate change and rapid urbanization. However, the modifiable areal unit problem (MAUP) introduces significant uncertainty in spatial assessments, undermining efforts to understand and address thermal comfort exposure inequality through landscape planning. Objectives This study aims to (1) evaluate how MAUP affects the measurement of thermal comfort exposure inequality and its influencing factors and (2) identify the optimal spatial scale for accurate analysis. The case study focuses on Zhengzhou’s central urban area. Methods Thermal comfort exposure inequality was quantified across 12 grid scales using the modified temperature‒humidity index, a population-weighted exposure model, and the Gini coefficient. We applied the optimal geodetector, gradient boosting regression tree, and multiscale geographically weighted regression (MGWR) to assess MAUP effects and spatial heterogeneity. Results MAUP significantly alters the explanatory power and ranking of influencing factors. A 3 × 3 km grid was identified as the optimal spatial unit. Population density (q = 0.837) and the green space ratio (q = 0.641) were the dominant drivers. Interaction detection revealed nonlinear enhancement between key factors. MGWR confirmed the spatially heterogeneous effects on the thermal comfort exposure inequality distribution. Conclusions This study highlights the importance of considering MAUP in thermal comfort exposure assessments to ensure accurate and equitable urban planning. Prioritizing green space expansion and optimizing its distribution in densely populated areas can effectively reduce thermal inequality. These findings offer insights for promoting environmental justice and sustainable urban development in high-density cities, such as Zhengzhou.