Block Scale Research Articles

Street trees: The contribution of latent heat flux to cooling dense urban areas

Trees are the most important natural factor to alleviate the urban heat island effect and the latent heat flux (LE) they release contributes significantly to urban cooling. In this study, the model ENVI-met was used to study the influence of building geometry on the LE exchanged by trees at the block scale in compact urban areas. The building density (BD), building height (BH) and sky view factor (SVF) were used to characterize building geometry. The sensitivity of LE to building geometry was estimated by multi-linear regression analysis. The following conclusions were drawn:(1) the LE of trees is sensitive to building geometry, higher during daytime than night-time in winter and the higher during night-time than daytime in summer; (2) LE changes as expected across the seasons, with LE larger in summer; (3) The shade affects the LE of a tree by influencing the solar irradiance; (4) In winter the average LE of a single tree is larger with 0.06 than 0.12 fractional vegetation cover (FVC). This study can provide useful leads towards further research to explore latent heat exchanges by trees at the street scale.

A Study on the Effect of Urban Form on the Street Interface Rhythm Based on Multisource Data and Waveform Classification

Good-quality urban street space is crucial for improving walkability. Frequency and amplitude are the main spatial characteristics of the street interface rhythm, known as a “virtual–real” relation. Exploring the mechanism influencing the urban street interface rhythm can help grasp the movement trend. In this study, the correlation between frequency and urban form is explored through a Pearson correlation analysis with multisource data, and the factors influencing the urban street interface rhythm are presented. The results indicate that frequency has a moderate negative correlation with the block scale and a moderate positive correlation with the number of pedestrian access entrances (PAE-n); the PAE-n also has a strong negative correlation with the block scale. Some spatial characteristics of outstanding streets from different countries are analyzed and discussed based on waveform classification. The regularities of interface rhythm that exist within multiple streets are found: multiple gaps on the street interface exist, acting as a “beat”, which regularly integrates or separates the street interface rhythm. The frequency and amplitude of the “beat” significantly affect streets’ walkability, and the amplitude is generally low and uniform, with good visual accessibility in all directions. A “Small Block and Dense Grid” becomes a key factor in improving walkability. Basic knowledge of the street interface rhythm in urban walking space research is supplemented by this study. Furthermore, theoretical guidance and parametric evidence are provided to improve walkability and promote the continuation of the traditional context.

Urban Morphology Classification and Organizational Patterns: A Multidimensional Numerical Analysis of Heping District, Shenyang City

Prior studies have failed to adequately address intangible characteristics and lacked a comprehensive quantification of cultural dimensions. Additionally, such works have not merged supervised and unsupervised classification methodologies. To address these gaps, this study employed multidimensional numerical techniques for precise spatial pattern recognition and urban morphology classification at the block scale. By examining building density, mean floor numbers, functional compositions, and street block mixed-use intensities, alongside historical and contemporary cultural assets within blocks—with assigned weights and entropy calculations from road networks, building vectors, and POI data—a hierarchical categorization of high, medium, and low groups was established. As a consequence, cluster analysis revealed seven distinctive morphology classifications within the studied area, each with unique spatial configurations and evolutionary tendencies. Key findings include the dominance of high-density, mixed-use blocks in the urban core, the persistence of historical morphologies in certain areas, and the emergence of new, high-rise clusters in recently developed zones. The investigation further elucidated the spatial configurations and evolutionary tendencies of each morphology category. These insights lay the groundwork for forthcoming studies to devise morphology-specific management strategies, thereby advancing towards a more scientifically grounded, rational, and precision-focused approach to urban morphology governance.

Spatial heterogeneity of the integrated risks of urban heat stress and flooding strike

Clarifying the spatial heterogeneity of the multiple climate-related risks has increasingly become a prerequisite for urban risk management and sustainability. As the datasets become more detailed in social attribute's representation at the fine scale within-city level, in contrast to those at a coarse region level, there is a continuous need to examine the spatial heterogeneity of integrated risk assessment. In this study, we applied the hazard-exposure-vulnerability framework to investigate the spatial variations of the integrations of urban heat stress and flooding strikes at the street block scale within Shenzhen, China. The findings showed approximately 16.85 % of the built-up areas experienced a strong dual pressure of heat and flooding, mostly concentrated in the street blocks constructed before 1990. Another 19.84 % of built-up areas exhibited a high level of heat risk, concentrated in the northern urban areas that developed in the recent period. While 26.28 % demonstrated a high level of flooding risk, located in the old urbanized areas. Such spatial variations of integrated risks resulted from the spatial mismatched hotspots among hazard, exposure, and vulnerability. The spatial heterogeneity of the integrated risk assessment suggests differentiated strategies to reduce the maladaptation of urban heat stress and flooding strike. The findings present opportunities to prioritize the street blocks and develop the most sustainable solutions.

Comparison and theoretical conceptualization analysis of statistical methods used to develop heat vulnerability indices in urban areas

In view of the impact of extreme temperatures on physical and psychological health, particularly in urban areas, several studies have focused on assessing social vulnerability using quantitative indexing approaches with the aim of creating a heat vulnerability index (HVI). In this context, this study employs three statistical methodologies frequently used to construct HVIs on the territory of the Toulouse Métropole, France, at the census block (IRIS) scale to assess the efficiency of this type of approach for evaluating social vulnerability in urban environments considering the current theoretical conceptualization. The three HVIs show the same general trends, with a spatial configuration in which high levels of vulnerability are concentrated in the downtown and suburbs of the Toulouse municipality. Vulnerability gradually decreases away from the urban core, becoming moderate in the inner suburbs and low on the outskirts. However, a spatial analysis of the clusters reveals variability in the boundaries of the vulnerability hotspots. Value class matching indicates that a significant number of census blocks are classified differently according to the method considered. These results raise questions concerning the ability of HVIs to provide reliable vulnerability assessments, given their geostatistical and conceptual limitations. Indexing approaches therefore appear to contradict current theoretical conceptualizations promoting the concept of vulnerability as being complex and multifactorial.

Multi-scale correlation analysis between geometric parameters and solar radiation in high density urban environment——Case study in Nanjing

This study explores the impact of multi-scale urban morphology on solar radiation in high-density environments, focusing on Nanjing as a case study. Using Grasshopper, the research decomposed urban models into four scales—district, block group, block, and plot—and analyzed eight morphological indicators, including site coverage (SC), floor area ratio (FAR), and block surface ratio (BSR). Solar radiation was simulated for the entire year, the summer solstice, and the winter solstice. Key findings reveal that different scales exhibit varying influences on solar radiation. At the district scale, BSR shows the highest correlation with annual solar radiation (R2 = 0.96), while at the neighborhood cluster scale, the minimum distance between buildings (DBmin) is most correlated (R2 = 0.7). At the block scale, BSR significantly correlates with summer solar radiation (R2 = 0.55). At the plot scale, no single indicator strongly correlates with solar radiation, but a combination of indicators is more relevant. These findings enable rapid solar performance assessments in urban design, promoting efficient solar energy use.

The role of Nature-Based Solutions for the water flow management in a Mediterranean urban area

Due to climate change and rapid urban sprawl, central Mediterranean regions are subjected to short but intensive storm events resulting in a significant increase of flow rates and runoff volumes in low-lying coastal urban areas. Within the framework of green urban infrastructures (GUIs), a suitable combination of Nature-Based Solutions (NBS) with traditional grey infrastructures should be adopted to mitigate flood risk effects in urban and sub-urban areas contributing at the same time to achieve multiple benefits for both the environment and the community. The aim of this study is (i) to evaluate flood hazard maps for identifying the areas within a Sicilian hydrological river basin (Toscano catchment) with a high risk of flooding by implementing the HEC-RAS model at catchment scale; (ii) to quantify the peak flow and floodplain area reduction; (iii) to assess the effectiveness of small-scale NBS (green roofs, porous pavements, rain gardens and rain barrel), in terms of peak flow and runoff volume reductions, at urban block scale by using the EPA SWMM model Model simulations are performed integrating the hydraulic (HEC-RAS) and hydrological (EPA SWMM) models for return periods of 10, 50 and 200 years. The results showed that the estimated peak flow (m3 s−1) obtained from the simulations performed at catchment scale for each T in the current scenario (without NBS) using HEC-RAS and EPA SWMM models are very close to each other (R2 = 0.99). In addition, the utopian scenario simulation showed the HEC-RAS model sensitivity to CN calibration achieving a peak flow reduction up to about 60% with the floodplain area decreasing up to about 17%. Finally, the model EPA SWMM shows its sensitivity to NBS implementation at urban block scale with a peak flow reduction up to about 16% and a runoff volume (mm) reduction up to about 24%. These reductions decrease as T increases with a higher NBS mitigation effects for the lowest T. The results highlighted that the integration of NBS in urban areas could have hydrological and hydraulic positive effects, particularly in terms of peak flow and runoff volume reduction. Furthermore, the results suggest that small-scale NBS have a potential to be effective to smaller rainfall events, but a combination with large-scale NBS is necessary to cope with extreme events.

Characterization of natural fracture development in coal reservoirs using logging machine learning inversion, well test data and simulated geostress analyses

Natural fractures directly affect the permeability and mechanical strength of reservoirs, and their development degree has an important impact on the design and implementation of engineering and development projects. Although there is some correlation between logging data and fracture development, studies using algorithms to optimize logging predictions are still scarce. Meanwhile, there is a scarcity of calculations and analyses concerning the distribution of geostress at the block scale, and the pivotal role that geostress plays as a tectonic factor in the development of fractures. In this study, machine learning methods are used to predict reservoir fracture development, and regional geostress distribution patterns derived from well test data and finite element methods are combined for verification. The support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost) and back propagation neural network (BPNN) algorithms are used to predict the fracture development of No.15 coal reservoir in the block. The results showed that the accuracy of SVM is 83.3 %, RF is 91.6 %, XGBoost is 93.7 % and BPNN is 95.8 %. The BPNN can effectively predict the reservoir fracture development of the block. Combined with the regional finite element stress-strain analysis and geostress measurement, the prediction of No.15 coal geostress distribution and fracture development model is established. Under comprehensive verification, the established distribution of the degree of regional fracture development under the control of geostress is consistent with the results of the BPNN prediction of fracture development. These results show that the regional geostress calculated in association with finite element analysis (FEA) can reflect the development of fracture in coalbed methane (CBM) reservoirs, and the neural network has good performance in predicting regional fracture development. This work provides a new approach to the application of machine learning in the field of geological engineering, and the comprehensively validated model provides geologists and geological engineers with ideas in algorithmic practice.

A study on the classification of complexly shaped cultivated land considering multi-scale features and edge priors.

Obtaining accurate cultivated land distribution data is crucial for sustainable agricultural development. The current cultivated land extraction studies mainly analyze crops on a regular shape and a small block scale. Aiming at the problem of fragmentation of plots in complexly shaped cultivated land leads to variable scales and blurred edges and the difficulty of extracting the context information by kernel convolution operation of the CNN-based model. We propose a complexly shaped farmland extraction network considering multi-scale features and edge priors (MFEPNet). Specifically, we design a context cross-attention fusion module to couple the local-global features extracted by the two-terminal path CNN-transformer network, which obtains more accurate cultivated land plot representations. This paper constructs the relation maps through a multi-scale feature reconstruction module to realize multi-scale information compensates by combining the gated weight parameter based on information entropy. Additionally, we design a texture-enhanced edge module, which uses the attention mechanism to fuse the edge information of texture feature extraction and the reconstructed feature map to enhance the edge features. In general, the network effectively reduces the influence of variable scale, blurred edges, and limited global field of view. The novel model proposed in this paper is compared with classical deep learning models such as UNet, DeeplabV3 +, DANet, PSPNet, RefineNet, SegNet, ACFNet, and OCRNet on the regular and irregular farmland datasets divided by IFLYTEK and Netherlands datasets. The experimental results show that MFEPNet achieves 92.40 and 91.65 MIoU on regular and irregular farmland datasets, which is better than the benchmark experimental model.

How do driving factors affect the diurnal variation of land surface temperature across different urban functional blocks? A case study of Xi'an, China

A comprehensive and in-depth understanding of the formation mechanisms of the urban thermal environment is the basis for thermal environment regulation, however, there is insufficient knowledge regarding how driving factors influence daytime and nighttime land surface temperature (LST) within urban functional blocks (UFBs). We selected Xi'an, China as a case study, integrating remote sensing data including ECOSTRESS, Landsat-8, and Gaofen-1, along with geographic data including road network, areas of interest, points of interest, building footprint, and mobile phone signaling. It divided 10 types of UFBs, inverted daytime and nighttime LST, calculated 5 types of driving factors, and finally analyzed the contribution and marginal effects of driving factors on day-night LST using boosted regression tree. The results showed that LST and its driving factors differed significantly in different times and UFBs. Industrial blocks and urban villages had higher LST in the daytime, while residential blocks, commercial blocks, and public service blocks had higher LST in nighttime. Industrial blocks were the dominant blocks that drove the overall LST up during the day, while residential blocks were the dominant blocks at night. Location distance (-) and population density (+) affected LST in all UFBs during day and night, NDVI (-), building density (+), and floor area ratio (-) were key factors for most UFBs during daytime, and NDVI (+), surface albedo (-), and point density of interest (+) were key factors during nighttime. Most of the driving factors had significant influence thresholds, but there were small differences across UFBs. This paper aims to elucidate the mechanisms by which driving factors influence urban LST during day and night across different UFBs, thereby providing new support for more targeted thermal environment regulation and diurnal trade-offs at the block scale.

Quantifying the influences of landscape gradient on urban spatial efficiency by using surface metrics in the central area of a mountainous city

Rapid urbanization in mountainous areas has caused unbalanced development, land use conflicts, and decreased urban spatial efficiency (USE) due to terrain constraints and disorderly land expansion, and this issue has not been fully explored. To address this gap, this study constructs a framework to quantify the impacts of landscape gradients on urban spatial efficiency. By developing indicator systems to characterize both landscape heterogeneity and urban spatial efficiency, the relationships between these factors are analyzed using the Boosting Regression Trees model, and clusters are identified to reveal spatial differentiation through key landscape gradient indicators. The results indicate that (1) the Summit Density (Sds) of Normalized Difference Vegetation Index (NDVI) exhibits the most significant negative impact on urban spatial efficiency, especially on spatial utilization efficiency; (2) the Root Mean Square Slope (Sdq) of Digital Elevation negatively affects traffic and public services efficiency; (3) the Texture Direction Index (Stdi) of building distribution has the most significant positive impact on public service efficiency. In mountainous environments, different landscape gradient types exhibit clear contrasts in urban spatial efficiency. Varied elevations lead to diverse construction sites and building layouts within urban blocks, resulting in spatial differentiation of urban spatial efficiency. This study enhances the use of gradient surface metrics in urban spatial research by describing landscape patterns and heterogeneity at the block scale. It offers valuable insights for urban planning and design with a focus on equity and sustainability.

Spatiotemporal heterogeneity of the relationship between urban morphology and land surface temperature at a block scale

Understanding the relationship between urban morphology and land surface temperature (LST) is essential for mitigating urban heat island (UHI). This study investigates the spatiotemporal heterogeneity of the relationship between urban morphology and LST across 5 experiment sites located in different temperature zones of China at a block scale. Normalized difference vegetation index (NDVI), building density (BD), floor area ratio (FAR), average building height (ABH) and open space ratio (OSR) are adopted to indicate the physical urban morphology. The results show positive relationship between BD and LST, and negative relations between LST and NDVI, ABH and OSR from a global perspective. The relations of FAR to LST are mixed. However, variable relationship between urban morphological indicators (UMIs) and LST are significantly observed at a block scale. 12 scenes that generate local relations of UMIs and LST differing from that of the surroundings are identified. Typical strategies for land development, vegetation phenology, large natural elements and human activities may be the most important causative factors to the heterogenous relationship between urban morphology and LST. Findings derived in the study would promote studies on mechanisms of the effects of urban morphology on LST and contribute to practices of UHI mitigation.

Assessing urban renewal opportunities by combining 3D building information and geographic big data

ABSTRACT The assessment of urban renewal (UR) potential aims to prioritize areas for UR, which are essential for sustainable urban revitalization. However, conventional data sources often fall short in encompassing diverse urban characteristics in the evaluation process, such as urban three-dimensional (3D) building information and the intensity of human activities. To address this gap, this study integrated 3D building data and geographic data to create a comprehensive set of 28 indicators spanning four dimensions: natural environmental conditions, land use, socio-economic factors, and building conditions. These indicators take into account vertical dimensions, dynamic aspects, and fine-scale details. Leveraging the existing UR practices as a positive example, we established an UR potential assessment model at street block scale using Presence and Background Learning combined with extreme gradient boosting algorithms (PBLXGBoost). Our findings revealed that the highest accuracy in evaluating industrial UR potential was achieved in Shenzhen (F pb _ avg = 0.80, RMSE avg = 0.21), followed by residential and commercial UR potential assessments. Conversely, other type UR exhibit lower accuracy. Street blocks with significant UR potential are predominantly located in Bao’an, Longgang, and Longhua Districts. Furthermore, employing the SHAP model to elucidate the evaluation results uncovered intricate hierarchical, positive-negative, and overlapping relationships among various factors and different UR types, where geographic big data and 3D building information showed strong correlations. The methodology proposed in this study enables objective and precise assessments of UR potential, offering valuable support for UR practice and sustainable urban development.

How Does Density Impact Carbon Emission Intensity: Insights from the Block Scale and an Optimal Parameters-Based Geographical Detector

Density is a crucial indicator for urban sustainable development and is considered a critical factor influencing the carbon emission intensity of construction land (CICL). The impact of density on carbon emissions has been extensively explored, mainly focusing on grid-scale and single-factor effects. However, how density and its interactions affect carbon emissions at the block scale is unclear. Therefore, based on multiple data sources such as energy consumption, remote sensing, and the point of interest (POI) in the urban block of Changxing County, this study constructed a density system that reflects the block’s physical environment and socioeconomic characteristics. An optimal-parameters-based geographical detector was employed to investigate the effects and interactions of density factors on the carbon emission intensity of residential blocks (CIRB), carbon emission intensity of commercial blocks (CICB), and carbon emission intensity of public blocks (CIPB). The results indicate the following: (1) The impact of density factors on different types of CICL varied significantly. Physical environmental factors (PEFs) had greater explanatory power than socioeconomic factors (SEFs) across the CIRB, CICB, and CIPB, with the floor area ratio (FAR) being the most influential. The spatial morphology of blocks also influenced the relationship between density factors and the CICL. (2) The interactions between the FAR and building density (BD), the FAR and commercial outlet density (COD), and the FAR and population density (PD) had the strongest explanatory power for the CIRB, CICB, and CIPB, respectively, and all exhibited nonlinear enhancements. Some factors exhibited more significant effects only when interacting with others. (3) An association chain encompassing the interactions of multiple density factors was extracted for the CIRB, CICB, and CIPB, respectively, as the basis for conducting collaborative management and control in spatial planning. The research findings can provide decision support for urban planners to consider the comprehensive effects of density factors and promote the development of low-carbon urban spaces.

Seismic vulnerability, municipality of Toluca: a holistic analysis of the structural, social and economic aspects

This research integrates physical, social, and economic aspects to address seismic vulnerability in the municipality of Toluca, Mexico. The objective is to design and implement a procedure that estimates seismic vulnerability at the urban block scale. The developed method combines physical and socio-economic dimensions to assess seismic vulnerability. The physical dimension includes susceptibility to seismic resonance, as well as the age and type of constructions, while the socio-economic dimension is based on the marginalization index. Mapping covers 7,807 urban blocks where five levels of vulnerability are identified, with 46.6% exhibiting severe and very severe levels. The resulting zoning is a robust tool for risk reduction, particularly for justifying the implementation of actions aimed at reducing vulnerability.

Study on Mapping and Identifying Risk Areas for Multiple Particulate Matter Pollution at the Block Scale Based on Local Climate Zones

As China’s urbanization process accelerates, the issue of air pollution becomes increasingly prominent and urgently requires improvement, based on the fact that environmental conditions such as meteorology and topography are difficult to change. Therefore, relevant optimization studies from the perspective of architectural patterns are operable to mitigate pollution. This paper takes the Wenhua Road block in Shenyang, China, as the research object; obtains the concentration data of three kinds of particulate matter through fixed and mobile monitoring; and analyzes the spatial distribution characteristics of Local Climate Zones ( LCZ) and particulate matter in the block based on the ArcGIS platform, identifies high-risk areas, and excavates the influence of LCZ on the concentrations of three kinds of particulate matter. The results show that the spatial distribution characteristics of PM1, PM2.5, and PM10 under the same pollution level are relatively similar, while the spatial heterogeneity of the distribution of the same particulate matter under different pollution levels is higher. The time-weighted results show that the PM1 pollution level in the block ranges from 44 to 51 μg/m³, PM2.5 ranges from 75 to 86 μg/m³, and PM10 ranges from 87 to 99 μg/m³. The pollution hot spots throughout the year are located in the central, eastern and western parts of the study area. In terms of the relationship between the LCZ and particulate matter, with the increase in the particulate matter diameter, the correlation between the three kinds of particulate matter and LCZ are all enhanced. The built-up LCZ always has a larger average concentration of particulate matter than that of the natural LCZ, and building height and building density are the main factors causing the difference. In the optimal design of the risk area, the proportion of natural vegetation or water surface should be increased and the building height should be properly controlled and the building density should be reduced in the renewal of the urban building form. This study will largely improve the spatial refinement of the optimization of urban architectural patterns oriented to mitigate particulate matter pollution.

Identifying Street Environmental Factors That Attract Public Attention from the Jogger’s Perspective: A Multiscale Spatial Exploration

Improving street jogging environments can promote urban health and sustainability, especially within urban built-up areas. Public attention to the environment during jogging has not been sufficiently studied, and the recommended route data from the fitness app offers an opportunity for multiscale spatial exploration. Initially, by analyzing the recommendation reason text, the study identified 22 environmental factors and proposed the Environmental Factor Public Attention Intensity (EFPAI) for quantification, with subsequent comparisons to expert opinions. Further, by analyzing five types of data from the recommended routes, the relationships between EFPAI and jogging frequency, route shape, spatial distribution, and seasonal variations were uncovered. The study revealed: (1) discrepancies between expert opinions and public attention, with experts more likely to overlook factors such as slope, visual quality, width, and acoustic quality; (2) the public tends to notice factors like pedestrians, green spaces, waterfront spaces, landscapes, culture, sports facilities, and accessibility on routes with high jogging frequency; (3) EFPAI for traffic infrastructure, waterfront spaces, landscapes, residential areas, and campuses is associated with route shape; (4) EFPAI of certain environmental factors is influenced by urban geographical spatial factors, and substantial differences exist between different cities. Specific recommendations were provided from three different scales—site scale, street block scale, and urban scale—to guide the resolution of issues in planning and decision-making processes for urban renewal.

Understanding the role of urban features in land surface temperature at the block scale: A diurnal cycle perspective

The diverse urban features considerably influence land surface temperature (LST). Numerous studies have extensively investigated the impacts of 2D/3D urban features on LST. However, the diurnal impacts have not been comprehensively understood. Therefore, taking 1, 510 blocks within the 4th ring road of Beijing as samples, this study examined the influence of urban features (2D: low vegetation, water, and impervious surface; 3D: buildings and trees) on diurnal LST at the block scale based on ECOSTRESS LST using boosted regression tree (BRT) algorithm. The results showed that trees exhibit better cooling effects than low vegetation except at 3:09. The 3D features exhibited a greater impact on diurnal LST compared with 2D features, and it contributed strongly to daytime LST, which was 27.8 % on average higher than the 2D features. Building and tree densities had the greatest influence on daytime LST, while building height influenced nighttime LST the most. The impacts of key metrics on diurnal LST were nonlinear, and the relationship had diurnal variations. Taller buildings and trees were negatively correlated with LST during the daytime and transition time, but positively correlated with nighttime LST. The findings provide insights into landscape optimization strategies to improve block thermal comfort.

Residential segregation in two cities in Peru’s southern macro-region

Studies on residential segregation in Peru have privileged the study of the capital city, to the detriment of cities with other scales and contexts. This article analyzes the residential segregation levels and patterns in two Peruvian cities in the southern macro-region: Arequipa and Tacna. Based on data provided by the 2007 and 2017 censuses, synthetic and spatial segregation indicators were analyzed in both cities, taking as reference the educational level of the head of household and calculating the data on the block, census area, and district scales. The results show that inherited segregation patterns are maintained, while at the same time, the growing middle-class sectors are included in the more consolidated working-class settlements. In addition, processes that reinforce segregation were identified, such as the modification of the role of central areas, urban land production for the upper-class areas, and homogeneity of disadvantages in new areas of urban expansion, which are linked, particularly in the city of Arequipa, to the occupation of risk areas. The study suggests that these processes shape a low-scale urban segregation or fragmentation pattern in both cities, which coexists with inherited patterns.

An Optimized Instance Segmentation of Underlying Surface in Low-Altitude TIR Sensing Images for Enhancing the Calculation of LSTs.

The calculation of land surface temperatures (LSTs) via low-altitude thermal infrared remote (TIR) sensing images at a block scale is gaining attention. However, the accurate calculation of LSTs requires a precise determination of the range of various underlying surfaces in the TIR images, and existing approaches face challenges in effectively segmenting the underlying surfaces in the TIR images. To address this challenge, this study proposes a deep learning (DL) methodology to complete the instance segmentation and quantification of underlying surfaces through the low-altitude TIR image dataset. Mask region-based convolutional neural networks were utilized for pixel-level classification and segmentation with an image dataset of 1350 annotated TIR images of an urban rail transit hub with a complex distribution of underlying surfaces. Subsequently, the hyper-parameters and architecture were optimized for the precise classification of the underlying surfaces. The algorithms were validated using 150 new TIR images, and four evaluation indictors demonstrated that the optimized algorithm outperformed the other algorithms. High-quality segmented masks of the underlying surfaces were generated, and the area of each instance was obtained by counting the true-positive pixels with values of 1. This research promotes the accurate calculation of LSTs based on the low-altitude TIR sensing images.