Urban street views shape everyday urban experience, yet their assessment still relies largely on researcher-defined indicators and structured elicitation, with limited use of naturally occurring public responses. This study develops an interpretable framework that transforms social-media image–comment interactions into eight-dimensional collective emotional appraisals of urban scenes. Under approved access, 1078 Facebook and Instagram cityscape posts and 20,546 comments were retrieved through the SOMAR Virtual Data Enclave. Comment-derived Plutchik labels were assessed through human validation and robustness tests, then used as weak supervision for R-ECoT, which jointly predicts emotion intensities and generates emotion-specific grounding maps from images. The trained CLIP-based model was applied to 610,017 ZENRIN street-view images in Setagaya Ward, Tokyo, and predictions were aggregated to 10 m road segments. Comment-derived labels agreed more closely with an independent post-level human reference than the strongest image-only estimate (Pearson 0.818 versus 0.751). CLIP-R-ECoT achieved the best performance in hierarchical benchmarks, with a KL divergence of 0.329, an MSE of 0.0106, and a balanced accuracy of 0.757. Its grounding maps showed greater random-corrected masking faithfulness than Grad-CAM (0.083 versus 0.049), higher perturbation stability, and lower spatial fragmentation. Street-level mapping revealed differentiated emotional patterns, while emotion-specific high-response regions in the images were associated with distinct semantic, color-atmospheric, and depth-structural attributes. By converting dispersed public reactions into spatially continuous and interpretable evidence, the framework supports fine-grained streetscape screening, helps identify locations warranting closer inspection, and directs design attention toward the visible conditions associated with different public responses.
Urbanization poses complex challenges and opportunities for biodiversity conservation, yet most studies rely on single taxa or a limited set of environmental dimensions. We calculated multispecies-diversity and abundance for 49 extensively managed dry grassland sites across an urban-to-rural gradient in Berlin, Germany, encompassing 13 taxonomic groups from primary producers to a top predator and 158 Red-listed species. We evaluated the relative influence of urban structure (impervious surface cover, patch size, habitat connectivity), environmental factors (air temperature, non-native plant cover), socioeconomic context (composite social index), and historical landscape configuration (historical connectivity) on total multispecies richness and abundance, as well as on Red-listed species richness. Historical connectivity was the strongest predictor for Red-listed species richness, indicating that many urban populations persist as relicts and may be subject to extinction debt. Impervious surface cover showed a nonlinear effect on total diversity, with substantial declines only beyond 40% coverage, suggesting conservation opportunities up to moderate development. Socioeconomic status positively influenced all multispecies measures (indices), consistent with the luxury effect, whereas 2D and 3D connectivity exhibited neutral and negative association with total multispecies richness and abundance. Patch size was important for Red-listed species but not for total multispecies diversity, while local temperature and non-native plant cover were not significantly related to any diversity index. Overall, biodiversity responses to urbanization were context-dependent and nonlinear, and often differed between total and Red-listed multispecies diversity. Consequently, urban conservation planning requires multidimensional approaches that integrate historical land-use legacies, socioeconomic conditions, and historical connectivity to support both common and endangered species in cities.
Anthropogenic processes modify the environment, influencing species distribution. In urban settings, wildlife persistence depends on the interaction between landscape patterns, local habitat characteristics, and species-specific traits. Despite habitat fragmentation, many wildlife species manage to adapt and thrive within the urban matrix. An example of this is the coypu (Myocastor coypus), which has increased its presence in urban habitats due to its high ecological plasticity. Although native to Argentina, it is considered one of the most harmful invasive mammals worldwide. Its expansion and population density can impact vegetation and create conflicts with humans. In the conurbano bonaerense, in central Argentina, coypus are frequently associated with gated communities, where they have become increasingly common. This study analyzed the influence of habitat characteristics measured at the microhabitat, macrohabitat, and landscape scales on coypu occurrence, abundance, and use intensity in urban environments of the conurbano bonaerense. Sampling was conducted at 31 sites between 2021 and 2023, covering 7,216.7 km2. Signs of activity were recorded in 397 transects along permanent water bodies, and habitat variables were quantified through field surveys, photointerpretation, and remote sensing using scale-specific spatial extents. The results showed that coypu occurrence, abundance, and use intensity were associated with anthropogenic disturbance, aquatic habitat configuration, and the availability of short herbaceous vegetation. Landscape-scale variables explained most of the variation in the three response variables, although habitat characteristics measured at macro- and microhabitat scales also contributed to explaining species responses. These findings identify habitat characteristics associated with spatial distribution of coypu that can support future conservation initiatives where the species is of conservation interest and management strategies where it generates conflicts.
