Ecological Informatics最新文献

{"title":"Urban buzz or urban bust? Beekeeping challenges, suitability, and survival insights in Montreal, Canada","authors":"Navid Mahdizadeh Gharakhanlou ,&nbsp;Julien Vadnais ,&nbsp;Liliana Perez ,&nbsp;Nico Coallier","doi":"10.1016/j.ecoinf.2025.103296","DOIUrl":"10.1016/j.ecoinf.2025.103296","url":null,"abstract":"<div><div>The rising interest in urban beekeeping underscores the need to investigate whether urban habitats are sustainable for managed honeybee populations. This study, conducted on the island of Montreal, Canada, aimed to i) assess honeybee colony survival within an urban environment, ii) determine the primary drivers affecting honeybee colony survival, and iii) explore the potential of urban areas to support beekeeping activities. This study applied two distinct survival analysis methods, namely random survival forests (RSF) and time-dependent Cox models, incorporating both static and dynamic geospatial variables including normalized difference vegetation index (NDVI), digital elevation model (DEM), percentages of urban areas and water, floral source diversity, road density, proximity to roads, surrounding hive count, ozone (O₃) concentration, fine particulate matter (PM2.5) levels, maximum temperature, and precipitation. To reflect typical honeybee foraging ranges, two buffer distances (1 km and 3 km) were analyzed, and model performance was assessed using the concordance index (C-index) and integrated Brier score (IBS). For the 1 km buffer, the RSF model achieved a C-index of 0.90 (training) and 0.82 (test) with IBS scores of 0.06 and 0.10, outperforming the Cox model, which showed a C-index of 0.56 (both training and test) and IBS values of 0.19 and 0.18. At 3 km, RSF further improved (C-index: 0.93 (training) and 0.84 (test); IBS: 0.05 (training) and 0.08 (test)), while the Cox model remained lower (C-index: 0.58 (training) and 0.60 (test); IBS: 0.19 (training) and 0.18 (test)). These results confirm RSF's superior performance and suggest that broader spatial context may enhance prediction accuracy. Additionally, our findings revealed that the surrounding hive count was the strongest predictor of beehive survival in both buffer scenarios. At 1 km, road proximity and elevation (i.e., DEM) followed in importance, while at 3 km, elevation and vegetation density (i.e., NDVI) were more influential. A primary outcome of this study was the generation of spatially explicit beehive habitat suitability maps for Montreal. Averaged over 2017–2021, these maps showed that large portions of the island are favorable for urban beekeeping, with 30.94 % of land classified as highly suitable and 38.28 % as moderately suitable, demonstrating strong potential for sustainable apiculture in urban environments. This study contributes to providing insights into urban planning and managed honeybee conservation through suitability mapping and predictor analysis.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103296"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A framework for predicting zoonotic hosts using pseudo-absences: the case of Echinococcus multilocularis","authors":"Andrea Simoncini ,&nbsp;Dimitri Giunchi ,&nbsp;Marta Marcucci ,&nbsp;Alessandro Massolo","doi":"10.1016/j.ecoinf.2025.103295","DOIUrl":"10.1016/j.ecoinf.2025.103295","url":null,"abstract":"<div><div>Identifying the host range of zoonotic parasites is challenging due to limited data and sampling biases. In particular, while more information exists for susceptible hosts, data on resistant species is extremely scant. <em>Echinococcus multilocularis</em> (Leuckart, 1863) (Cestoda: Taeniidae) is the causative agent of alveolar echinococcosis, one of the most significant food-borne zoonoses worldwide. Using data on susceptibility and competence of Holarctic cricetid and murid rodents, key intermediate hosts for <em>E. multilocularis</em>, we developed models to predict the likelihood of infection for any rodent species in the Holarctic. These models incorporated morphological and ecological characteristics and employed two approaches: Generalized Linear Models (GLM) and Presence-Unlabeled Learning (PU-L), a machine learning technique. To train the models, we defined pseudo-absences based on the bias in research effort. We compared the two algorithms and selected GLM as the most effective, using it to map potentially susceptible rodent species across phylogeny and geographic space. Predictions identified several potentially unreported hosts, suggesting that the current understanding of <em>E. multilocularis</em> host distribution may underestimate the true risk. The predicted richness of intermediate hosts peaked in Central-Eastern Europe, Western North America and Central Asia, while the ratio of predicted hosts to total rodent richness was highest in the northern latitudes and the Tibetan Plateau. The average temperature in the geographic range and range size emerged as the strongest predictors of host susceptibility. The workflow demonstrates promise for application to other host-parasite systems with unknown host ranges.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103295"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Composite likelihood inference for analysis of individual animal identification data","authors":"Xueli Xu ,&nbsp;Xiaoyue Zhang ,&nbsp;Hal Whitehead ,&nbsp;Dehan Kong ,&nbsp;Ximing Xu","doi":"10.1016/j.ecoinf.2025.103298","DOIUrl":"10.1016/j.ecoinf.2025.103298","url":null,"abstract":"<div><div>Individual identification data collection is a common practice in animal behaviour, movement ecology, and conservation biology. While likelihood analysis is widely employed for ecological insights, the complexity of individual identification data, characterized by numerous interdependent individuals and identification times, makes direct likelihood calculation challenging. To address this, we introduce a composite likelihood inference framework. We establish the consistency and asymptotic normality of maximum composite likelihood estimators within this framework. Furthermore, we develop a composite likelihood-based information criterion for model selection, capable of handling complex individual identification data. Our approach is demonstrated through extensive simulations and applied to the northern bottlenose whale population in the Gully, Nova Scotia. This study provides a statistically rigorous framework for individual animal identification models, with potential applications extending beyond whale populations.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103298"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing Gonipterus defoliation levels using multispectral unmanned aerial vehicle (UAV) data in Eucalyptus plantations","authors":"Phumlani Nzuza ,&nbsp;Michelle L. Schröder ,&nbsp;Rene J. Heim ,&nbsp;Louis Daniels ,&nbsp;Bernard Slippers ,&nbsp;Brett P. Hurley ,&nbsp;IIaria Germishuizen ,&nbsp;Benice Sivparsad ,&nbsp;Jolanda Roux ,&nbsp;Wouter. H Maes","doi":"10.1016/j.ecoinf.2025.103301","DOIUrl":"10.1016/j.ecoinf.2025.103301","url":null,"abstract":"<div><div>Invasive insect pest <em>Gonipterus</em> sp. n. 2 (Coleoptera: Curculionidae) threatens <em>Eucalyptus</em> species, causing defoliation and yield loss through adult and larval feeding. Early detection is important for early intervention to prevent pest outbreaks. As conventional insect pest monitoring methods are time-consuming and spatially restrictive, this study assessed the potential of UAV monitoring. Multispectral imagery was obtained with Unmanned Aerial Vehicles (UAVs) across six different stands of young <em>Eucalyptus dunnii</em> with varying levels of <em>Gonipterus</em> sp. n. 2 infestations. Some stands were revisited, a total of 9 datasets were covered. Reference damage levels were obtained through visual assessments of (<em>n</em> = 89–100) trees at each site. Across sites, a decrease in canopy reflectance in both the visual and the near-infrared domains with increasing damage levels was consistently observed. Several vegetation indices showed consistent patterns, but none showed site independence. XGBoost, Support Vector Machine and Random Forest (RF) were used to predict damage levels using five input spectral data types. XGBoost performed best, closely followed by RF. Both models consistently selected very similar features. The best-performing models included reflectance, vegetation indices and grey-level co-occurrence matrix data. When data from 10 different wavelengths were used, the highest classification accuracy was 92 % across all sites in classifying defoliation levels. With a classical 5-band multispectral camera, accuracy was 88 %, but distinguishing medium damage from low remained challenging. However, the method was less reliable when trained and validated on separate fields. This study highlights the potential of multi-site datasets in increasing the model's generalization, using UAV based multispectral imagery to assess <em>Gonipterus</em> sp. n. 2 damage and demonstrating reliable upscaling from individual tree assessments to stand scale. However, it also recognises the difficulty of generating a robust model that performs well on untrained sites.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103301"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Few-shot transfer learning enables robust acoustic monitoring of wildlife communities at the landscape scale","authors":"Giordano Jacuzzi,&nbsp;Julian D. Olden","doi":"10.1016/j.ecoinf.2025.103294","DOIUrl":"10.1016/j.ecoinf.2025.103294","url":null,"abstract":"<div><div>Pre-trained classifiers for bioacoustic species detection have emerged as accessible tools for conservation and automated biodiversity monitoring at scale. Despite their wide use, these models are trained primarily on high-quality, weakly labeled species recordings from disparate regions that can fail to account for variation in passive ambient soundscape data due to poor signal-to-noise ratio and the presence of novel sounds such as abiotic noise and concurrent vocalizations. This domain shift may limit a pre-trained model's reliability and preclude its use in applied acoustic monitoring. Although relatively underexplored in bioacoustic monitoring, transfer learning may help overcome the limitations of existing pre-trained classifiers by enhancing predictive performance while avoiding the time, resources, and expertise required to develop entirely new models. We demonstrate the use of few-shot transfer learning as a strategy to efficiently adapt a pre-trained BirdNET source model to a new target domain with minimal local training data. We present an open-source workflow with guidelines to evaluate performance with ecologically meaningful metrics and train a target model with improved or missing classes for biotic and abiotic signals of interest. This process is demonstrated with an applied case study of community level acoustic monitoring across a managed temperate rainforest landscape in western Washington, United States.</div><div>The target model achieved a mean precision-recall AUC of 0.94 at the audio segment level and a mean accuracy of 92 % at the site use level across trained avian species classes, an increase of 0.15 and 13 % over the pre-trained source model, respectively. These improvements increased the probability of individual species detection and produced more accurate estimates of local species richness. Several species of high conservation and management priority that could not be reliably detected by the source model achieved high performance. Superior performance was achieved with an average of only 8 local training examples per species class. Training novel classes for other signals of interest (e.g., anurans, insects, aircraft, logging, rain) reduced confusion rates and mitigated the impact of the local environment on performance. Few-shot transfer learning leverages the learned knowledge of a pre-trained classifier to enable robust monitoring at the community level across the landscape and offers an approach that can be readily applied to other environments and taxa.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103294"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating isotopic niche metrics and gut microbiota assembly reveals coexistence mechanisms in subtropical riverine fish","authors":"Yaqiu Liu ,&nbsp;Xinhui Li ,&nbsp;Konstantinos Ar. Kormas ,&nbsp;Chunni Kou ,&nbsp;Huifeng Li ,&nbsp;Yuefei Li ,&nbsp;Jie Li","doi":"10.1016/j.ecoinf.2025.103305","DOIUrl":"10.1016/j.ecoinf.2025.103305","url":null,"abstract":"<div><div>Understanding interspecific niche overlap is fundamental for evaluating resource partitioning and competitive interactions among sympatric species. Microbial symbiont facilitates rapid adaptation to novel ecological niches, substantially augmenting host evolutionary fitness and ecological success. Nevertheless, the mechanisms through which host-microbe symbiosis mediates fish coexistence patterns in subtropical riverine ecosystems remain incompletely understood. This investigation employed stable carbon (δ¹³C) and nitrogen (δ¹⁵N) isotope analysis to quantify trophic niche width and overlap among seven sympatric fish species in the Yuanjiang River ecosystem, complemented by high-throughput sequencing of gut microbial communities. Our results showed that host phylogenetic specificity primarily reflected the similarity in deterministic selection processes (host filtering) mediated by host phylogenetic conservatism. Comprehensive β-diversity analyses consistently confirmed phylosymbiosis patterns across multiple community metrics. Moreover, stochastic processes, including dispersal limitation and drift, also played an important role in shaping the exact composition of gut microbial communities within specific host individuals. Furthermore, our findings indicated fish host trophic niche differentiation emerges as an essential adaptive mechanism facilitating interspecific coexistence by minimizing resource competition. Crucially, we identified the similarity of the intestinal microbial community structure is closely related to the degree of overlap of its nutritional ecological niche, indicating functional convergence between host trophic niches and their symbiotic microbiomes.These microbial adaptations facilitate nutritional optimization from varied trophic sources, mediate interspecific resource partitioning, and expand ecological opportunities within the fish community. Our integrative analysis identifies host-microbiome symbiosis as an evolutionary innovation. Through this mechanism, niche expansion and competitive coexistence are enhanced in subtropical river ecosystems.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103305"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting stress parameters in dromedary camels using computer vision","authors":"Hiba Moideen ,&nbsp;Manar Abu Talib ,&nbsp;Nabil Mansour ,&nbsp;Shaher Bano Mirza ,&nbsp;Ali Bou Nassif ,&nbsp;Simon Zerisenay Ghebremeskel ,&nbsp;Fouad Lamghari ,&nbsp;Yaman Afadar ,&nbsp;Takua Mokhamed","doi":"10.1016/j.ecoinf.2025.103292","DOIUrl":"10.1016/j.ecoinf.2025.103292","url":null,"abstract":"<div><div>Dromedary camels exhibit behavioral responses influenced by both physiological conditions and environmental factors. Poor health, physical or emotional, can manifest as behavioral abnormalities. This study aims to build a video-based stress detection model by analyzing camel behavior under different conditions. Camels from Marmoom Farm, UAE, were observed over eight days: six days included interventions such as blood collection and/or intensive training, and two days followed their typical routine. Video footage was captured from three cameras positioned around the enclosures and pens. Using the YOLOv8 architecture, we developed a model to classify normal behaviors - “standing”, “sitting”, “sleeping” and stress-related behaviors - “distressed sitting”, “moving around uncontrollably”, “pulling on rope”. The model obtained a precision of 0.971, recall of 0.959, mAP50 of 0.985, and mAP50–95 of 0.924. Four camels were closely monitored to analyze correlations between behavioral stress indicators and activities such as blood sampling, race training, and environmental conditions. Results indicate that while high-intensity training often induces stress, individual endurance levels and external factors like weather also significantly influence stress responses. This study presents a novel, automated method for early stress detection in camels, contributing to improved animal welfare and farm management practices.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103292"},"PeriodicalIF":5.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating generative AI and climate modeling for urban heat island mitigation","authors":"Mo Wang ,&nbsp;Ziheng Xiong ,&nbsp;Shiqi Zhou ,&nbsp;Jiayu Zhao ,&nbsp;Chuanhao Sun ,&nbsp;Yuankai Wang ,&nbsp;Lie Wang ,&nbsp;Soon Keat Tan","doi":"10.1016/j.ecoinf.2025.103284","DOIUrl":"10.1016/j.ecoinf.2025.103284","url":null,"abstract":"<div><div>Conventional urban heat island (UHI) studies often rely on static urban morphology inputs and oversimplified design variables, limiting their ability to support dynamic, climate-responsive urban planning. To address this gap, this study proposes a novel framework that integrates a hybrid generative adversarial network (GAN) with the Urban Weather Generator (UWG) for high-fidelity 3D urban form generation and microclimate simulation. The proposed GAN architecture combines the geometric accuracy of Pix2pix with the style refinement capability of CycleGAN, achieving improved morphologicalrealism (SSIM = 0.754, R² = 0.834 against ground-truth data) and resolving key distortions that impede microclimate analysis. Applied Shenzhen Bay Super Headquarters as a case study, ten urban development plans were generated and evaluated for their thermal performance. Results revealed that plans exceeding a facade-to-site ratio of 5.0 and footprint density of 0.30 showed intensified nocturnal heat retention, with Plan V exhibiting a + 2.3 °C nighttime temperature increase. In contrast, Plan I, with lower morphological density, achieved a 1.8 °C reduction, demonstrating superior heat dissipation. These insights provide actionable guidelines for climate-responsive urban planning, advocating for lower-density layouts with optimized facade exposure and increased vegetative cover. The proposed framework offers a robust tool for planners and policymakers to assess and design urban forms that enhance climate resilience while reducing UHI intensity.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103284"},"PeriodicalIF":5.8,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tracking freshwater depletion in Northern Australia: A multi-satellite approach","authors":"Christopher E. Ndehedehe ,&nbsp;Ikechukwu Kalu ,&nbsp;Vagner G. Ferreira ,&nbsp;Alex O. Onojeghuo ,&nbsp;Oluwafemi E. Adeyeri ,&nbsp;Mohammad J. Tourian ,&nbsp;Matthew Currell ,&nbsp;Sue Jackson","doi":"10.1016/j.ecoinf.2025.103248","DOIUrl":"10.1016/j.ecoinf.2025.103248","url":null,"abstract":"<div><div>Accurate freshwater accounting is critical for effective local water planning and governance, but this is limited by availability of in-situ data. In Australia’s Northern Territory, significant climatic and hydrologic knowledge gaps have brought into question the sustainability of groundwater regulation amidst expansion of agricultural and mining activities. We demonstrate how multi-satellite remote sensing data can enhance understanding of human and drought impacts on changes in freshwater storage to underpin management strategies. By integrating historical Landsat data and in-situ groundwater levels, river discharge, rainfall, and climate data (1986–2022) with satellite gravity observations and output from a hydrological model (2002–2022), we develop a framework to document changes in surface and sub-surface water storage systems over the Cambrian Limestone Aquifer (CLA). We assess the response of these systems to hydrological drought, quantify water deficits and assess how much water may potentially be missing due to drought or extraction. Our satellite analyses show that changes in freshwater storage (or terrestrial water storage-TWS) in the CLA started to significantly decline after 2014. The CLA continued to experience variations in TWS deficits in the last decade (2014–2023) with average time to recovery increasing considerably from less than 5 months in 2014 to more than 15 months in 2021 when water storage deficits reached <span><math><mrow><mo>∼</mo><mn>150</mn><mspace></mspace><msup><mrow><mi>km</mi></mrow><mrow><mn>3</mn></mrow></msup></mrow></math></span>. The CLA appears to be getting drier, evidenced by recent (2011–2022) and significant depletion in groundwater storage (−3.88 ± 0.29 km³/yr) and TWS declines (ranging from 6.28 ± 0.75 km³/yr to 8.20 ± 0.75 km³/yr), coinciding with large losses in aerial extent of open surface water features. While acknowledging that drought-affected areas and occurrences during the 2011–2022 period were significantly less than those experienced between 2003 and 2010, it is noteworthy that the recent drying coincided with the commencement of licensed groundwater extraction in the CLA. Building on these findings, we highlight the unique capabilities and benefits of combining satellite gravity and optical data to enhance our understanding of hydrological processes, while also advancing water governance and management responses to droughts and pressures from water extraction.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103248"},"PeriodicalIF":5.8,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatio-temporal heterogeneity and topic evolution trends of public carbon neutrality attention in China","authors":"Lifang Fu ,&nbsp;Changjin Ma","doi":"10.1016/j.ecoinf.2025.103274","DOIUrl":"10.1016/j.ecoinf.2025.103274","url":null,"abstract":"<div><div>This study examines the spatiotemporal evolution and regional disparities in public attention to carbon neutrality under the ”dual carbo” goals to inform more effective policy design. Departing from traditional single-dimensional approaches, it introduces an interdisciplinary analytical framework – spatiotemporal measurement, sentiment analysis, and topic evolution – to capture dynamic shifts in public discourse on carbon neutrality in China, based on 119,000 Sina Weibo posts (2018–2023). The study makes the following key contributions: (1) It applies Dagum Gini coefficient decomposition and kernel density estimation to identify regional attention patterns, revealing higher attention in central regions, lower levels in the west, and evident ”multi-polarization” within regions; (2) It develops a CNN-BiLSTM-Attention model for sentiment classification, demonstrating that the emotional polarity of topics such as ”low-carbon lifestyle” closely aligns with policy promulgation frequency; (3) It employs the VSTC clustering model to examine topic evolution, identifying four major thematic trajectories: individual environmental behavior, green economy, global governance, and sustainable development. These reflect a progression from micro-level personal actions to macro-level policies and industrial practices. Overall, this study provides a solid quantitative basis for optimizing carbon neutrality policies in China.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103274"},"PeriodicalIF":5.8,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}