ABSTRACT Passive Acoustic Monitoring (PAM) offers a powerful approach for detecting and assessing the presence of invasive species, thereby supporting the conservation of native ecosystems. In this study, we developed a species-specific classification model using convolutional neural networks (CNNs) to analyse the nocturnal calling activity patterns of Pelophylax nigromaculatus and Dryophytes leopardus in rice paddies, a microhabitat where interactions between translocated and native species are of ecological concern. Despite environmental noise from bird calls and wind, the mel-spectrogram-based model classified anuran vocalisations with high accuracy (88.45%). Misclassifications at dawn were mitigated by limiting the ecological analysis to specific nocturnal periods. The results revealed clearly distinct peak times of nocturnal calling activity between the two species at the study site. These findings demonstrate the usefulness of deep learning for describing fine-scale activity patterns in field-recorded amphibian soundscapes. This study provides methodological insights into the acoustic monitoring of domestically translocated and native species and highlights the potential of bioacoustics approaches for ecological assessment in paddy environments. Future research should focus on refining species classification models and integrating sound-source separation for more accurate species-specific assessments of calling activity patterns.

Artificial intelligence for marine oil spill management: Recent advances and future directions.

Forests of Northeast India, a global biodiversity hotspot, are increasingly threatened by climate change and human disturbances, placing narrowly distributed plant species at risk of extinction. The genus Pyrenaria (Theaceae), which includes several endemic and poorly studied species, lacks comprehensive ecological and distributional assessments necessary for evidence-based conservation planning. This study integrates extensive field surveys and MaxEnt modeling to assess the diversity, population structure, phenology, and habitat suitability of six Pyrenaria taxa across five states in Northeast India. A total of 40 occurrence points and 167 individuals (47 seedlings, 21 saplings, 99 adults) were recorded, revealing poor regeneration linked to disturbances like logging, agricultural expansion, mining and fire. Habitat suitability was modeled using the MaxEnt algorithm with eleven environmental predictors derived from WorldClim, including elevation after removing correlated variables (r > 0.8). The model showed high predictive accuracy, with Area Under the Curve (AUC) values ranging from 0.850 to 0.999 and True Skill Statistic (TSS) values from 0.50 to 0.998. Habitat suitability analysis revealed large potential distributions for most species, except for the endemic P. cherrapunjeana, which showed a highly restricted suitable habitat of only 1,633km². Mean diurnal temperature range, precipitation, and elevation emerged as key factors influencing species distribution. By combining field-based ecological data with spatial modeling, this study identifies priority conservation areas and potential reintroduction sites, providing a framework for safeguarding Pyrenaria under ongoing environmental change.

ABSTRACT High-resolution remote-sensing image change detection has become a crucial technical approach in urban ecological monitoring and disaster assessment. However, its practical application still faces several challenges: object-scale variation, blurred boundaries in change regions, the difficulty of capturing subtle changes, and temporal discrepancies across large time spans. These factors increase the complexity of change detection, making it difficult for existing models to achieve optimal feature learning and detection accuracy in real-world scenarios. To address these issues, we propose a GCN-Mamba-based model for high-resolution remote sensing change detection. A local and global feature aggregation (LGFA) module is designed to address the omissions and representational inconsistencies caused by object-scale variations in high-resolution imagery, fusing local edge details with global semantic structures extracted by Mamba to preserve multi-scale features. Then, a sequential enhancement module (SEM) is introduced, which improves temporal-spatial continuity and enhances the detection of subtle changes and boundary integrity. A dual-perspective adaptive gated multi-feature fusion (DPAGMF) module is proposed to reduce interference from long-term temporal discrepancies. This module utilizes the acquired multi-scale boundary-enhanced features to capture synergistic relationships via dual-perspective modeling, improving robustness under complex spatiotemporal conditions. The proposed method achieves F1 gains of 1.20% and 0.53% on WHU-CD and LEVIR-CD, along with a 0.27% increase on WCD, demonstrating strong generalization capability. Overall, the proposed method demonstrates excellent performance in short-term change detection scenarios, but faces challenges in long-term cases influenced by significant environmental differences. Future work will focus on improving the collaborative modeling of bi-temporal features across extended time spans.

Sedentary behavior is a recognized and modifiable risk factor for cognitive decline and dementia across neurodegenerative conditions. This study used a smartwatch-based telemonitoring procedure combined with ecological cognitive assessment to examine whether step counts can capture sedentary behavior and its association with cognitive functioning in patients with mild cognitive impairment (ADMCI) and dementia (ADD) due to Alzheimer's disease. Then, 19 ADD, 28 ADMCI, and 23 cognitively unimpaired older adults (Nold) were consecutively recruited. Participants underwent clinical assessment, resting-state electroencephalography (rsEEG), and neuropsychological testing. They were then monitored at home for approximately one week using Samsung Galaxy Watch 4-6 devices recording step counts (total, purposeful, and incidental) and activity intensity (peak 30-min cadence), together with the unsupervised SmartMe&You-TELEMAIA serious videogame battery administered on a commercial tablet for cognitive assessment. The ADD group showed reduced step counts and lower peak cadence than both ADMCI and Nold participants, whereas rsEEG markers and cognitive measures discriminated the three groups with a graded pattern. Within the AD sample, smartwatch-derived activity metrics were associated with cognitive functioning as assessed by conventional neuropsychological testing and ecological serious videogame performance, but showed limited associations with rsEEG rhythms. EEG delta and alpha rhythms were also more abnormal in the ADD group than in the ADMCI group. Home-based daytime activity monitoring with commercial smartwatches indicated that step volume and intensity are associated with cognitive status in patients with ADMCI and ADD. These findings suggest that smartwatch-derived activity metrics may provide feasible and cost-effective markers of everyday functioning in Alzheimer's disease.

The terrestrial molluscan fauna of the Caatinga Dominion, a seasonally dry tropical region in north-eastern Brazil, remains one of the least-documented components of its biota, thereby limiting its inclusion in ecological, biogeographical and conservation assessments. Here, we present a diagnosis of Caatinga terrestrial molluscs by addressing three questions: how much diversity is currently known, how strongly available records are spatially biased, and how sensitive species visibility is to minimum-occurrence thresholds commonly applied in spatial analyses. We compiled 944 records representing 155 species, 62 genera and 25 families. Stylommatophora accounted for 141 species (91%), highlighting the great taxonomic concentration of the known fauna. Despite this apparent richness, records were sparse and unevenly distributed.Only 221 of 8,761 grid cells (2.5%) contained records, whereas 8,443 cells (97.4%) lay within the expected occupancy area but lacked any record. Mean sampling completeness per cell, measured as the ratio between observed and expected richness, was 0.003, and observed-expected overlap was low (Jaccard = 0.0255). Species retained under increasing occurrence thresholds declined from 88 at t = 3 to one at t = 38, revealing pronounced taxonomic invisibility. These patterns may directly affect conservation planning and the reliability of spatial analyses that depend on minimum occurrence thresholds.

The exacerbation of global climate change has led to the continuous deterioration of the urban ecological environment. Scientifically planning blue-green spaces can mitigate ecological crises and promote sustainable urban development. There exists a close relationship between the ecological benefits of blue-green spaces and their spatial characteristics, and synergistically enhancing the ecological service efficiency of blue-green spaces through these two aspects is an urgent research topic. This study integrates four ecological benefit objectives-carbon sink, cooling, stormwater resilience, and biodiversity-and applies a multi-objective optimization framework based on grid-based spatial decision units to optimize blue-green space configurations. By establishing a multi-ecological benefit evaluation framework, this study combines ecological benefit assessment models with the NSGA-II multi-objective optimization algorithm and the entropy weight method for weight allocation. Ultimately, an optimal scenario and four preference-oriented scenarios for blue-green space layouts are derived. A case study in Nanjing, China, demonstrates the applicability of the integrated optimization framework in generating urban blue-green spatial layouts that balance multiple ecological benefit objectives. The results indicate that carbon sink and cooling show a positive synergy, while biodiversity and stormwater resilience exhibit trade-off tendencies, and the comprehensive scenario achieves a relatively balanced performance across objectives. The spatial layout characteristics of blue-green spaces vary distinctively across different ecological benefit objectives, with the multi-objective comprehensive optimal under the given proxies, constraints and algorithm settings demonstrating relative balance. The proposed multi-objective optimization methodology for blue-green spatial configuration provides scientifically quantifiable decision-making support for urban blue-green space planning.

Background Environmental DNA (eDNA) has transformed biodiversity monitoring, but its application for long-term ecological assessment remains limited by uncertainty in the temporal stability and consistency of eDNA signals, as well as by specialized workflows that limit accessibility for community-led programs. Expanding participation in biomonitoring requires approaches that are both logistically feasible and scientifically robust. Here, we evaluated eDNA tools for coral reef monitoring in Hawai'i by comparing (1) coral-specific genetic markers for tracking benthic community dynamics through time, and (2) passive eDNA samplers (PEDS) as a low-effort alternative to active filtration. This research was conducted with local stewardship organizations on O'ahu, Hawai'i, positioning eDNA as a complementary tool to place-based ecological knowledge that can inform conservation strategies and enhance ecological monitoring. Results Across five broad taxonomic markers, we detected diverse reef communities spanning 17 phyla, with consistent regional differences in community composition, including clear differentiation in algal assemblages. Passive samplers recovered comparable taxonomic richness to active filtration when sampling effort was standardized, but showed greater variability among replicates, whereas active methods more consistently detected rare and transient taxa. Despite this, passive samplers captured similar broad-scale community patterns with reduced logistical effort. For coral monitoring, all three markers (12S, 16S, ITS2) showed strong correlations with visual cover and detected more genera than visual surveys. Among these, 16S showed the strongest and most consistent performance across temporal replicates, while ITS2 showed greater temporal variability. Conclusions Accessible eDNA approaches can generate ecologically meaningful data for reef monitoring when matched to specific objectives. Passive samplers provide a scalable, low-barrier option for widespread community biomonitoring, while active filtration remains important for detecting rare taxa. A multimarker approach enabled detection of native, endemic, and nuisance taxa, offering an ecosystem-level perspective for management. Given the relatively slow pace of change in coral assemblages, periodic eDNA surveys may provide a useful and practical longer-term complement to rapid visual assessments of coral cover. Integrating these tools with local stewardship efforts can expand participation in eDNA biomonitoring while supporting conservation in urbanized, culturally significant reef systems.

Accurate mapping of bamboo resources is important for ecological assessment, forest management and regional resource planning, particularly in landscapes where bamboo occurs with other vegetation types. This study presents a hybrid learning framework for bamboo mapping using Sentinel-2 surface reflectance imagery acquired from January to December 2024 for Karbi Anglong and Dima Hasao districts of Assam, India. The proposed approach integrates unsupervised K-means clustering with supervised Random Forest classification to improve the discrimination of bamboo-related land-cover classes. Spectral bands B2, B3, B4 and B8, together with the Normalised Difference Vegetation Index, were used as input features. K-means clustering was first applied to identify spectrally homogeneous regions and to support the refinement of bamboo training samples. The refined training dataset was then used to classify six land-cover classes: water, land, forest, mixed vegetation, pure bamboo and bamboo-dominated areas. A total of 1,138 training samples was used, and the dataset was divided using a 70:30 train-test split. The proposed Hybrid Random Forest model achieved an overall accuracy of 95.3%, a kappa coefficient of 0.94 and a bamboo F1-score of 0.95. The results indicated improved classification performance compared with the standalone Random Forest and Support Vector Machine models evaluated in the study. Area-wise assessment showed substantial bamboo presence in both study districts, with pure bamboo and bamboo-dominated classes forming major components of the classified landscape. The findings suggest that cluster-assisted training sample refinement can improve bamboo classification in heterogeneous forest landscapes using medium-resolution multispectral satellite data, provided that the training samples and outputs are carefully validated.

Selection-driven shifts in airborne bacterial communities and potentially pathogenic genera across environmental and PM2.5 gradients in urban Beijing.

ABSTRACTRationaleClosely related whale species can appear similar yet occupy distinct ecological niches. Sato's beaked whale (Berardius minimus) was only recently recognized as a separate species and was previously grouped with Baird's beaked whale (Berardius bairdii), limiting our understanding of their ecological differences. Clarifying their trophic ecology is essential for accurate species‐specific conservation and management.MethodsSkin biopsy and necropsy samples of B. bairdii and B. minimus were collected in the western North Pacific in 2017–2025. Carbon (δ13C) and nitrogen (δ15N) stable isotope ratios were measured from three separately analyzed epidermal layers of skin samples using isotope ratio mass spectrometry.ResultsB. bairdii exhibited significantly higher δ13C values than B. minimus, whereas δ15N values were broadly similar, indicating comparable trophic positions but distinct foraging habitats. Higher δ13C values in B. bairdii suggest greater reliance on benthic or coastal food webs, whereas lower δ13C values in B. minimus reflect stronger associations with offshore ecosystems. Isotopic variation of different epidermal layers revealed temporal dietary shifts within individuals.ConclusionsThese results demonstrate clear ecological differentiation between B. bairdii and the recently described B. minimus. Historical data attributed to B. bairdii should be re‐evaluated to ensure accurate species‐specific interpretations of diet and habitat use, improving ecological understanding and conservation assessments.

Objective: Topographical disorientation refers to the partial or complete loss of the ability to navigate environments. Traditionally, it has been assessed with "paper and pencil" tests, but recent technological advances have introduced more ecological assessment methods. One such technology is virtual reality (VR), which enables assessment orientation within a three-dimensional environment without the need for actual open spaces. Our aim was to design a test to assess cognitive skills related to topographic orientation in VR environments.Materials and Methods: A battery of neuropsychological tests was administered together with a gamified VR task where participants learned to navigate in a large-scale virtual environment. The sample comprised 40 young adults (11 male; ages 18-35) with no history of neurological impairment.Results: After item reliability analysis, a test with solid internal consistency (Cronbach's alpha = 0.737) was developed. Additionally, a positive correlation was found between the skills of perception, retention, and visuospatial information processing and the VR test (ps ≤ 0.05).Conclusion: This study successfully developed a reliable gamified VR test, aligned with cognitive processes involved in anterograde topographic orientation. Although this tool still requires further studies to establish normative data and measures of specificity and sensitivity in clinical populations, it represents a crucial first step toward implementing this technology in the ecological evaluation of cognitive processes that are difficult to explore in clinical settings.

A structure-function integrated ecological index for ecological quality assessment in urbanizing subtropical regions.

ABSTRACT Urban forests are critical infrastructure within urban ecosystems and provide multiple ecosystem services, including heat island mitigation and enhanced carbon storage. However, classification accuracy and transferability in cities are constrained by high landscape heterogeneity, patch fragmentation, mixed pixels, and spectral confusion among different land-cover types. To improve forest-classification robustness under highly heterogeneous urban conditions, this study used Xi’an, China, as the study area and constructed a 2020–2025 multi-source remote sensing time-series dataset on the GEE platform. Ninety features were extracted from seasonal median composites, and collinear variables were removed using the variance inflation factor (VIF). The study compared three models, namely RF, GBT, and CART, selected the best-performing RF model, and further optimized it using recursive feature elimination (RFE), ultimately identifying 58 key features. The results show that: (1) RF (RFE) achieved the highest accuracy (OA = 77.40%, Kappa = 0.7175), and the original feature set was reduced from 90 dimensions to an optimal 58-dimensional feature subset; (2) topographic factors (elevation and slope) and third-quarter vegetation indices (GNDVI, NDVI, and ARVI) were the core features; (3) the spatial pattern of forests followed a ‘southern forests, northern grasslands; denser in the south, sparser in the north’ configuration, with evergreen needleleaf forest concentrated in the southern mountains, other vegetation occurring mostly as patchy distributions across the northern plain and peri-urban areas, and non-vegetated areas concentrated in the central-northern core; and (4) From 2020 to 2025, evergreen needleleaf forest first decreased and then increased; deciduous broadleaf forest fluctuated at a high level; evergreen broadleaf forest continued to shrink; other vegetation remained generally stable; and all land-cover classes exhibited differentiated temporal trajectories. The automated mapping framework based on the GEE machine-learning model developed in this study can provide quantitative and continuously updatable data support for urban forest planning and ecological performance assessment in Xi’an.

Basin-scale multi-index assessment of heavy metal contamination and risk partitioning across intertidal-supratidal sands in an industrialized Mediterranean coast (Gulf of Gabès; Tunisia).

Development of a new episodic memory assessment tool (NEM): Preliminary data and clinical perspectives.

A non-invasive framework for automated fish monitoring and morphological trait extraction: Implications for ecological monitoring and sustainable fisheries.

Exploring the ecological restoration zoning and diagnosis of the territorial space of the upper reaches of the Yangtze River shoreline in the Chongqing section could provide a scientific basis for regional land space ecological restoration. This study used the "sensitivity-resilience-pressure" （SRP） model to evaluate the ecological vulnerability of the upper reaches of the Yangtze River shoreline in the Chongqing section from 2010 to 2023 and used various methods to construct the ecological security pattern， including morphological spatial pattern analysis （MSPA）， minimum cumulative resistance （MCR） model， circuit theory， and others. Based on the ecological vulnerability assessment and ecological security pattern construction， this study carried out the territorial ecological restoration zoning and proposed diagnostic strategies. ① From 2010 to 2023， the ecological vulnerability index showed an overall upward trend， with moderate and above ecological vulnerable areas accounting for 95.86%. Highly and severely vulnerable areas were primarily concentrated in the main urban area of Chongqing and along the shorelines of the central urban areas of districts and counties. ② The study identified 17 ecological sources totaling 155.10 km2 in area， 25 ecological corridors with a total length of 438.46 km， 12 ecological pinch points concentrated in the shoreline of Chongqing's main urban area， and 39 ecological barriers predominantly located in the shoreline from Yunyang to Fengjie section. ③ There were four categories of ecological restoration zoning， including key protection areas， independent protection areas， key restoration areas， and ecological remediation areas. This paper proposed diagnostic strategies for different zones to provide references for the protection and restoration of ecosystems in the upper reaches of the Yangtze River.

The phenological changes of vegetation， as an important representation of the response of terrestrial ecosystems to external environmental changes， have significant implications for ecological environment assessment and biodiversity conservation. However， the regulatory mechanisms of pre-seasonal climate and terrain on vegetation phenology have not been fully elucidated， especially in high-altitude complex terrain areas. Based on SIF data， a Savitzky-Golay filter is used to reconstruct the SIF time series of the Yunnan-Guizhou Plateau from 2001 to 2023， and the vegetation phenology is extracted using the dynamic threshold method. Through partial correlation analysis and structural equation modeling （SEM）， the regulation mechanism of climate change and terrain on vegetation phenology change is discussed. The results showed that： ①SOS in the Yunnan-Guizhou Plateau was mainly concentrated in the 80th to 100th days， showing an early trend； EOS was concentrated between the 300th and 340th days， showing a delayed trend； and the average LOS was 218 days， showing a trend of extension. As the terrain rose from east to west， SOS gradually delayed， EOS advanced， and LOS correspondingly shortened. ② Pre-seasonal climate factors had a significant effect on vegetation phenological delay. SOS was significantly regulated by the 1-3 month lag effect of pre-season factors， with negative correlations in low latitude and low altitude areas and positive correlations in high-altitude and high-altitude areas. EOS was also regulated by the 1-3 month lag effect of pre-season factors， with a negative correlation between the eastern and low altitude regions and a positive correlation between the western and high-altitude regions. ③ Terrain indirectly regulated vegetation phenology by influencing temperature and precipitation. Slope had a significant regulatory effect on SOS and EOS but not on LOS. The influence of slope orientation on climate factors was weak， resulting in limited regulation of phenology. Altitude significantly regulated EOS and LOS by influencing temperature and precipitation.

Against the backdrop of spatial imbalance and frequent conflicts within metropolitan areas， constructing ecological security patterns （ESPs） that balance ecological value with spatial conflict adaptability is essential for promoting coordinated regional development. Existing ESPs construction methods primarily focus on ecological structural connectivity and functional importance assessments， while often overlooking real-world constraints such as spatial conflict intensity. This oversight leads to overlaps between identified ecological zones and high-conflict areas， limiting the applicability and effectiveness of such patterns in territorial spatial planning. To address this issue， this study takes the Xi'an metropolitan area as a case study， introducing spatial conflict intensity as a regulatory factor to optimize the identification of ecological sources and to construct conflict-regulated ESPs. Based on graph theory， the performance of this pattern is evaluated in comparison with mainstream structural， functional， and integrated ESPs across dimensions such as source robustness and network connectivity. The results showed that the conflict-regulated ESPs identified 228 ecological sources with a total area of 3 240.34 km2 and 594 ecological corridors with a total length of approximately 3，814.71 km. Compared to the other three ESPs types， the conflict-regulated pattern demonstrated superior performance in terms of source conflict robustness （0.491 8）， network closure （α = 0.286 3）， line-point ratio （β = 0.571 2）， and cost ratio （c = 0.991 9）. The study confirms that integrating spatial conflict factors into ESPs construction significantly enhances its practical adaptability and implementability， offering theoretical support and methodological pathways for optimizing ecological spatial patterns under multi-objective constraints in metropolitan regions.