-
4461
Changing grizzly bear space use and functional connectivity in response to human disturbance in the southern Canadian Rocky Mountains
Published 2025-08-01“…Our study builds upon existing work simulating animal space use from fitted iSSFs by incorporating individual‐level variation into population‐level simulations and by fitting functional responses that help capture broad‐scale variation in behavior and improve model transferability to new areas. Our results provide insights into grizzly bear movement and connectivity in an area of high conservation importance, and our predictive maps can be used to directly inform transboundary management actions and conservation planning.…”
Get full text
Article -
4462
Multi-scale attention-enhanced deep learning approach for detecting seven trunk pests and diseases in Shanghai’s urban plane trees
Published 2025-08-01“…Trained on 3,983 annotated samples from Shanghai, the model achieved a 3.8% increase in mean Average Precision at a 50% Intersection over Union threshold (mAP50) and a significant reduction in missed detections compared to the baseline YOLOv8. …”
Get full text
Article -
4463
Soil Salinity Detection and Mapping by Multi-Temporal Landsat Data: Zaghouan Case Study (Tunisia)
Published 2024-12-01“…These samples were representative of distinct soil salinity classes, including non-saline, slightly saline, moderately saline, strongly saline, and very strongly saline soils. Soil salinity modeling using Landsat-8 OLI data revealed that the SI-5 index provided the most accurate predictions, with an R<sup>2</sup> of 0.67 and an RMSE of 0.12 dS/m. …”
Get full text
Article -
4464
Normative structural connectome constrains spreading transient brain activity in generalized epilepsy
Published 2025-05-01“…The collective abnormality of structurally connected neighbors significantly predicted regional activity abnormality, indicating that white matter network architecture constrains aberrant activity patterns. …”
Get full text
Article -
4465
CNN Based Fault Classification and Predition of 33kw Solar PV System with IoT Based Smart Data Collection Setup
Published 2024-12-01“…Therefore, CNN is used as the fault prediction also. The model is implemented using Python programming language and demonstrated its effectiveness on test cases. …”
Get full text
Article -
4466
-
4467
A Three-Level Meta-Frontier Framework with Machine Learning Projections for Carbon Emission Efficiency Analysis: Heterogeneity Decomposition and Policy Implications
Published 2025-05-01“…Methodologically, we introduce two novel projection combinations—“exogenous-exogenous-accumulation (E-E-A) and exogenous-exogenous-consistent (E-E-C)”—to resolve the inconsistency of technology gap ratios (TGRs > 1) in traditional nonradial directional distance function (DDF) models. Reinforcement learning (RL) optimizes dynamic direction vectors, whereas graph neural networks (GNNs) encode spatial interdependencies to constrain the TGR within [0, 1]. …”
Get full text
Article -
4468
Accounting for transience in the baseline climate state changes the surface climate response attributed to stratospheric aerosol injection
Published 2024-01-01“…However, relative to the hypothetical scenario with lower CO _2 concentrations that would achieve a stabilised climate at the same temperature, SAI produces a 69% larger reduction in global precipitation. Accounting for stabilisation can also meaningfully change the spatial pattern of surface temperature response attributable to SAI. …”
Get full text
Article -
4469
Impact of modulating surface heat flux through sea ice leads on Arctic sea ice in EC-Earth3 in different climates
Published 2025-08-01“…<p>This sensitivity study examines the impact of modulating surface sensible heat flux over leads – open-water areas within sea ice cover – to approximate finer-scale processes that are often underrepresented in climate models. We aim to assess how this parameterization (referred to as ECE3L) influences the persistent positive bias in Arctic sea ice (concentration and thickness) in the global climate model EC-Earth3 (ECE3). …”
Get full text
Article -
4470
GOES‐R PM2.5 Evaluation and Bias Correction: A Deep Learning Approach
Published 2025-02-01“…Abstract Estimating surface‐level fine particulate matter from satellite remote sensing can expand the spatial coverage of ground‐based monitors. This approach is particularly effective in assessing rapidly changing air pollution events such as wildland fires that often start far away from centralized ground monitors. …”
Get full text
Article -
4471
PCES-YOLO: High-Precision PCB Detection via Pre-Convolution Receptive Field Enhancement and Geometry-Perception Feature Fusion
Published 2025-07-01“…To address these issues, this paper proposes PCES-YOLO, an enhanced YOLOv11-based model. First, a developed Pre-convolution Receptive Field Enhancement (PRFE) module replaces C3k in the C3k2 module. …”
Get full text
Article -
4472
Mapping emergent coral reefs: a comparison of pixel‐ and object‐based methods
Published 2025-02-01Get full text
Article -
4473
Implications of human induced changes on the distribution of important plant species in the northwestern coastal desert of Egypt
Published 2015-12-01“…Few studies have conducted spatially explicit modeling of plant species distribution in Egypt. …”
Get full text
Article -
4474
Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
Published 2025-08-01“…The 3D model enabled millimeter-precision quantification, supporting multi-angle and multi-level GT assessment that overcame the limitations of traditional 2D measurements.ConclusionThis system represents a methodological advancement from qualitative to spatial quantitative GT assessment. …”
Get full text
Article -
4475
Bayesian active sound localisation: To what extent do humans perform like an ideal-observer?
Published 2025-01-01“…The model predictions showed a general agreement with actual human performance. …”
Get full text
Article -
4476
Orchard variable-rate spraying method integrating GNSS and wind-excited audio-conducted leaf area density
Published 2025-07-01“…A variable-rate spray control model and algorithm were then constructed to regulate spray flow according to the spatial distribution of leaf area density across the orchard.ResultsField experiments demonstrated that the system achieved a mean relative error of only 5.52% in spray flow rate regulation. …”
Get full text
Article -
4477
On the convective nature of roll waves instability
Published 2005-01-01“…The study reveals an influence of the disturbance frequency on the perturbation spatial growth rate, which constitutes the theoretical foundation of semiempirical criteria commonly employed for predicting roll waves occurrence.…”
Get full text
Article -
4478
Study on the Disturbed Mechanical Behavior and Energy Evolution Characteristics of Deep Roof Rock Considering Spatio-Temporal Effects
Published 2024-01-01“…This model generalizes the disturbance stress path generated by the multi-working face mining of coal seam group in the longitudinal dimension as a cyclic loading and unloading process, the increase of the disturbance stress concentration factor caused by the reduction of the distance between the coal seams is reflected in the stress path as the increase of the peak stress of cyclic loading and unloading. …”
Get full text
Article -
4479
Using satellite-based Sun-induced chlorophyll fluorescence and spectral reflectance for improving terrestrial CO2 flux estimates of India
Published 2025-01-01“…We improve these model predictions by additionally using satellite-based solar-induced chlorophyll fluorescence (SIF), soil temperature , and soil moisture specific to the vegetation classes of the domain. …”
Get full text
Article -
4480
Arsenic toxicity exacerbates China’s groundwater and health crisis
Published 2025-04-01“…A random forest analysis identified chemical properties (including oxidation–reduction potential, pH, total manganese ion, total iron ion, total dissolved solids, and sulfate ion) as the most influential drivers, contributing 56% to the model’s explanatory power, followed by geographical factors at 28%, climatic factors at 10%, and human activities at 6%. …”
Get full text
Article