Ecological Informatics最新文献

{"title":"SWARM-IS: Adaptive sensor swarm search strategy and simulation framework for predator surveillance and control","authors":"Hugh Parsons,&nbsp;Sandra Gómez-Gálvez,&nbsp;Liam Brydon-Brown,&nbsp;Rachelle Binny,&nbsp;Bruce Warburton,&nbsp;Katerina Taškova","doi":"10.1016/j.ecoinf.2026.103930","DOIUrl":"10.1016/j.ecoinf.2026.103930","url":null,"abstract":"<div><div>Effective monitoring of predator eradication and control efforts critically depends on reliable detection across diverse and heterogeneous environments. However, existing search strategies do not take full advantage of the developed AI-enabled sensing technologies. In this paper, we present SWARM-IS, a novel adaptive sensor swarm strategy that dynamically optimises the spatial deployment of predator-detecting sensors based on their collective detection histories. The method leverages collective swarm information to iteratively guide sensor placement, enabling responsive adaptation to evolving environmental and ecological conditions. To evaluate the proposed approach, we developed a modular surveillance simulation framework that models varying predator densities, spatial ecology, and sensor detection efficacy. The performance of SWARM-IS is compared against conventional systematic and random search strategies across a range of ecological scenarios. The framework is generalisable and can be readily adapted to other predator surveillance and management contexts. Using this framework, we conducted a case study on brushtail possum surveillance under diverse ecological conditions and detection-efficacy regimes. Results demonstrate that the proposed adaptive swarm-based strategy can achieve up to a 40% absolute improvement in the number of individuals removed from the site compared to conventional approaches, highlighting its potential to enhance predator monitoring and, consequently, improve management outcomes.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103930"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Drivers of tree growth across Europe: An explainable AI analysis of tree- and site-level influences","authors":"Grégory Mermoud,&nbsp;Glory Mary Givi,&nbsp;Raphaël Lüthi,&nbsp;Volodymyr Trotsiuk,&nbsp;Nenad Potočić,&nbsp;Tanja G.M. Sanders,&nbsp;Bruno De Vos,&nbsp;Arthur Gessler,&nbsp;Stefan Hunziker","doi":"10.1016/j.ecoinf.2026.103932","DOIUrl":"10.1016/j.ecoinf.2026.103932","url":null,"abstract":"<div><div>Climate change is increasingly impairing forest ecosystems in Europe, reducing tree vitality and increasing mortality. Crown defoliation and stem growth are widely used indicators of early stress responses, yet their drivers remain difficult to disentangle due to complex, non-linear interactions among climatic, edaphic, and biotic factors.</div><div>Here, we apply explainable AI (XAI) to model annual diameter growth of individual trees from four dominant European tree species (<em>Norway spruce, Scots pine, Common beech, and Oak</em>) using long-term data from the ICP Forests Level II network. Gradient-boosted decision trees trained on tree-level attributes (e.g., defoliation, social class) and plot-level variables (e.g., soil solution chemistry, atmospheric deposition, and topography) outperform linear baselines across all ablations and grouping strategies. Ablation experiments show that plot-level features account for most of the predictive power while defoliation contributes only marginally.</div><div>XAI analyses reveal strong non-linear, species-specific response regimes, including marked growth reductions at high defoliation levels (∼35–60%) and optimal regimes of nitrogen and sulphate deposition, illustrating the capacity of XAI to identify candidate growth-relevant regimes and interactions.</div><div>However, temporally explicit validation using tree-wise cross validation results in a 54% reduction in R² score whereas spatially explicit validation based on plot-wise cross-validation leads to a near-complete collapse in predictive performance, indicating strong reliance on both temporal and spatial autocorrelation and context-specific patterns. Moreover, ablating defoliation features causes attribution to shift toward correlated environmental variables, highlighting the role of proxying and statistical confounding.</div><div>Overall, our results illustrate both the potential and the limitations of XAI for forest ecology: while effective for screening large observational datasets and generating hypotheses, XAI outputs require cautious interpretation, mechanistic understanding and spatially robust validation.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103932"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interannual variability of European beech spring phenology across elevation gradients derived from Sentinel-2 time series","authors":"Ana Potočnik Buhvald,&nbsp;Krištof Oštir,&nbsp;Mitja Skudnik","doi":"10.1016/j.ecoinf.2026.103934","DOIUrl":"10.1016/j.ecoinf.2026.103934","url":null,"abstract":"<div><div>Spring phenology of temperate deciduous forests is highly sensitive to interannual temperature variability, particularly in mountainous regions where strong elevational gradients create pronounced spatial differences in thermal forcing. In this study, we use dense Sentinel-2 time series to quantify start-of-season (SOS) dynamics of European beech across Slovenia between 2018 and 2021 and compare satellite-derived phenology with <em>in situ</em> observations from the Slovenian National Phenological Network.</div><div>Satellite-derived SOS estimates showed moderate agreement with <em>in situ</em> phenological observations. Spring onset showed a clear elevational gradient, with SOS delayed by approximately 2.5–2.8 days per 100 m increase in elevation, consistent with temperature-related differences in spring thermal accumulation across the mountain landscape. Interannual variability was substantial, with a 16.9-day difference in national mean SOS between 2018 and 2021. Spatial patterns of phenological shifts reflected contrasting spring thermal conditions, suggesting a close association between SOS variability and April temperature during the 2018–2021 study period.</div><div>These results highlight the short-term temperature-associated variability of European beech spring phenology and demonstrate the potential of high-resolution satellite time series to quantify canopy-level phenological patterns in topographically complex landscapes.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103934"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to ‘Exploring the trade-offs between spatial and spectral resolution in mapping invasive alien trees’ [Ecological Informatics 92 (2025) 103448]","authors":"Thandeka E. Skosana,&nbsp;Karen J. Esler,&nbsp;Alanna J. Rebelo","doi":"10.1016/j.ecoinf.2026.103955","DOIUrl":"10.1016/j.ecoinf.2026.103955","url":null,"abstract":"","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103955"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148738380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An uncertainty-aware Deep Learning approach for rapid burned area mapping using high-resolution PlanetScope multispectral imagery","authors":"Maximilian Jaderson de Melo,&nbsp;Thiago Edgar Bauce Venancio,&nbsp;Lucas Yuri Dutra de Oliveira,&nbsp;Keiller Nogueira,&nbsp;Lucas Prado Osco,&nbsp;Farid Melgani,&nbsp;Ana Paula Marques Ramos,&nbsp;José Marcato Junior,&nbsp;Wesley Nunes Gonçalves","doi":"10.1016/j.ecoinf.2026.103939","DOIUrl":"10.1016/j.ecoinf.2026.103939","url":null,"abstract":"<div><div>The increasing frequency of wildfires in wetlands demands rapid and accurate monitoring tools to mitigate regional ecological damage and assess carbon emission impacts. While Deep Learning (DL) models offer high precision for environmental monitoring, their operational deployment by environmental agencies is often hindered by the prohibitive cost and time required to generate dense, pixel-wise manual annotations. To address this labeling bottleneck, which critically delays disaster response and restoration policies, this work proposes an uncertainty-aware Weakly Supervised Semantic Segmentation (WSSS) framework tailored for high-resolution multispectral imagery. Our approach relies solely on image-level tags (e.g., “burned” or “unburned”) to train segmentation models, significantly democratizing and accelerating the mapping process. Technically, we adapt the Puzzle-CAM architecture to handle RGB-NIR data and integrate an Imbalanced Class and Uncertainty-aware loss (<span><math><msub><mrow><mi>L</mi></mrow><mrow><mi>I</mi><mi>C</mi><mi>U</mi></mrow></msub></math></span>) during the training stage. This loss function is specifically designed to mitigate the label noise inherent in the WSSS, particularly at the fuzzy boundaries between burned areas and spectrally similar wetland features. Experimental results demonstrate that our method produces sharp, boundary-adherent segmentation masks, achieving an IoU of 83.74% for the burned class. Notably, our approach outperforms recent contrast-based WSSS baselines and excels in detecting small, fragmented fire scars (1%–20% coverage). Furthermore, while a performance gap of approximately 11 percentage points remains when benchmarked against cutting-edge fully supervised foundation models, these findings suggest that uncertainty-aware WSSS is a viable, cost-effective alternative for operational fire monitoring, providing robust spatial data for environmental management, carbon accounting, and data-driven ecosystem analysis.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103939"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ecoregion-specific restructuring of green-season and peak-season phenology across the continental United States","authors":"Horia G. Olariu","doi":"10.1016/j.ecoinf.2026.103933","DOIUrl":"10.1016/j.ecoinf.2026.103933","url":null,"abstract":"<div><div>Vegetation phenology regulates ecosystem carbon, water, and energy exchanges; however, continental-scale assessments often emphasize growing-season boundaries while paying less attention to peak-season dynamics. We used MODIS Enhanced Vegetation Index (EVI) time series to quantify phase-specific phenological trends across stable non-crop vegetation in the continental United States (CONUS) from 2001 to 2024. Metrics included start of season (SOS), start of peak season (POS), end of peak season (POE), end of season (EOS), green-season length (GSL), and peak-season length (PSL). EVI-derived dates were benchmarked against USA National Phenology Network observations. Trend robustness was evaluated through threshold and smoothing sensitivity analyses, and environmental associations were assessed using XGBoost and SHAP attribution methods. Validation showed moderate agreement with USA-NPN observations (R² = 0.58–0.67; RMSE = 16.28–19.75 days). Ecoregion-level trends revealed phase-specific restructuring: GSL increased most in the Texas-Louisiana Coastal Plain (+0.68 days yr⁻¹), Western Sierra Madre Piedmont (+0.63 days yr⁻¹), and Everglades (+0.61 days yr⁻¹), whereas PSL shortened most in the South Central Semi-Arid Prairies (−0.50 days yr⁻¹), West-Central Semi-Arid Prairies (−0.32 days yr⁻¹), and Southeastern USA Plains (−0.30 days yr⁻¹). Several ecoregions exhibited longer green seasons but shorter peak seasons, indicating expanded shoulder-season greenness without a corresponding increase in sustained peak greenness. Attribution analyses indicated that SOS was associated with a combination of climatic, thermal, and topographic predictors, while POS, POE, and EOS were more closely linked to thermal and hydrologic conditions. These findings suggest that recent greening across CONUS reflects phase-specific restructuring of satellite-observed canopy greenness rather than a uniform extension of the growing season.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103933"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to “Temporal and spectral classification of satellite-derived aridity reveals multi-scale environmental signals in southern South America” [Ecological Informatics 96 (2026) 103871]","authors":"Pablo Marcelo Cometto,&nbsp;Santiago Ignacio Hurtado,&nbsp;Octavio Augusto Bruzzone,&nbsp;Marcos Horacio Easdale,&nbsp;Juan Manuel Casañas","doi":"10.1016/j.ecoinf.2026.103925","DOIUrl":"10.1016/j.ecoinf.2026.103925","url":null,"abstract":"","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103925"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148738381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classifying rodent behaviors one frame at a time: A CNN-based method","authors":"Ehsan Noshahri,&nbsp;Andres Molares-Ulloa,&nbsp;Carlota Fraga-Seijas,&nbsp;Alejandro Puente-Castro,&nbsp;Alvaro Rodriguez","doi":"10.1016/j.ecoinf.2026.103927","DOIUrl":"10.1016/j.ecoinf.2026.103927","url":null,"abstract":"<div><div>The classification of animal behavior is essential in disciplines such as pharmacology, neuroscience, and ecology. Traditional methods are labor-intensive, time-consuming, and dependent on human observation, while many existing automated approaches rely on pose estimation and temporal models that demand extensive data, annotations, and computational resources. This study proposes a non-temporal, frame-by-frame deep learning approach for classifying rodent behaviors directly from annotated video frames, without relying on pose estimation, body-part segmentation, or temporal context, and requiring only frame-level annotations. We constructed a large dataset of images representing distinct rodent behaviors in operant conditioning chambers to evaluate multiple convolutional neural network (CNN) architectures of various sizes. Our results show that deep CNNs achieve high classification performance in terms of accuracy and F1-score. The models maintain strong performance under challenging conditions, including restricted training data, noisy labels, and low subject diversity, demonstrating their data efficiency and resilience. Performance remains stable even when trained on data from a limited number of animals, supporting the method’s practicality for population-level behavior classification. Together, these results suggest that robust behavior classification can be achieved without temporal context, even under realistic experimental constraints such as limited data availability and label noise. The proposed framework also offers flexibility across different data formats, including static images and partial video recordings. Overall, our approach provides an accessible and scalable alternative for behavioral researchers, lowering barriers to automated animal behavior analysis while preserving strong classification performance.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103927"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When accessibility distorts niche estimates: A virtual species framework across species prevalence and sample size gradients","authors":"Rocìo Beatriz Cortès Lobos,&nbsp;Lorenzo Ricci,&nbsp;Matilde Martini,&nbsp;Riccardo Testolin,&nbsp;Michele Di Musciano,&nbsp;Vítězslav Moudrý,&nbsp;Quentin Groom,&nbsp;Duccio Rocchini","doi":"10.1016/j.ecoinf.2026.103937","DOIUrl":"10.1016/j.ecoinf.2026.103937","url":null,"abstract":"<div><div>Species distribution models are widely used in ecology and conservation biology to predict species' habitat suitability, but their performance is often compromised by biases in occurrence data. One of the most pervasive sources of bias arises from geographically uneven sampling, particularly the overrepresentation of areas close to roads. In this work, we outline a reproducible workflow to assess whether such geographic biases affect the representation of species' ecological niches in environmental space. We simulated 250 virtual species within the Abruzzo region (Italy) and evaluated the effects of sampling bias by systematically varying sample size and species prevalence (i.e., geographic range size). For each species, we compared random sampling from within the species' range with sampling constrained to areas near roads.</div><div>Rather than revealing a uniform effect of road-biased sampling, our results show that its consequences depend strongly on species prevalence, sample size, and the spatial correspondence between species' ranges and the accessible areas near the roads. The extent to which niche estimates are distorted therefore varies among species, implying that the effects of road-based sampling are species-dependent: sampling near roads can either misrepresent or adequately capture environmental conditions depending on the species considered. These findings highlight the need to be aware of how sampling patterns interact with species' spatial distributions when interpreting model outputs.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103937"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the reliability of the 1-meter resolution meta-estimated global canopy height map for estimating forest structural metrics in Alpine environment","authors":"Michele Torresani,&nbsp;Vítězslav Moudrý,&nbsp;Christopher R. Hakkenberg,&nbsp;Vojtěch Barták,&nbsp;Duccio Rocchini,&nbsp;Stefano Puliti,&nbsp;Paweł Hawryło,&nbsp;Krzysztof Stereńczak,&nbsp;Alexander Cotrina-Sanchez,&nbsp;Gabriele Giuseppe Antonio Satta,&nbsp;Luca da Ros,&nbsp;Patrick Kacic,&nbsp;Roberto Tognetti","doi":"10.1016/j.ecoinf.2026.103950","DOIUrl":"10.1016/j.ecoinf.2026.103950","url":null,"abstract":"<div><div>Monitoring forests globally through the assessment of structural characteristics is indispensable in times of increasing disturbances and biodiversity loss. The recent development of a 1-meter resolution Global Canopy Height Map by Meta and the World Resources Institute (Meta/WRI CHM) offers new opportunities for large-scale forest structure analysis. However, its reliability for estimating key forest structural metrics in selected forest sites of the Italian Alps remains largely untested. In this study, we compared estimates of canopy cover, mean and maximum canopy height, tree count, and crown size computed from the Meta/WRI CHM with the corresponding metrics computed from airborne laser scanning (ALS)-based CHMs across five forested sites in Alpine ecosystems representing diverse forest structures, species compositions, and management practices. Our results show that the Meta/WRI CHM provides reliable estimates of canopy cover (R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> = 0.82–0.92, RMSE = 8%–15%) and, to some extent, mean canopy height (R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> = 0.69–0.85, RMSE = 2.2–2.9 m). However, it substantially underestimates maximum canopy height and fails to reliably estimate tree count, positions, and crown size, overestimating the number of trees by 200–750 per hectare. In addition, the quality of the evaluated metrics estimates varied with respect to topographic gradients (i.e., slope, aspect, and altitude). Our findings define clear application boundaries for the Meta/WRI CHM in Alpine forest environments: while the product can support stand-level estimates of canopy cover and mean canopy height, it remains unsuitable for estimating maximum canopy height and individual-tree-level metrics such as tree count, tree position, and crown size. Future efforts should focus on refining global CHMs to improve accuracy and expand their applicability for forest monitoring.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103950"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}