Ecological Informatics最新文献

{"title":"Functional traits and ecosystem services across urban greenery, urban forests, and forests in nature-based solutions: A review","authors":"Margherita Paladini,&nbsp;Bruno Lasserre,&nbsp;Mario Pagano,&nbsp;Alessio Giovannelli,&nbsp;Claudia Cocozza","doi":"10.1016/j.ecoinf.2026.103943","DOIUrl":"10.1016/j.ecoinf.2026.103943","url":null,"abstract":"<div><div>Understanding how plant functional traits influence ecosystem functioning is essential for implementing effective nature-based solutions in both urban and forest contexts. In this study, 80 papers (12.1% of the initially identified literature) were systematically reviewed using the SPIDER selection method to examine how traits mediate resilience, adaptation, and ecosystem service delivery across urban greenery, urban forests, and forests. The analysis revealed that functional traits mediate the relationship between biodiversity and ecosystem service provision, and that their expression is strongly context-dependent, shaped by management intensity, species selection, and environmental stressors. The discussion highlights the importance of trait-based approaches for restoration planning, urban forestry, and ecosystem management, underscoring the need for standardized measurements, mechanistic models, and long-term monitoring to optimize ecosystem service delivery and strengthen resilience.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103943"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657356","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 ‘Predictive capabilities of novel deep neural networks learning for long-term streamflow prediction: Insights from the Barandouz Chay River’ [Ecological Informatics Volume 96 (2026) 103830]","authors":"Edris Merufinia,&nbsp;Ahmad Sharafati,&nbsp;Hirad Abghari,&nbsp;Yousef Hassanzadeh","doi":"10.1016/j.ecoinf.2026.103893","DOIUrl":"10.1016/j.ecoinf.2026.103893","url":null,"abstract":"","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103893"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148738378","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":"Evidence for the influence of shipping underwater radiated noise on sperm whale coda structure","authors":"Roee Diamant,&nbsp;David F. Gruber,&nbsp;Shane Gero,&nbsp;Gašper Beguš","doi":"10.1016/j.ecoinf.2026.103881","DOIUrl":"10.1016/j.ecoinf.2026.103881","url":null,"abstract":"<div><div>Shipping underwater radiated noise (S-URN) has been shown to harm whale populations, yet the mechanisms by which anthropogenic sounds interfere with whale vocalization systems are less understood. This paper investigates the impacts of S-URN on the structure of sperm whale coda vocalizations for hundreds of codas collected in the Eastern Caribbean. For the dataset collected, we show that the presence or absence of S-URN can be used to classify coda features, which arguably indicates a systematic effect on sperm whale vocalization. S-URN also results in changes in the spectral properties of the codas. In particular, S-URN decreases the accuracy of coda spectral classification even at short distances (several meters), suggesting that underwater noise impacts the structure of sperm whale coda signals. We further show that in the presence of S-URN, codas are shorter and more coda signals with a specific spectral pattern are vocalized.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103881"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148738379","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":"Automated bird flight pattern extraction and classification using machine learning","authors":"Milica Ostojic,&nbsp;Sarab S. Sethi","doi":"10.1016/j.ecoinf.2026.103946","DOIUrl":"10.1016/j.ecoinf.2026.103946","url":null,"abstract":"<div><div>With bird populations across the world being impacted by ever-growing anthropogenic pressures, reliable monitoring is essential to help halt or reverse declines. Existing visual bird monitoring approaches, which employ cameras or radars to deliver automated and large-scale monitoring data, face a variety of issues. Image-based species classification is only possible if the fine-scale features of a bird are clear, which can be difficult to achieve in real monitoring contexts without expensive, high-resolution cameras due to occlusion and lighting. Radar and video-based approaches which analyse longer-term flight behaviour over the course of seconds can achieve more reliable results in real monitoring contexts, particularly from greater distances, but still require expensive equipment and do not account for all the possible types of flight patterns. Here we present a novel approach to track a wide range of bird flight patterns using easily acquired videos from inexpensive, non-specialist cameras. As a proof-of-concept, we demonstrate how our approach can be used to classify birds between four species, Red Kite, Kestrel, Black-Headed Gull and Sparrowhawk, which represent four different types of flight patterns. The balanced accuracy of the classification is 0.5583, with a recall and precision per species that range from 0.2640 to 0.7750 and 0.4583–0.5962, respectively. Our proof-of-concept study demonstrates how new and existing visual bird monitoring systems can leverage flight patterns to deliver species-level insights at lower costs and on larger scales than before.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103946"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657288","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":"Network analysis of co-occurrence patterns in macroinvertebrate communities in lentic and lotic ecosystems of the tropical Andes, Ecuador","authors":"Andreea-Melisa Tripon,&nbsp;Henrietta Hampel,&nbsp;Raúl F. Vázquez,&nbsp;Diego Vimos-Lojano,&nbsp;Pablo V. Mosquera,&nbsp;Ferenc Jordán","doi":"10.1016/j.ecoinf.2026.103945","DOIUrl":"10.1016/j.ecoinf.2026.103945","url":null,"abstract":"<div><div>Co-occurrence networks are highly useful tools for studying fundamental aspects of ecosystems and for measuring ecosystem resilience. This information is especially valuable for the poorly studied tropical Andean aquatic ecosystems. Hence, co-occurrence networks were identified across three aquatic systems of southern Ecuador using extensive macroinvertebrate datasets from tropical Andean rivers and lakes. Full, positive, and negative networks were characterised through 8 network metrics, whilst the centrality of graph nodes was assessed using 3 centrality indices. The Tomebamba River had the most complex network, followed by the Yanuncay River and the Lakes in CNP (Cajas National Park). Oligochaeta, Hydracarina, and Chironomidae were present in all ecosystems. Different key taxa were identified, including <em>Heterelmis</em> and <em>Psychoda</em> (Tomebamba River), <em>Palpomyia</em> (Yanuncay River), and <em>Hyalella</em>, <em>Liodessus</em>, and Chironomidae (Lakes in CNP). In general, negative associations were more frequent than positive ones (statistically), indicating that these ecosystems could be driven by strong selection, competition, or niche partitioning. Clustering, average path length, and modularity metrics across the three network types indicate that riverine communities were divided into distinct subcommunities with niche exclusion. In contrast, taxa within these subcommunities tend to cooperate. The flow serves as a conduit, shortening paths between different parts of the network and linking subcommunities. In the lakes, environmental conditions were stable, leading to the development of possible strict competitive boundaries among taxa. Since water movement is limited, these groups were poorly connected. Positive interactions were localised in the lakes. Understanding community interactions and driving forces, and identifying key taxa, could provide valuable information for management and conservation, especially amid rapidly increasing anthropogenic pressures in these high-mountain ecosystems.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103945"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657295","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":"Intra-pixel scaling bias in satellite data for coastal monitoring: Evidence from photosynthetic biofilms","authors":"Augustin Debly,&nbsp;Bede Ffinian Rowe Davies,&nbsp;Simon Oiry,&nbsp;Julien Deloffre,&nbsp;Philippe Rosa,&nbsp;Alexandra Petit,&nbsp;Juline Boulinguez,&nbsp;Laurent Barillé,&nbsp;Vona Méléder","doi":"10.1016/j.ecoinf.2026.103953","DOIUrl":"10.1016/j.ecoinf.2026.103953","url":null,"abstract":"<div><div>Microphytobenthos (MPB) refers to photosynthetic, unicellular organisms that live in sediment, particularly in the intertidal zone of estuarine mudflats, where they can form biofilms. MPB provides a range of ecosystem services, including its role in carbon fluxes, sediment stabilisation, nutrient cycling, and the trophic network. MPB biomass is usually estimated by measuring the concentration of chlorophyll <em>a</em> at the sediment surface during low tide, which can be estimated locally and then extrapolated spatially using remote sensing methods, to produce biomass maps. Satellites are of particular interest since they provide long time series at high frequencies for studying MPB phenology. However, the MPB exhibits high spatial variability at the sub-satellite pixel scale, which is known to induce a scaling bias that results in the biomass being underestimated. This study used an unmanned aerial vehicle (UAV) to investigate the fine-scale spatial patterns of MPB, quantified the scaling bias and modelled it using generalized additive models (GAMs). Twenty-seven flights were performed over four different sites in different seasons in 2024 and 2025. The spatial resolutions of four satellites were compared: Pléiades Neo (1.2 m), Pléiades 1 A and 1B (2 m), SPOT 6 and 7 (6 m), and Sentinel-2 A, 2B and 2C (10 m). The bias values ranged between −14.2% (Pléiades Neo) and − 68.5% (Sentinel-2 A, 2B and 2C) when all the results were combined. This study emphasised the importance of spatial structure in quantitative remote sensing and proposed a practical framework for modelling the bias.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103953"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657793","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":"FF-fusion: A knowledge-distilled lightweight visible–infrared image fusion framework for Forest fire monitoring","authors":"Qian Yu,&nbsp;Gui Zhang,&nbsp;Ying Wang,&nbsp;Xin Wu,&nbsp;Wenping Liu,&nbsp;Zhuo Ouyang,&nbsp;Zhi Jiang,&nbsp;Long Qi,&nbsp;Wuyang Hu","doi":"10.1016/j.ecoinf.2026.103952","DOIUrl":"10.1016/j.ecoinf.2026.103952","url":null,"abstract":"<div><div>Visible–infrared image fusion offers an effective strategy for forest fire monitoring by integrating complementary information from visible-light and thermal-infrared modalities, particularly under smoke interference, low illumination, and complex forest backgrounds. However, forest-fire-specific paired datasets remain scarce, and lightweight fusion methods have seldom been evaluated under real-world monitoring scenarios and edge-deployment constraints. To address these limitations, this study constructs TF-1770, a spatially aligned visible–infrared forest fire dataset collected from ground-based and UAV-based firefighting scenes. The dataset comprises paired visible-light and thermal-infrared images captured under diverse viewpoints, smoke densities, illumination conditions, and target scales. Based on TF-1770, we propose FF-Fusion, a lightweight visible–infrared image fusion framework based on knowledge distillation. The teacher network learns robust multimodal representations through wavelet-based fusion and cross-modal feature modeling, while the student network incorporates re-parameterizable convolution blocks to enable efficient edge inference. Experimental results on TF-1770 show that FF-Fusion achieves entropy, standard deviation, average gradient, visual information fidelity, and edge information transfer metric values of 7.10, 43.66, 10.83, 0.649, and 0.584, respectively. The deployable student model maintains a compact size of only 1.34 MB. Downstream detection experiments demonstrate that the fused images enhance the perception of flames, smoke, and firefighters. Moreover, edge-deployment tests on heterogeneous platforms verify the feasibility of FF-Fusion for resource-constrained devices. These results indicate that lightweight visible–infrared image fusion can provide effective visual support for practical forest fire monitoring. The proposed workflow, spanning dataset construction, model design, downstream validation, and edge deployment, may also serve as a reference for future deployable ecological monitoring systems.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103952"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657294","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":"Acoustic recordings from narrow-band telemetry arrays allow long-term monitoring of the marine ecological state","authors":"Yuval Mendelson,&nbsp;Renanel Pickholtz,&nbsp;Moshe Kiflawi,&nbsp;Yossi Yovel,&nbsp;Jonathan Belmaker","doi":"10.1016/j.ecoinf.2026.103954","DOIUrl":"10.1016/j.ecoinf.2026.103954","url":null,"abstract":"<div><div>The use of Passive Acoustic Monitoring (PAM) to monitor marine diversity and ecological health is gaining popularity. However, long-term marine ecoacoustics monitoring remains limited, primarily due to technical challenges associated with data storage limitations and energy sources underwater.</div><div>Acoustic telemetry is a widely used tracking technique in which receivers record signals from acoustic tags, typically over long periods of time. While this method is widely used to record animal location and behavior, the receiver's recorded environment sound levels are mostly overlooked.</div><div>In this study, we introduce a new PAM method, which we call <em>Telemetry-based PAM,</em> that provides continuous long-term monitoring of the state of marine systems using currently untapped sound levels from acoustic telemetry. We demonstrate strong correlations between sound levels and biophonic sound sources, specifically invertebrate sounds, on a coral reef. We further demonstrate that the spatial and temporal decline and recovery patterns of sound from the receivers on the reef following a major storm closely aligned with parallel information from visual surveys.</div><div>As acoustic receiver arrays are already widespread globally, <em>Telemetry-based PAM</em> can provide an easy and affordable monitoring tool for marine environments. Importantly, as recordings are continuous, deployed for long durations, and based on multiple receivers, we can use these recordings to detect small-scale variations in sound levels over space and time, offering an unparalleled fine-grained view of reef dynamics.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103954"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657352","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":"Extreme droughts' impact on Scots pine net primary productivity in Poland in the period 2002–2023","authors":"Oliwier Zając,&nbsp;Kinga Kulesza,&nbsp;Agata Hościło","doi":"10.1016/j.ecoinf.2026.103936","DOIUrl":"10.1016/j.ecoinf.2026.103936","url":null,"abstract":"<div><div>Severe drought episodes significantly influence the productivity of trees in many parts of Europe. This paper shows in detail the impact of the most extreme drought events on the productivity of the most important and dominant tree species in Poland – Scots pine (<em>Pinus sylvestris L.</em>). We identified four months with most severe drought conditions that occurred in Poland during 2002–2023: July 2006, April 2009, August 2015 and June 2019. To estimate the net primary productivity (NPP) of pine forests, we used the Moderate Resolution Imaging Spectroradiometer (MODIS) NPP product for homogeneous pixels for this tree species. The obtained values were further correlated with temperature, precipitation, evapotranspiration and climatic water balance. The identified summer droughts had considerable effect on pine forest productivity. August 2015 exhibited the lowest NPP among all Augusts within the study period, representing a decrease of 57.80% relative to the long-term August mean. Similarly, July 2006 and June 2019 recorded pronounced reductions in NPP, declining by 40.81% and 20.59%, respectively, representing the lowest NPP values for these months across the entire period analysed. Our study demonstrates that the relationship between drought severity and pine's productivity depends on the time during the year, when the drought occurs. Summer droughts, with their peak in June, July or August, resulted in significantly decreased productivity of trees, while spring droughts, tend to have an initial positive impact on pine's condition. Pine forest productivity showed a prolonged decrease during summer droughts (e.g., August 2015, June 2019), with a negative relationship between NPP and temperature. Such long response of MODIS-derived NPP of pine is not clearly visible for drought occurring on the beginning of the growing season (April 2009). The results indicate that drought events significantly reduce pine NPP in Poland, with both the magnitude and duration of their impacts being strongly modulated by the timing of drought occurrence.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"97 ","pages":"Article 103936"},"PeriodicalIF":8.5,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657712","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":"Benchmarking large language models for biodiversity assessment: Performance and biases across IUCN Red List species","authors":"Shinya Uryu","doi":"10.1016/j.ecoinf.2026.103839","DOIUrl":"10.1016/j.ecoinf.2026.103839","url":null,"abstract":"<div><div>Although large language models (LLMs) are being widely applied in conservation science, their reliability for species assessment remains uncertain. In this study, five general-purpose LLMs available in August 2025 were benchmarked across 21,955 IUCN Red List species and four assessment components – taxonomic classification, conservation status, geographic distribution, and threat identification – using task-specific metrics and hierarchical statistical models that account for taxonomic structure. Performance was strongly task-dependent. The models exhibited high accuracy in taxonomic classification (94.9%) but limited capability in conservation-status assessment (27.2%). This 67.7 percentage-point gap, consistent across all models, highlights a distinction between information-processing and judgment-based assessments. Category errors were structured: Least Concern was underpredicted, whereas Data Deficient and Vulnerable were overpredicted. Approximately half of the misclassifications fell within the EX–LC threat continuum, often remaining close on the ordinal scale (about one-third were adjacent and four-fifths were within two ordinal steps). The remaining misclassifications lay outside the continuum – predominantly Data Deficient, with a small fraction of Not Evaluated or unparsable outputs – and were incomparable on the ordinal scale. Geographic distribution (45.6%) and threat identification (46.4%) showed intermediate performance, with systematic overprediction errors. Statistical analysis indicated significant taxonomic bias: the results for vertebrates were superior to those for invertebrates by 6.5 percentage points (<span><math><mrow><mi>P</mi><mo>&lt;</mo><mn>0</mn><mo>.</mo><mn>001</mn></mrow></math></span>), reflecting disparities in biodiversity knowledge representation. These findings support differentiated deployment: automation for structured information retrieval, human verification for moderate-confidence tasks, and expert-led assessment for judgment-based decisions. This study establishes an interpretable baseline for retrieval-augmented, multimodal, and multilingual successors in biodiversity informatics.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"96 ","pages":"Article 103839"},"PeriodicalIF":7.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148241937","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}