Ecological Informatics最新文献

{"title":"Towards eco-efficiency of OECD countries: How does environmental governance restrain the destructive ecological effect of the excess use of natural resources?","authors":"Brahim Bergougui ,&nbsp;Elma Satrovic","doi":"10.1016/j.ecoinf.2025.103093","DOIUrl":"10.1016/j.ecoinf.2025.103093","url":null,"abstract":"<div><div>Developed economies face mounting environmental challenges from excessive resource consumption, but we lack clear evidence on how environmental policies can best address these issues. This study investigates how environmental governance shapes resource use and ecological efficiency across nine OECD countries from 1997 to 2020. Our analysis reveals that stronger environmental policies significantly improve eco-efficiency: a 1 % increase in environmental governance effectiveness enhances eco-efficiency by 0.65–0.95 %, with the strongest effects observed in countries currently showing lower ecological efficiency. We find that increasing energy transition efforts and research and development investment each contribute to improved eco-efficiency (0.07–0.11 % and 0.19–0.35 % respectively), while excessive resource use reduces it by 0.07–0.03 %. Notably, our study introduces a novel analytical approach by examining how environmental policies moderate the negative impacts of resource overuse across different levels of ecological efficiency. This relationship proves especially important for countries struggling with lower eco-efficiency, where strong environmental governance can effectively offset the harmful effects of excessive resource consumption. These findings remain consistent across multiple measures of eco-efficiency and trade indicators, offering robust evidence for policymakers. Our research provides practical guidance for balancing economic development with environmental protection through targeted policy interventions, particularly in resource-intensive economies working to improve their ecological performance.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103093"},"PeriodicalIF":5.8,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143520519","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":"SPREAD: A large-scale, high-fidelity synthetic dataset for multiple forest vision tasks","authors":"Zhengpeng Feng,&nbsp;Yihang She,&nbsp;Srinivasan Keshav","doi":"10.1016/j.ecoinf.2025.103085","DOIUrl":"10.1016/j.ecoinf.2025.103085","url":null,"abstract":"<div><div>We present the Synthetic Photo-realistic Arboreal Dataset (SPREAD), a state-of-the-art synthetic dataset specifically designed for forest-related machine learning tasks. Developed using Unreal Engine 5, SPREAD goes beyond existing synthetic forest datasets in terms of realism, diversity, and comprehensiveness. It includes RGB, depth images, point clouds, semantic and instance segmentation labels, along with key parameters such as tree ID, location, diameter at breast height (DBH), height, and canopy diameter. In exemplary experiments, we found that SPREAD significantly reduces the need to use real-world datasets for trunk segmentation tasks and enhances model segmentation performance. Specifically, by pretraining on SPREAD, MobileNetV3 and DeepLabV3 models require only 25% of a fine-tuning real-world dataset to match or even surpass the performance of ImageNet-pretrained models fine-tuned on the entire real-world dataset. Furthermore, our hybrid training experiments demonstrate that by combining SPREAD and real data at a 1:1 or 2:1 ratio greatly improves task performance. For the canopy instance segmentation task, SPREAD pretraining still provides varying degrees of performance improvement for the models. All datasets, data collection frameworks, and codes are available at <span><span>https://github.com/FrankFeng-23/SPREAD</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103085"},"PeriodicalIF":5.8,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510977","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":"Advancing lakes algal chlorophyll estimation in the contiguous USA: A comparative study of machine learning models and satellite data","authors":"Md Mamun,&nbsp;Xiao Yang","doi":"10.1016/j.ecoinf.2025.103087","DOIUrl":"10.1016/j.ecoinf.2025.103087","url":null,"abstract":"<div><div>Algal blooms are ubiquitous in lentic ecosystems and pose a risk to human and other organisms' health. Accurate measurement of chlorophyll-a (CHL-a) in lakes at a macroscale is challenging due to the optical complexity of individual water bodies, which hinders the optimization of conventional bio-optical algorithms. This study harnesses the synergy of satellite remote sensing and machine learning (ML) to enhance CHL-a quantification from space. Given the cost and logistical demands of in-situ CHL-a data collection, especially over vast areas, we explore the potential of the open-source AquaSat dataset for CHL-a estimation across the contiguous USA. We assess the performance of four ML algorithms (random forest, extra tree regressor, bagging regressor, and xgboost model), discern the most influential spectral bands and indices, and compare these methods to established remote sensing techniques for CHL-a prediction. Both bagging regressor and random forest performed equally well on all AquaSat data or data from each sensor separately (R² = 0.35–0.54, RMSE = 20.48–23.90 μg/L). Model-agnostic SHAP summary plots were used to identify important indexes in CHL-a estimation. Spatio-temporal validations demonstrated the models' reliability across diverse conditions, with better generalizability in spatial domains compared to seasonal or yearly transitions. The accuracy of algorithms for estimating CHL-a depends on the satellite sensor. We found that by comparing remote sensing studies with various atmospheric correction approaches, the Landsat collection 1 (LC1) surface reflectance product offers consistent CHL-a estimates throughout the USA. Overall, acknowledging the existing limitations and challenges of such approaches, this research illustrates the potential of utilizing open-source data with ML to facilitate large-scale estimation of lake CHL-a.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103087"},"PeriodicalIF":5.8,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511126","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":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","authors":"René Heinrich ,&nbsp;Lukas Rauch ,&nbsp;Bernhard Sick ,&nbsp;Christoph Scholz","doi":"10.1016/j.ecoinf.2025.103081","DOIUrl":"10.1016/j.ecoinf.2025.103081","url":null,"abstract":"<div><div>Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103081"},"PeriodicalIF":5.8,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143508782","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":"Reduced dimensionality space of features using spectral indices for detecting changes in multitemporal Landsat-8 images","authors":"Elvira Martínez de Icaya-Gómez ,&nbsp;Estíbaliz Martínez-Izquierdo ,&nbsp;Montserrat Hernández-Viñas ,&nbsp;Jose E. Naranjo-Hernández","doi":"10.1016/j.ecoinf.2025.103090","DOIUrl":"10.1016/j.ecoinf.2025.103090","url":null,"abstract":"<div><div>In this study, spatio-temporal changes in water covers are calculated for Lake Urmia (Iran) from 2013 to 2023 using multi-temporal Landsat-8 OLI (Operational Land Imager) and TIRS (Thermal InfraRed Sensor) multispectral images. The challenge was working in a reduced dimensionality space of characteristics. With this objective, ten spectral water indices have been assessed. Moreover, Land Surface Temperature (LST) maps have been obtained from water bodies for correlation purposes. The evaluation of the indices is developed by K-means (unsupervised) and Random Forest (supervised) machine learning non-parametric classifiers. The total agreement between the classification results and the test data in the case of the Salinity Water Index (SWI) exceeds 95 % (96.00–98.50 %) for Overall Accuracy (OA) and 0.80 (0.84–0.99) for F1-Score. Furthermore, a strong correlation is observed between the LST and the SWI index, with correlation coefficient values exceeding 0.77 in all cases. These results show the effectiveness of the SWI spectral index in detecting changes in water area, particularly for tracking variations over time in hyper-saline water bodies such as Lake Urmia. In this case, the water coverage observed from 2013 to 2023 shows a slight recovery in 2016, followed by a more significant increase in 2019 and 2020. However, in recent years, the lake has experienced a dramatic decline, with water coverage sharply decreasing by 2023.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103090"},"PeriodicalIF":5.8,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511125","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":"ExActR: A Shiny app for creating ecosystem extent accounts","authors":"Anthony Gibbons ,&nbsp;Francesco Martini ,&nbsp;Cian White ,&nbsp;Emma King ,&nbsp;Jane C. Stout ,&nbsp;Ian Donohue ,&nbsp;Andrew Parnell","doi":"10.1016/j.ecoinf.2025.103072","DOIUrl":"10.1016/j.ecoinf.2025.103072","url":null,"abstract":"<div><div>Ecosystem accounting is a structured way to integrate nature into sustainable decision-making. The System of Environmental Economic Accounting-Ecosystem Accounting (SEEA-EA) was adopted by the United Nations as a set of international standards for the collection of habitat data and compiling ecosystem accounts. The ecosystem extent account is one of the four pillars of the SEEA-EA framework, where the spatial composition of an ecosystem accounting area is grouped by habitat types, and the land cover change over time is quantified. Although a variety of tools exist for preparing extent accounts, most of them require moderate to high levels of technical expertise. Here, we present <em>ExActR</em> (Extent Accounts in R), an open-source application for generating extent accounts using shapefiles, a geospatial vector data format. The app is built in <span>R</span> and the associated Shiny framework, which automatically updates as the user interacts with it. The application supports multiple timepoints, where extent accounts (tables) are generated for consecutive pairs of timepoints, accommodating users’ needs for dynamic ecosystem assessments across several periods. Data visualisations are generated in the form of both interactive (leaflet) and static maps of each timepoint, and barplots to illustrate land type composition and change. A version of the app has been deployed (available at <span><span>https://gibbona1.shinyapps.io/extent_app/</span><svg><path></path></svg></span>), offering a space for interactive exploration of ecosystems. Shiny’s reactivity, combined with JavaScript plugins for copying tables into multiple formats, including LaTeX and plots, make the application results suitable to insert directly into reports. The app is suitable for using with any spatial grouping variable. We test its functionality on small and large study sites on CORINE land cover data, as well as land cover maps generated using very-high resolution satellite imagery of a wind farm site in Ireland, during and post construction, demonstrating its ability to adapt to various land cover classification systems. The tool can be used to understand, visualise and track changes in ecosystem assets, aiding interpretation by both scientists and stakeholders.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103072"},"PeriodicalIF":5.8,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480763","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":"Land-Unet: A deep learning network for precise segmentation and identification of non-structured land use types in rural areas for green urban space analysis","authors":"Yan Zhao ,&nbsp;Junru Xie ,&nbsp;Huiru Zhu ,&nbsp;Taige Luo ,&nbsp;Yao Xiong ,&nbsp;Chenyang Fan ,&nbsp;Haoxiang Xia ,&nbsp;Yuheng Chen ,&nbsp;Fuquan Zhang","doi":"10.1016/j.ecoinf.2025.103078","DOIUrl":"10.1016/j.ecoinf.2025.103078","url":null,"abstract":"<div><div>Land Use and Land Cover Change (LUCC) have become popular research topics in the environmental field. With the development of artificial intelligence technology, many downstream applications based on intelligent urban–rural semantic analysis have emerged. Scholars have made significant progress in the intelligent analysis of urban imagery, but exploration of unstructured rural remote sensing data has been limited. This paper addresses the existing pixel-level semantic ambiguity issues and proposes a new deep learning model, Land-Unet. The network features a dual-branch Edge-Sensing Block (ESB) structure, including a Spatial and Channel Synergistic Attention (SCSA) branch and a Dynamic Upsampling (DYU) technique, which effectively resolves contour ambiguity in edge semantic information in rural images. Experiments on multiple datasets using various deep learning methods show that compared with the original structure, the proposed method increases <span><math><mrow><mi>m</mi><mi>I</mi><mi>o</mi><mi>U</mi></mrow></math></span> by 9.7%, <span><math><mrow><mi>m</mi><mi>D</mi><mi>i</mi><mi>c</mi><mi>e</mi></mrow></math></span> by 5.9%, and <span><math><mrow><mi>m</mi><mi>A</mi><mi>c</mi><mi>c</mi></mrow></math></span> by 12.2%. Compared to transformer-based methods, proposed method also demonstrated improved performance. Additionally, a new rural satellite imagery dataset, RuralUse, has been open-sourced for semantic segmentation research.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103078"},"PeriodicalIF":5.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471479","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":"Quantification of chlorophyll-a in inland waters by remote sensing algorithm based on modified equivalent spectra of Sentinel-2","authors":"Wenbin Pan ,&nbsp;Fei Yu ,&nbsp;Jialin Li ,&nbsp;Chunqiang Li ,&nbsp;Ming Ye","doi":"10.1016/j.ecoinf.2025.103061","DOIUrl":"10.1016/j.ecoinf.2025.103061","url":null,"abstract":"<div><div>The development of remote sensing algorithms has traditionally relied on satellite spectra or simulated equivalents derived from in-situ spectra to monitor inland water quality. However, such equivalent spectra often result in significant errors when retrieving chlorophyll-<em>a</em> (Chl-<em>a</em>) concentrations due to discrepancies between in-situ and satellite-derived spectra. In this research, the authors innovatively adjusted the red-light component of in-situ spectra for application in two inland waters, Dongzhang Reservoir and Jie Zhukou Reservoir. Sentinel-2 multispectral images (MSI), standard equivalent spectra (ES), and modified equivalent spectra (MES) were utilized as input data to assess models' effectiveness in terms of accuracy, robustness, and generalizability. The research applied Chl-<em>a</em> retrieval models including deep neural networks (DNN), extreme gradient boosting (XGB), and conventional statistical approaches with various spectral indices, such as the red-NIR method, the three-band method, and the normalized difference chlorophyll index (NDCI). The results revealed that the MES-based model achieved best results in Chl-<em>a</em> retrieval (RMSE = 2.04 mg/m³) comparable to MSI-based model (RMSE = 2.07 mg/m³) and ES-based model (RMSE = 7.71 mg/m³). Moreover, MES-based model behaved robustness and precision within selected water bodies and temporal periods. Notably, the integration of the red-NIR method with DNN was particularly effective in retrieving Chl-<em>a</em> with higher accuracy, robustness, and generalizability. Enhancement method to the equivalent spectra methodology provided by the research have reduced retrieval errors in retrieving Chl-<em>a</em>, and providing a valuable reference for future model development in this domain.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103061"},"PeriodicalIF":5.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143489026","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":"Vegetation coverage patterns in the “mountain–basin” system of arid regions: Driving force contribution, non-stationarity, and threshold effects","authors":"Rou Ma ,&nbsp;Zhengyong Zhang ,&nbsp;Lin Liu ,&nbsp;Mingyu Zhang ,&nbsp;Chen Ma ,&nbsp;Yu Cao ,&nbsp;Yu Gao ,&nbsp;Xueying Zhang ,&nbsp;Xinyi Liu ,&nbsp;Jiayi Zhang ,&nbsp;Zifan Yuan","doi":"10.1016/j.ecoinf.2025.103084","DOIUrl":"10.1016/j.ecoinf.2025.103084","url":null,"abstract":"<div><div>The spatiotemporal pattern and asymmetry characteristics of the normalized difference vegetation index (NDVI) in Xinjiang were analyzed on multiple scales. A multi-model attribution analysis framework that combined a geodetector model (GD), geographically weighted regression (GWR), and random forest (RF) was constructed, since previous efforts using these approaches individually were not able to capture both linear and nonlinear effects. The action laws of contribution degree identification, spatial non-stationarity analysis, and response threshold exploration of NDVI driving factors were also analyzed. The results showed that: (1) the annual mean NDVI in Xinjiang from 2000 to 2021 was 0.106, and overall macroscopic pattern was high in mountainous areas and low in basins. The interannual NDVI exhibited a fluctuating and slightly increasing trend, while the summer NDVI increased the fastest. The asymmetric change trend of the NDVI between seasons was the strongest in the Altay Mountains and Yili River Valley. (2) The NDVI first increased and then decreased with increasing elevation, reaching a peak at a height ranging 2–3 km. The NDVI was highly heterogeneous in mountainous and oasis areas and relatively homogeneous in basins. (3) A scale effect was observed. The detection results of the GD model differed between the Xinjiang and mountain scales. (4) Temperature (Tem), relative humidity (Rh), and precipitation (Pre) had positive effects on NDVI changes, whereas land surface temperature (LST) and summer temperature had negative effects. The threshold of LST was 9 °C in summer, and the temperature threshold was 25 °C. Our results provide guidance for analyzing the causes and ecological effects of vegetation growth.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103084"},"PeriodicalIF":5.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480737","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":"Assessing eco-physiological patterns of Ailanthus altissima (Mill.) Swingle and differences with native vegetation using Copernicus satellite data on a Mediterranean Island","authors":"Flavio Marzialetti ,&nbsp;Vanessa Lozano ,&nbsp;André Große-Stoltenberg ,&nbsp;Maria Laura Carranza ,&nbsp;Michele Innangi ,&nbsp;Greta La Bella ,&nbsp;Simonetta Bagella ,&nbsp;Giovanni Rivieccio ,&nbsp;Gianluigi Bacchetta ,&nbsp;Lina Podda ,&nbsp;Giuseppe Brundu","doi":"10.1016/j.ecoinf.2025.103080","DOIUrl":"10.1016/j.ecoinf.2025.103080","url":null,"abstract":"<div><div>Biological invasions, one of the most pervasive components of global change, can cause irreversible alterations in the composition and functioning of ecosystems. This includes changes of eco-physiological traits of plant communities. Satellite remote sensing provides the means to map surrogates of ecosystem composition and functioning such as eco-physiological traits over large spatial extents. In this study, Sentinel-2 and Sentinel-3 Copernicus satellite data resampled to 20 m² spatial resolution was used to characterize the annual cycle of spectral eco-physiological traits in 176 patches invaded by <em>Ailanthus altissima</em> (Mill.) Swingle in Sardinia (Italy) and in their corresponding and surrounding non-invaded areas. The overall aim was to examine if and how eco-physiological traits differed between <em>A. altissima</em> and native vegetation classes. A set of spectral eco-physiological indices proxies related to leaf chlorophyll <em>a</em>nd carotenoid content (Chlorophyll Vegetation Index − CVI, Structure Intensive Pigment Index 3 − SIPI3), productivity and canopy biomass (Enhanced Vegetation Index − EVI, Leaf Area Index − LAI), leaf water content (Normalized Multi-band Drought Index − NMDI, Moisture Stress Index − MSI), daily evapotranspiration (ET), and soil features (Coloration Index − CI) were calculated. The monthly trends of these indices in invaded patches and the seasonal differences between invaded and non-invaded cells were analyzed using linear mixed models (LMMs). One-way Analysis of Variance (ANOVA), and Estimated Marginal Means (EMMs) were used to test the differences between invaded and non-invaded cells. Our results highlighted the effectiveness of Sentinel-2 and -3 data in capturing the temporal trends of spectral eco-physiological traits. Most significant differences between invaded and non-invaded cells were observed during summer, with invaded cells featuring higher productivity, canopy biomass, and leaf water content, while leaf carotenoid content and bare soil cover was lower. Overall, our findings based on satellite-based remote sensing analysis provide further evidence of the competitive advantages <em>A. altissima</em> has over native vegetation, particularly in summer, when vegetation in Mediterranean-type ecosystems faces an intense drought stress. Such spatially explicit information facilitates the identification and selection of field sites for proximal measurements of the alterations and potential impacts attributed to <em>A. altissima</em> invasion.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"87 ","pages":"Article 103080"},"PeriodicalIF":5.8,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511128","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}