Ecological Informatics最新文献

{"title":"Predicting Lokta (Daphne bholua) distribution using machine learning algorithms: Implications for sustainable management","authors":"Shambhu Charmakar ,&nbsp;Dipesh Kumar Sharma ,&nbsp;Pratistha Shrestha ,&nbsp;Bishnu Bahadur K.C. ,&nbsp;Tama Ray ,&nbsp;Ametus Kuuwill","doi":"10.1016/j.ecoinf.2026.103774","DOIUrl":"10.1016/j.ecoinf.2026.103774","url":null,"abstract":"<div><div>Machine learning has markedly improved the accuracy of species distribution modelling, yet its use in the management of Non-Timber Forest Products remains limited. This gap is especially evident in Nepal for Lokta (Daphne bholua). Although Lokta has long been valued for traditional use and trade, its spatial distribution and production ecology have received little scientific attention, limiting efforts to manage it sustainably. Against this background, this study provides the first machine-learning-based prediction of Lokta distribution in Nepal and examines how climatic, edaphic, and topographic factors shape its occurrence. Data were collected from 396 randomly established 100 m² plots in Dolakha district, Bagmati Province, Nepal, of which 161 recorded the presence of Lokta. Four machine learning models were used to predict its distribution and generate habitat suitability maps based on climatic, edaphic, and topographic variables. Among the tested models, Extreme Gradient Boosting (XGB) delivered the best predictive performance (AUC = 0.93; accuracy = 86%), outperforming Random Forest, Artificial Neural Networks, and K-Nearest Neighbours. The model estimated that about 43% of the 100,311 ha of forest area is suitable for Lokta growth. Precipitation during the driest quarter was the strongest predictor, followed by elevation and soil texture, indicating that seasonal moisture, terrain, and soil conditions jointly shape Lokta habitat suitability. These findings provide a stronger scientific basis for targeting Lokta cultivation and enrichment planting in ecologically suitable areas, while also informing soil and water conservation measures to support natural regeneration and production in marginal habitats. More broadly, the study shows the value of machine learning, particularly XGB, for identifying suitable Lokta habitats and supporting conservation planning, sustainable harvesting, and spatially informed management at community forest, municipal, and national levels.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103774"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797902","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}

{"title":"Determining the suitable distance thresholds for optimizing functional connectivity and identifying conservation priorities of meadow in Poyang Lake, China","authors":"Cheng Zhang ,&nbsp;Wenbo Chen ,&nbsp;Fangfang Huang","doi":"10.1016/j.ecoinf.2026.103790","DOIUrl":"10.1016/j.ecoinf.2026.103790","url":null,"abstract":"<div><div>Landscape functional connectivity and the contribution of individual patches for overall functional connectivity varies depending on species dispersal distance. Determining the suitable distance thresholds enables the detection of vulnerable landscape connections and the identification of key habitat patches. However, the selection of distance thresholds is often arbitrary, and the effects of threshold choice on the assessment of landscape functional connectivity and identification of conservation priorities for habitat patches remain largely unknown. Taking the meadow of Poyang Lake as the research object, this study firstly identified the spatial distribution of meadow at each water level. Then, functional connectivity and the importance of meadow patches were analyzed under different dispersal distances using the graph-theoretic connectivity indices and the delta value of the probability of connectivity (dPC). Finally, the suitable distance threshold was determined by means of the natural breakpoint method. Our results indicated as follows: (1) The meadow was inundated and divided by water, and its shrinkage coexisted with fragmentation as the water level rose. When the water level fell, the meadow emerged and spliced, and its expansion coincided with cohesion. (2) Landscape functional connectivity showed a positive relationship with species dispersal distance. Meadow functional connectivity increased progressively with increasing dispersal distance. A range of 600–1000 m can be selected as the suitable distance threshold for optimizing meadow functional connectivity in Poyang Lake. Within this range, meadow functional connectivity varied little, which facilitates the identification of small components and isolated patches with low resilience to environmental risks, as well as the timely detection of vulnerable landscape connections. (3) The importance of habitat patches for overall functional connectivity was highly sensitive to species dispersal distance. The importance of meadow patches exhibited spatial differentiation, with large meadow patches being highly significant and small meadow patches becoming less detectable as dispersal distance increased. A distance of 800 m was ultimately determined as the optimal threshold for identifying conservation priorities of meadow patches in Poyang Lake. At this distance, the distribution pattern of important meadow patches was stable, and both large and small meadow patches could be clearly highlighted, thereby facilitating the effective identification of key meadow patches that make vital contributions to maintaining overall functional connectivity. This study provides a scientific basis for landscape pattern optimization and habitat protection in lake areas.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103790"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797903","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}

{"title":"Deep learning based detection of wild bee parasites under natural conditions","authors":"Svetlana Ionova ,&nbsp;Henri Greil ,&nbsp;Patrick Mäder ,&nbsp;Marco Seeland","doi":"10.1016/j.ecoinf.2026.103754","DOIUrl":"10.1016/j.ecoinf.2026.103754","url":null,"abstract":"<div><div>Wild bees are threatened by numerous parasites that can significantly impair their health and even lead to death. Such parasites can weaken entire colonies, ultimately causing their eradication. However, existing studies focus on domesticated honey bees and apply methods under well-controlled conditions. Methods for automated detection of parasites in wild bees and under natural conditions are lacking.</div><div>We focus on two types of parasites: endoparasites of the family Stylopidae and kleptoparasitic larvae of specific blister beetles of the tribe Meloidae. We followed an opportunistic data collection approach and sampled images of parasites present in the wild in Germany.</div><div>We investigate the feasibility of using deep learning methods to detect these parasites in images of wild bees with diverse natural backgrounds. In detail, we gathered, analyzed, and annotated publicly available images of parasitized bees. Then we trained an object detection model YOLO to localize and classify parasites in images of wild bees. Because the number of suitable images is limited, we applied data augmentation techniques to increase the dataset size. Most notably, we created composite images by overlaying segmented parasite crops on images of healthy bees.</div><div>Our trained model is a proof-of-concept to demonstrate automated parasite detection in images of wild bees under natural conditions. We note that detecting parasites poses a significant challenge, because they are often difficult to discern. Issues such as blurry images, poor illumination, occluded and overlapping parasites further complicate detection. The scarcity of available images exacerbates the problem. However, we demonstrate in a use case that the trained model can be used to analyze images of wild bees to find and identify unlabeled parasites in public image repositories. We provide a publicly available demonstrator to showcase the model’s capabilities and to encourage further research in this area.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103754"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797803","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}

{"title":"African swine fever spread in wild boars shaped by landscape and population processes","authors":"Hyemee Hwang ,&nbsp;Axel G. Rossberg ,&nbsp;Daseul Kim ,&nbsp;Injae Hwang ,&nbsp;Eun Sub Kim ,&nbsp;Yoonho Jeon ,&nbsp;Jiyoung Kim ,&nbsp;Byeong Jin Park ,&nbsp;Sae Yeon Jang ,&nbsp;Dong Kun Lee","doi":"10.1016/j.ecoinf.2026.103763","DOIUrl":"10.1016/j.ecoinf.2026.103763","url":null,"abstract":"<div><div>Human-driven landscape modification alters wildlife movements and contact networks, generating new and often more efficient pathways for pathogen transmission. Wild boars exhibit strong adaptability to anthropogenic environments and sustain and maintain African swine fever (ASF) circulation through dense aggregations and persistent carcasses, producing considerable ecological and economic impacts. Existing individual-based models frequently underrepresent mechanistic pathways by which hosts acquire energy, interact with heterogeneous resources, and convert these dynamics into growth, movement, and transmission risk. A spatially explicit individual-based model (IBM) was developed, integrating host bioenergetics, demography, and home-range foraging and relocation with a Susceptible Exposed Infectious Dead Carcass infectious Removed/Recovered (SEIDCR) transmission module incorporating carcass persistence to predict ASF risk in wild boar populations. Incorporating behavioral processes altered epidemic trajectories, generating secondary infection waves and sustaining intermediate-phase effective reproduction numbers (<span><math><msub><mi>R</mi><mi>e</mi></msub></math></span>), compared to a single-peaked trajectory under behavior-off scenario. This configuration improved spatial predictive performance (AUC = 0.63), with high-risk areas forming patch-like clusters consistent with observed ASF-positive carcass distributions. Embedding individual-level behavior within a population dynamic transmission framework enhanced predictive accuracy, captured recurrent epidemic waves, and delineated high-risk areas at operational management scale. This framework links landscape structure to host aggregation and contact processes, producing decision-ready risk maps to inform carcass removal, population management, and surveillance strategies.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103763"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797900","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}

{"title":"Hurricanes drive bird displacement revealed by deep learning species distribution models","authors":"Liying Li ,&nbsp;Marcos Zuzuarregui ,&nbsp;Junwen Bai ,&nbsp;Shoukun Sun ,&nbsp;Yangkang Chen ,&nbsp;Zhe Wang","doi":"10.1016/j.ecoinf.2026.103785","DOIUrl":"10.1016/j.ecoinf.2026.103785","url":null,"abstract":"<div><div>Hurricanes are increasing in frequency and intensity under climate change, driving rapid and cascading transformations in coastal ecosystems. In affected regions, storm-driven flooding can restructure habitats and facilitate the spread of invasive species, with impacts propagating across trophic levels. Because birds link terrestrial and aquatic systems, understanding hurricane-driven displacement is critical for biodiversity monitoring and adaptive conservation planning. We develop an adaptive stratified deep learning framework to analyze citizen-science observations and quantify hurricane impacts on 332 bird species. The model achieves high predictive performance while jointly capturing abiotic and biotic niche structure, enabling the generation of fine-scale maps of post-hurricane habitat suitability and species redistribution. Our results suggest that projected bird displacement is contingent on long-term trajectories of climate change and sea-level rise, reflecting the interaction of acute disturbance and chronic environmental change. Vulnerability varies systematically across functional morphology groups and hurricane seasons: medium-sized, medium-long-winged, and granivorous species exhibit greater resilience, whereas winter emerges as a critical bottleneck for maintaining structural habitat complexity. Prioritizing winter habitat quality and protecting refugia adjacent to agricultural lands may therefore yield disproportionate conservation benefits as hurricane intensity increases. Sheltering and rebound patterns further demonstrate that scenario contrasts are critical for coastal conservation, supporting a shift from static protection toward dynamic, surge-aware strategies. Collectively, this work provides a scalable analytical framework for proactive, climate-adaptive decision-making under intensifying extreme events.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103785"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797904","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}

{"title":"A graph neural network approach for aquatic biodiversity prediction leveraging water system interconnections","authors":"Byeongkeun Kwon ,&nbsp;Dain Lee ,&nbsp;Hyunjun Ko ,&nbsp;Hanbin Lee ,&nbsp;Hyeonjun Hwang ,&nbsp;Suhyeon Kim","doi":"10.1016/j.ecoinf.2026.103776","DOIUrl":"10.1016/j.ecoinf.2026.103776","url":null,"abstract":"<div><div>Rapid climate change and human activity have led to dramatic declines in aquatic biodiversity, which has destabilized ecosystems and accelerated ecological imbalances. Accordingly, analyzing and predicting shifts in aquatic biodiversity accurately is crucial for supporting effective conservation and sustainable resource management efforts. Previous studies have largely focused on statistical analysis and basic machine learning methods, considering water quality data from aquatic zones as independent and neglecting their connectivity. However, the interconnected nature of rivers, estuaries, and oceans means that changes in aquatic biodiversity are linked across water systems. We propose a data structure called the aquatic biodiversity graph (ABG) to account for these interconnected relationships. We then present a novel deep learning model called the ABG-based graph neural network (ABGNN), to analyze ABGs for aquatic biodiversity prediction. First, the ABGNN learns water quality information from observation point nodes utilizing a graph attention network by considering both the spatial and temporal characteristics of an ABG, and extracts node embeddings at the observation point level. Second, the proposed method aggregates these embeddings into sub-basin node embeddings and predicts the aquatic biodiversity of each sub-basin in an end-to-end manner. To conduct empirical analysis and model validation, we collected river and marine water quality data and biodiversity data from the Republic of Korea. The experimental prediction results of the ABGNN demonstrate superior performance compared with various baselines for aquatic biodiversity prediction. Our study provides a valuable tool for ecosystem management, supporting informed decision making for conservation efforts by predicting biodiversity dynamics accurately.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103776"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797905","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}

{"title":"Modelling fire behaviour in the lodgepole pine forests of interior British Columbia: An evaluation of models against field evidence","authors":"Mingrui Liu ,&nbsp;Gregory Greene ,&nbsp;Daniel D.B. Perrakis ,&nbsp;Dominik Roeser","doi":"10.1016/j.ecoinf.2026.103789","DOIUrl":"10.1016/j.ecoinf.2026.103789","url":null,"abstract":"<div><div>Fire behaviour models are increasingly used to guide wildfire management decisions, yet few have been rigorously validated with field-based evidence. Following a 2017 wildfire, we evaluated four fire behaviour models in natural and irregular shelterwood–treated lodgepole pine stands in interior British Columbia by comparing modelled against field-reconstructed head fire intensity (HFI) under recorded fire-weather scenarios. The Canadian Conifer Pyrometrics (ConPyro) model, when ladder fuels were included, produced predictions that closely matched reconstructed head fire intensity at the 75th wind percentile, with a mean absolute quantile distance (MAQD) of 1407 kW m⁻¹ across quantiles. Crown Fire Initiation and Spread (CFIS) predictions exhibited higher variance, with MAQD values ranging from 4545 to 7470 kW m⁻¹. The Canadian Forest Fire Behaviour Prediction (FBP) System (C2 and C3 fuel types) showed strong sensitivity to wind speed, resulting in large variability in predicted intensity. In contrast, BehavePlus consistently underestimated HFI (MAQD = 11,387 kW m⁻¹, <em>p</em> &lt; 0.01). In treated stands, all models either over- or underestimated HFI relative to reconstructed values, reflecting limited applicability in forests with discontinuous canopy structure. Overall, ConPyro performed adequately in natural conifer stands when ladder fuels were included, whereas all current models inadequately represented the spatial discontinuity and structural complexity created by treatments. These findings highlight the need to explicitly incorporate canopy structure into future model development to improve fire behaviour predictions in both natural and managed forests.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103789"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797901","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}

{"title":"InsectRoleVision: A computer vision system to study arthropod diversity and functional roles","authors":"Song-Quan Ong ,&nbsp;Min-Hui Lim ,&nbsp;Kim Bjerge ,&nbsp;Francisco Javier Peris-Felipo ,&nbsp;Rob Lind ,&nbsp;Toke Thomas Høye","doi":"10.1016/j.ecoinf.2026.103701","DOIUrl":"10.1016/j.ecoinf.2026.103701","url":null,"abstract":"<div><h3>Background</h3><div>Arthropods make up the majority of species on Earth. To study their diversity and ecological roles in ecosystems, bulk sampling is commonly used to collect large numbers of specimens. Processing these samples is labor-intensive and time-consuming, often delaying timely decision-making in ecosystem monitoring. Automated detection systems offer a promising alternative to support sample processing; however, most existing systems still have two major limitations. First, the pipelines for localizing and classifying arthropods in images, whether single- or double-stage, are limited. Second, the prediction results often lack information about functional roles. Therefore, we developed <em>InsectRoleVision</em>, a more expert-centered and reliable system that enables inference of arthropod diversity based on their functional roles.</div></div><div><h3>Methodology</h3><div>To develop the system, an image dataset with taxonomic resolution was designed and created to support conclusions about the functional roles of the animals. Both single-stage and double-stage recognition pipelines were compared. For single-stage detection and the first stage of double-stage detection, four YOLO models and a transformer were evaluated to localize and classify the arthropods in each image. In double-stage detection, the region of interest (RoI) was cropped into individual images after localization and used to compare four classification models: InceptionV3, ResNet, MobileNet, and VGG19. A logic block pipeline was connected to the prediction results to further infer the richness and proportionality of each class or taxon with respect to their functional roles.</div></div><div><h3>Result</h3><div>YOLOv11 was the best-performing model, achieving over 93% mAP, precision, and recall in localizing arthropods in the images. InceptionV3 was the best-performing classifier, achieving 80% precision and recall in classifying more than 43,000 cropped images of arthropods. There was no significant difference between the results of single- and modular double-stage detection strategies. Therefore, the choice between strategies depends on the intended application: single-stage detection provides real-time results and is suitable for real-time detection applications, while double-stage detection allows a human expert to review the detection proposal and refine the classification result. <em>InsectRoleVision</em> has adopted the YOLOv11-InceptionV3 architecture, which is more flexible and human-centered, allowing quick access to both arthropod diversity and ecological roles.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103701"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797906","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}

{"title":"Predicting reference evapotranspiration using the weighted instance handler wrapper algorithm","authors":"Khabat Khosravi ,&nbsp;Aitazaz A. Farooque ,&nbsp;Heydar Mirzaei ,&nbsp;Javad Hatamiafkoueieh","doi":"10.1016/j.ecoinf.2026.103684","DOIUrl":"10.1016/j.ecoinf.2026.103684","url":null,"abstract":"<div><div>Reference evapotranspiration (ET_o) is a critical climate parameter for drought management and the optimization of agricultural water use. This paper presents a machine learning-based framework for ET_o prediction that was developed and tested at Santa Barbara Station, USA, and evaluated using data from four additional stations, namely Santa Monica, San Benito, San Diego II, and San Luis OW. Two feature selection approaches were employed: Particle swarm optimization (PSO)and a manually selected highly correlated variable (HCVS). These approaches identified the most effective input scenarios from 11 potential variables. The selected inputs were then used in machine learning models, including weighted instance handler wrapper (WIHW) combined with alternating model tree (AMTree) (WIHW-AMTree-PSO and WIHW-AMTree-HCVS), dual perturb and combine tree (WIHW-DPCTree-PSO and WIHW-DPCTree-HCVS), and random tree (WIHW-RANTree-PSO and WIHW-RANTree-HCVS). Analysis showed PSO reduced errors in a range of 4.06% to 30.77% compared with HCVS across all five stations. Among the models, WIHW-AMTree-PSO achieved the best performance, with root mean square error values of 0.213 mm/day at Santa Barbara, 0.235 mm/day at Santa Monica, 0.275 mm/day at San Benito, 0.239 mm/day at San Diego II, and 0.279 mm/day at San Luis OW. The corresponding percentage of Bias values were − 1.89%, −0.659%, 2.00%, 1.11%, and 2.82%, whereas Nash-Sutcliff efficiency values were 0.985, 0.975, 0.980, 0.972, and 0.966. Additionally, the Kling–Gupta efficiency values ranged from 0.966 to 0.982, and the legates–McCabe coefficient of efficiency values ranged from 0.867 to 0.900. Collectively, the results demonstrate that the proposed methodology offers high reliability for ET_o prediction and holds considerable promise for broader applications in environmental, hydrological and climate-impact modeling. These findings highlight the value of advanced machine learning approaches for robust estimation of ET_o, thereby supporting effective water resource management and agricultural planning, particularly in data-limited regions</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103684"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797899","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}

{"title":"A site prioritization tool for invasive species management: Integrating diverse spatial data to improve decision making","authors":"Janet S. Prevéy ,&nbsp;Cameron J. Reimer ,&nbsp;Peder S. Engelstad ,&nbsp;Pairsa N. Belamaric ,&nbsp;Terri Hogan ,&nbsp;Jillian M. LaRoe ,&nbsp;Colter J. Mumford ,&nbsp;Jennifer L. Sieracki ,&nbsp;Catherine S. Jarnevich","doi":"10.1016/j.ecoinf.2026.103779","DOIUrl":"10.1016/j.ecoinf.2026.103779","url":null,"abstract":"<div><div>Resource managers are tasked with protecting natural areas from invasive species with limited resources. Further, invasive management goals can vary greatly based on different management priorities specific to management agencies or taxa of interest. The site prioritization tool for invasive species management addresses these challenges by creating a platform to view and combine diverse spatial data layers to estimate cumulative invasion risk based on user-specific needs. For this tool, we developed a human transport risk layer, estimating invasion risk based on proximity to human population centers and transportation corridors, and created maps of non-native species richness across the conterminous United States. The tool also includes spatial layers showing projected changes in key climate variables through the end of the century to identify areas where invasion risk may shift. Users can explore these layers to prioritize sites based on the invasive taxa of interest, likely invasion pathways, and disturbances that may elevate invasion risk. This interactive tool will allow managers to make the spatial comparisons needed to focus efforts on areas that are highly susceptible to invasion and efficiently target monitoring and suppression efforts.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"95 ","pages":"Article 103779"},"PeriodicalIF":7.3,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147798007","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}