Ecological Informatics最新文献

{"title":"Spatiotemporal water quality data reconstruction: A tensor factorization framework","authors":"Xuke Wu ,&nbsp;Kun Shan ,&nbsp;Lan Wang ,&nbsp;Jingkai Wang ,&nbsp;Mingsheng Shang","doi":"10.1016/j.ecoinf.2025.103283","DOIUrl":"10.1016/j.ecoinf.2025.103283","url":null,"abstract":"<div><div>Automatic high-frequency monitoring (AHFM) of water quality parameters has gained growing attention for managing eutrophic lakes. However, missing data in water quality datasets remains a persistent challenge, often compromising the reliability of mathematical models and statistical analyses. While traditional imputation methods fail to adequately capture complex spatiotemporal dependencies among water quality variables, this study proposes a novel nonnegative tensor factorization (NTF) model designed to reconstruct missing values by effectively modeling variable-site-time triad interactions. Previous findings indicate that incorporating bias schemes into NTF architectures substantially reduces underfitting risks. Leveraging this insight, we develop and rigorously evaluate seven distinct biased NTF variants. Their diversified bias term designs not only enhance individual model performance but also enable highly effective ensemble learning through complementary strengths. To validate the proposed models, we conduct comprehensive experiments using real-world AHFM data from Lake Dianchi, China, under various missing data scenarios (20–80 % missing ratios and 1–4 weeks missing gaps). The key water quality parameters include chlorophyll-<em>a</em> concentration, water temperature, pH, dissolved oxygen, electrical conductivity, turbidity, chemical oxygen demand, ammonia, total phosphorus, and total nitrogen. The results demonstrate the superiority of the seven biased NTF models, achieving optimal performance with a root mean squared error (RMSE) of 0.2796 ± 0.0041, mean absolute error (MAE) of 0.1611 ± 0.0034, and Nash-Sutcliffe efficiency (NSE) of 0.9704 ± 0.0009 across all missingness scenarios. Compared to state-of-the-art models, these methods yield consistent improvements of 3.42 %–30.74 % in RMSE, 2.30 %–30.38 % in MAE, and 0.20 %–3.22 % in NSE. Notably, an ensemble of the seven models further elevates imputation accuracy, attaining an RMSE of 0.2409 ± 0.0018, MAE of 0.1384 ± 0.0012, and NSE of 0.9768 ± 0.0009. These findings underscore the potential of bias-enhanced NTF frameworks as a robust tool for analyzing high-dimensional monitoring data.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103283"},"PeriodicalIF":5.8,"publicationDate":"2025-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321475","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":"AI-based estimation of forest plant community composition from UAV imagery","authors":"Lindo Nepi ,&nbsp;Giacomo Quattrini ,&nbsp;Simone Pesaresi ,&nbsp;Adriano Mancini ,&nbsp;Roberto Pierdicca","doi":"10.1016/j.ecoinf.2025.103199","DOIUrl":"10.1016/j.ecoinf.2025.103199","url":null,"abstract":"<div><div>The spatial distribution and abundance of plant species are of critical importance for the identification of plant communities, the assessment of biodiversity, and the fulfilment of environmental policy requirements, such as those outlined in the Habitat Directive 92/43/EEC. Recent advancement in high-resolution drone imaging provides new opportunities for the identification of plant species, offering significant advantages over traditional expert-based methods, which, while accurate, are often time-consuming. This study utilizes deep learning models, namely Vision Transformer (VIT-B16 and VIT-H14) and Convolutional Neural Networks (VGG19 and Resnet101), to quantify the abundance of tree species from RGB images captured by drones in multiple areas of central Italy. The images were segmented into 256 × 256-pixel tiles to enable efficient computational analysis. Following a rigorous training and evaluation process, the ViT-H14 model was identified as the most effective approach, demonstrating an accuracy of over 0.93. The model’s efficacy was substantiated through a comparison with manual analyses conducted by botanical experts, utilising the Mantel Test. This analysis revealed a strong correlation (r =0.87), substantiating the model’s capacity to interpret forest images with a high degree of accuracy. These findings demonstrate the potential of deep learning models, particularly ViT-B16 and VIT-H14, for efficient and scalable ecological monitoring and biodiversity assessments.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103199"},"PeriodicalIF":5.8,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144312588","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":"PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring","authors":"Bingjia Huang ,&nbsp;Yi Wu ,&nbsp;Yihua Lyu ,&nbsp;Xi Yan ,&nbsp;Mengmeng Tong ,&nbsp;Xiaoping Wang","doi":"10.1016/j.ecoinf.2025.103280","DOIUrl":"10.1016/j.ecoinf.2025.103280","url":null,"abstract":"<div><div>Passive acoustic monitoring faces methodological challenges when isolating biological signals from anthropogenically dominated marine soundscapes. To address this, we present two novel computational workflows: (1) a Principal Component Analysis (PCA)-driven noise reduction algorithm that selectively suppresses anthropogenic noise (e.g., vessel sounds) overlapping with biological frequency bands; and (2) an automatic Bio-voice Count Index (BCI) that quantifies target biological sounds through energy thresholding and adjustable frequency-weighting curve. We validated these methods using both synthetic soundscapes and 700 min of field recordings from coral reef ecosystems in Sanya, China. The PCA algorithm improved mean signal-to-noise ratios of field recordings by 5.3 dB (from 7.6 dB to 12.9 dB), effectively enhancing biological sound detectability. The BCI demonstrated strong correlations with biological metrics. When combined with the Acoustic Complexity Index, it improved the accuracy of fish abundance estimation compared to single-index approaches. Critically, our method reduces the analysis time by &gt;90 % compared to manual methods. These tools provide ecologists with a reproducible framework for quantifying biodiversity in noisy environments, directly applicable to coral reef health monitoring and anthropogenic impact assessments.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103280"},"PeriodicalIF":5.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330062","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 synergistic UAV-Landsat novel strategy for enhanced estimation of above-ground biomass and shrub dominance in Sandy land","authors":"Yiran Zhang ,&nbsp;Tingxi Liu ,&nbsp;Asaad Y. Shamseldin ,&nbsp;Xin Tong ,&nbsp;Limin Duan ,&nbsp;Tianyu Jia ,&nbsp;Shuo Lun ,&nbsp;Simin Zhang","doi":"10.1016/j.ecoinf.2025.103282","DOIUrl":"10.1016/j.ecoinf.2025.103282","url":null,"abstract":"<div><div>Accurate estimation of above-ground biomass (AGB) and shrub dominance in sandy lands is crucial for monitoring desertification risk and guiding effective management policies. This study proposed a novel strategy for large-scale AGB estimation in sandy landscapes, focusing on Horqin Sandy Land, by integrating ground reference data with unmanned aerial vehicle (UAV) observations and Landsat 8 OLI imagery. This integration enhanced both the accuracy and efficiency of mapping AGB and shrub dominance. Initially, UAV data were employed to classify shrub and herbaceous vegetation using an object-oriented method, followed by estimating shrub and herbaceous AGB using an allometric growth model (AGM) and partial least squares regression (PLSR). UAV-derived biomass estimates were then aggregated into landscape-scale samples and combined with Landsat imagery to develop Shapley Additive explanation-extreme gradient boosting (SHAP-XGBoost) models for shrub and total AGB. Finally, shrub dominance was mapped as the shrub AGB /total AGB across the region. At the plot scale, AGM coupled with shrub volume provided the highest accuracy for shrub AGB estimation (R² = 0.97, MAE = 176.24 g). Visible-light features from UAV data significantly contributed to herbaceous AGB estimation, achieving a PLSR model accuracy of R² of 0.91 and an MAE of 14.76 g/m². At the landscape scale, the SHAP-XGBoost models demonstrated excellent accuracy, yielding R² values of 0.78 (MAE = 14.96 g/m²) for shrub AGB and 0.83 (MAE = 30.47 g/m²) for total AGB. These high-precision estimation results facilitated the mapping of the shrub dominance.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103282"},"PeriodicalIF":5.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297311","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":"Supporting offshore wind growth: Automating data analysis in digital aerial surveys to enhance wildlife protection and survey efficiency","authors":"Ben Bartlett ,&nbsp;Matheus Santos ,&nbsp;Petar Trslic ,&nbsp;Gerard Dooly","doi":"10.1016/j.ecoinf.2025.103242","DOIUrl":"10.1016/j.ecoinf.2025.103242","url":null,"abstract":"<div><div>With Europe projected to install 260 GW of new wind power between 2024 and 2030, much of it offshore, efficient Environmental Impact Assessments (EIAs) are essential. Regulations require 24 monthly aerial digital surveys before development, with continued monitoring during and after construction. This generates massive volumes of ecological data. We present an automated system that drastically reduces the time required for the most labour-intensive task: screening imagery to identify objects or individuals for further species classification. The process is reduced from several months to the 4-hour survey duration. In a 15-month case study (with one month excluded for testing), the system achieved 97.9 % accuracy, outperforming manual screening (68.75 %), and eliminated 99.13 % of frames from requiring manual review. Avian detection matched manual performance but remained limited by current survey conditions and image resolution. Critically, we found that the commonly assumed 2 cm ground sampling distance (GSD) was inconsistent across survey frames, with no part of any image achieving 2 cm/px, due to camera angles and aircraft configuration. This reduces classification confidence and highlights a need for improved data standards and transparency. As the first study to directly examine these assumptions using raw data, our results demonstrate that survey resolution is insufficient for consistent species identification, and that manual screening may miss up to 30 % of individuals. These findings underscore the importance of questioning inherited data assumptions and improving survey methodologies before such outputs are used to inform policy or conservation action.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103242"},"PeriodicalIF":5.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321467","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":"ArcticSoundsNET: BirdNET embeddings facilitate improved bioacoustic classification of Arctic species","authors":"Morgan A. Ziegenhorn ,&nbsp;Richard B. Lanctot ,&nbsp;Stephen C. Brown ,&nbsp;Miles Brengle ,&nbsp;Shiloh Schulte ,&nbsp;Sarah T. Saalfeld ,&nbsp;Christopher J. Latty ,&nbsp;Paul A. Smith ,&nbsp;Nicolas Lecomte","doi":"10.1016/j.ecoinf.2025.103270","DOIUrl":"10.1016/j.ecoinf.2025.103270","url":null,"abstract":"<div><div>In recent years, deep learning has become a popular solution for processing large ecological monitoring datasets. This rise in use has resulted in global classification models for a variety of data types and taxa, such as BirdNET, which classifies vocalizations of more than 6000 avian species from acoustic data. These global models can be useful pre-trained models for transfer learning, allowing researchers to more easily develop classifiers specialized to their datasets. However, the development of such models hinges on the availability of comprehensive, high-quality training data, which can be difficult to acquire, produce, and use. We present a novel pipeline for creating training data from a large and unlabeled dataset with minimal human oversight. We used this pipeline and BirdNET as our base model to develop a transfer-learning-based model, ArcticSoundsNET, using acoustic monitoring data from 205 sites across Alaska's Arctic Coastal Plain. We compared performance of ArcticSoundsNET with that of BirdNET to evaluate the effectiveness of our pipeline and success of the new model. We found that the ability of ArcticSoundsNET to detect and classify avian vocalizations in our data greatly exceeded that of BirdNET (AUC ROC = 0.888 for ArcticSoundsNET, AUC ROC = 0.593 for BirdNET). Importantly, our method for developing a training dataset is widely applicable for ecologists who do not have large amounts of labeled data, facilitating the creation of task-specific classification models. Developing such models is an essential step in using large acoustic datasets to support ecological conservation of critical species and habitats.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103270"},"PeriodicalIF":5.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288899","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":"Challenges of passive citizen science in ecology within a shifting social media landscape","authors":"Pablo Otero ,&nbsp;Javier Menéndez-Blázquez ,&nbsp;David March","doi":"10.1016/j.ecoinf.2025.103278","DOIUrl":"10.1016/j.ecoinf.2025.103278","url":null,"abstract":"<div><div>Effective conservation relies on comprehensive ecological data, including detailed species occurrences, to track distribution shifts, detect invasive species, and assess wildlife-human interactions. Despite recent technological advancements, environmental and biodiversity monitoring still faces financial and logistical limitations. Passive citizen science, which gathers data from social media platforms, provides a complementary approach that has proven effective in monitoring plants, insects, coral reefs, birds, recreational fishing, or marine pollution, among others. However, the rapid transformation of established social media platforms, the emergence of new distributed networks, and the rise of misinformation are reshaping the social media landscape and casting uncertainty on the future of this method. In this Viewpoint article, we review the current challenges of passive citizen science and call for strengthening this valuable approach for regional solutions that consider linguistic diversity, multiple data sources, fluctuating user engagement, and the integration of artificial intelligence tools for supervising and classifying images and text. At the policy level, a collaborative effort between platform providers and policymakers is essential to democratize research data access.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103278"},"PeriodicalIF":5.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321477","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":"Enhancing sound-based classification of birds and anurans with spectrogram representations and acoustic indices in neural network architectures","authors":"Fábio Felix Dias ,&nbsp;Moacir Antonelli Ponti ,&nbsp;Rosane Minghim","doi":"10.1016/j.ecoinf.2025.103232","DOIUrl":"10.1016/j.ecoinf.2025.103232","url":null,"abstract":"<div><div>Research on habitat monitoring via passive acoustics has generated vast audio resources for soundscape ecology, calling for automated methods to aid data analysis. While Deep Neural Networks excel in classification tasks, their application to audio collected in the wild presents several challenges compared to other audio sources. Nature recordings present ambient noise, sparsity of targeted events, various vocalizations attributed to the same species, and fine-grained sound variance. In addition to sound characterization, we lack annotated datasets of suitable size to train networks accurately for detecting and identifying animal species. To leverage the best from these models, this work investigates different audio input representations, particularly spectrogram-based and acoustic indices, which are pre-processed features extracted from audio sources. We evaluate the impact of combining both input categories, often treated separately, in various architectures, employing quantification in the training process as well as transfer learning. With that, we propose guidelines for using neural networks to classify species based on their sound patterns, even for a small dataset. We have evaluated these guidelines with a dataset collected in Brazil under different environmental conditions and a dataset for detecting and classifying acoustic scenes and events. The empirical results ratify that the pre-trained network learns better (accuracy up to 0.91); that using acoustic features can improve the results marginally (up to 13 percentage points of difference) depending on the time-frequency input and main architecture; and that combining spectrogram representations with acoustic features yields the best results (accuracy up to 0.91).</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103232"},"PeriodicalIF":5.8,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321476","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":"Quantifying ruminal health: A statistical review and application of area and time under the curve in animal science","authors":"Luis O. Tedeschi","doi":"10.1016/j.ecoinf.2025.103271","DOIUrl":"10.1016/j.ecoinf.2025.103271","url":null,"abstract":"<div><div>The concepts of area under the curve (AUC) and time under the curve (TUC), along with their complements area above the curve (AAC) and time above the curve (TAC), provide a powerful statistical framework for quantifying temporal dynamics across various scientific disciplines. These metrics distill complex, time-dependent phenomena into comprehensible values, enabling detailed comparisons of diverse processes. This paper explores the theoretical foundations of these methods and applies them to ruminal pH analysis, a critical indicator of ruminant health, welfare, and productivity. The paper introduces the Area and Time Above and Under the Curve (ATAUC) algorithm, a comprehensive R-based tool designed for analyzing continuous time-series data from multiple sensors. Traditional approaches like the trapezoidal and Simpson's rules are reviewed, alongside advanced methods such as spline interpolation, which better handle irregular data and complex curve behavior. ATAUC integrates robust threshold analysis, smoothing functions for sensor transition, and advanced statistical summaries to ensure accurate and reproducible measurements even in the presence of sampling irregularities or sensor drift. By applying ATAUC to the study of ruminal acidosis, the paper demonstrates the utility of AUC and TUC metrics in capturing the intensity and duration of pH fluctuations relative to critical thresholds. These insights allow researchers and practitioners to evaluate feeding strategies, diagnose metabolic disorders, and optimize animal management practices. AUC-based metrics, supported by the ATAUC algorithm, enable scalable and pragmatic solutions for real-time monitoring and decision-making. This study underscores the relevance of advanced AUC and TUC methodologies for addressing challenges in animal science and beyond. By combining these methods with advancements in data processing, such as machine learning and predictive modeling, the potential for broader applications becomes evident. The findings emphasize that these approaches are not only valuable for quantifying ruminal health but also for understanding and managing complex biological systems across various disciplines. The integration of robust analytical frameworks like ATAUC provides a pathway for improved decision-making, enhanced productivity, and greater welfare in ruminant systems while offering insights applicable to other time-dependent phenomena in science and industry.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103271"},"PeriodicalIF":5.8,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297197","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":"Balancing signature variance between local and global minima/maxima: Restricted maximum likelihood (REML) classification and the search for plagioclimax","authors":"N. Manspeizer ,&nbsp;A. Karnieli","doi":"10.1016/j.ecoinf.2025.103273","DOIUrl":"10.1016/j.ecoinf.2025.103273","url":null,"abstract":"<div><div>Due to long-term anthropogenic disturbance, plagioclimax results in vegetation compositions that cannot develop to a climax state. The overarching goal of the study was to develop a method to identify plagioclimax sub-regionally in the eastern Mediterranean (Israel) through signature extension. A case study was established in the Carob-Mastic (<em>typicum judaicum</em>) vegetation sub-association, demonstrating plagioclimax in both a southern, moderately affected stand and a northern, heavily impacted one. Training sets for supervised classification were constructed in the southern stand from an existing 1 m land cover classification with global and local class sets. Signature extension was employed to identify the plagioclimax in the northern stand using 30 m Landsat-9 data. The specific objectives were twofold: (1) to construct a mixture modeling technique that enabled fusing the 1 m and 30 m data sets; (2) to devise a classification method by which the complex segmentation of the plagioclimax, as an interstitial garrigue between phanerophyte shrub matrices, could be identified. An experimental method was devised in which five levels of density-restricted training sets, based on minimum pixels per patch, were built from the patch spatial structures of shrub community-related classes. Patch ecology metrics were derived directly from the restriction levels to develop an understanding of the landscape mosaic. Entropy (a measure of disorder) and emptiness (a proxy for fragmentation) measures were designed into bin tables and examined relative to the variance in the spectral signatures. A restricted maximum likelihood (REML) classifier that relies on limiting variance was chosen to identify local maximum clusters (the unique plagioclimax classes), and the five classification results were compared. The results were successful in identifying the plagioclimax at the local maximum. This strategy is appropriate for cases where disturbance has caused continuous ensembles of vegetation compositions, which result in unstructured remotely sensed data.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"90 ","pages":"Article 103273"},"PeriodicalIF":5.8,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365541","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}