Ecological Informatics最新文献

{"title":"A Monte Carlo-augmented geographical random forest approach for spatial biodiversity modeling: managing bird communities in small urban wetlands","authors":"Weifeng Xiao ,&nbsp;Yifan Xu ,&nbsp;Yuanzhi Shi ,&nbsp;Shaohua Lei","doi":"10.1016/j.ecoinf.2026.103631","DOIUrl":"10.1016/j.ecoinf.2026.103631","url":null,"abstract":"<div><div>Small urban wetlands face intensifying pressures from rapid urbanization, yet their biodiversity patterns remain underexplored due to data scarcity and spatial complexity. We established a Monte Carlo-augmented geographical random forest (GRF) framework to model avian diversity across 45 small wetlands in Hefei, China, documenting 102 bird species (31 waterbirds, 71 terrestrial) along urban-suburban gradients. This methodology addresses concurrent challenges of limited sample sizes and spatial heterogeneity by integrating Monte Carlo simulation with spatially explicit machine learning. The GRF model demonstrated superior performance over conventional approaches, reducing RMSE from 15.234 (ordinary least squares, OLS) to 2.863 while achieving R² = 0.854 for waterbird species richness compared to R² = 0.765 for the standard random forest. Monte Carlo simulations stabilized after 100 iterations for waterbird richness and 150 for density metrics. Critical ecological thresholds were identified: Waterbird richness peaked at wetland sizes of 2 ha then declined, while construction intensity exceeding 40% caused a 75% reduction in waterbird diversity (from ∼80 to ∼20 species). Terrestrial birds exhibited consistent positive responses to wetland area, with this factor dominating in 86.67% of sites for both richness and density. Spatial analysis revealed distinct urban gradient patterns—The urbanization index influenced waterbird richness in 35.56% of wetlands primarily located in urban cores, whereas vegetation cover affected terrestrial birds in 28.89% of sites mainly situated in peripheral areas. Factor synergies were strongest in low-quality waterbird habitats (+80.2% above expected richness) and high-quality terrestrial sites (+30.4%), indicating disproportionate conservation benefits from coordinated management strategies. These findings provide quantitative guidelines for urban wetland design: Networks of 1.5–3-ha wetlands optimized for waterbirds, larger refugia (&gt;5 ha) for terrestrial species, and construction intensity limits below 30% within 500 m buffers. This methodological framework offers a transferable approach for biodiversity modeling in data-limited urban systems while establishing actionable targets for wetland conservation planning.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103631"},"PeriodicalIF":7.3,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174414","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":"Filling the gap: Improving the spatio-temporal coverage of small pelagic fish surveys through modelling approaches","authors":"Stefanie Haase ,&nbsp;Clarissa Vock ,&nbsp;Beata Schmidt ,&nbsp;Ismael Núñez-Riboni ,&nbsp;Stefan Lüdtke","doi":"10.1016/j.ecoinf.2026.103634","DOIUrl":"10.1016/j.ecoinf.2026.103634","url":null,"abstract":"<div><div>Abundance indices from fisheries-independent surveys provide key information for fish stock assessments, serving as a foundation for sustainable resource management. Changes in survey effort, e.g., caused by vessel breakdowns or bad weather conditions, can lead to areas not being covered in certain years. These spatio-temporal gaps in survey coverage increase uncertainty or can even lead to discontinuation in time series. The current approach for imputing missing strata in Baltic pelagic clupeid surveys uses area-corrected abundances from higher-level subdivision units (baseline model), which does not account for stratum-specific effects and requires at least partial subdivision coverage. We tested three alternative imputation methods: Linear mixed-effects models (LMMs), Generalized additive models (GAMs), and Gradient boosted trees (XGB). Our results suggest that modelling abundance variations across strata, as implemented in the LMMs, improved abundance estimates compared to the baseline model, particularly when only few areas were not covered, i.e., under typical annual variations in survey coverage. When larger areas were not covered, LMMs, relying on explicit spatial strata, performed worse, whereas the XGB models and, in particular, the spatial GAM remained robust and could still be applied even when entire subdivisions were not surveyed. In conclusion, advanced data imputation techniques can enhance the robustness of abundance indices and should be considered as standard practice in survey groups when survey effort varies between years.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103634"},"PeriodicalIF":7.3,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174000","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":"Remote sensing monitoring of cropland abandonment at the parcel level based on time-series fitting of cultivation probability values","authors":"Xinyu Yang ,&nbsp;Yufeng Liu ,&nbsp;Hu Li ,&nbsp;Ji Ma ,&nbsp;Zhicheng Ye","doi":"10.1016/j.ecoinf.2026.103632","DOIUrl":"10.1016/j.ecoinf.2026.103632","url":null,"abstract":"<div><div>Abandoned cropland is a critical component of agricultural land-use change, with notable implications for food production and the ecological sustainability. This study proposes an integrated monitoring framework, termed OBIA–LT, to address the temporal complexity and spatial fragmentation of abandoned cropland. Cultivation probability is constructed as a time series and analyzed through LandTrendr segmentation fitting. The use of land parcels as analysis units suppresses pixel-level noise, enabling precise identification of the timing and dynamics of abandoned cropland. The Jianghuai hilly region was selected as the study area, and multi-temporal remote sensing imagery and field samples were used for analysis. Results indicate that abandoned cropland exhibits pronounced spatial clustering, with high-density concentrations in the central and western hilly areas and a scattered distribution in the southern plains. The timing of abandonment shows seasonal patterns, occurring predominantly in spring and winter. Long-term continuous abandonment is rare, with more than half the parcels abandoned for only a single quarter, demonstrating the sensitivity of the OBIA–LT framework to short-term cultivation gaps at a monthly scale. This study confirms the effectiveness of the method in achieving high accuracy and spatiotemporal consistency and provides a valuable reference for large-scale monitoring of abandoned cropland dynamics.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103632"},"PeriodicalIF":7.3,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173891","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":"What AIS misses and Acoustics reveal: Monitoring seafloor disturbance and recovery from bottom trawling in the southern Baltic Sea over five years","authors":"Mischa Schönke ,&nbsp;Inken Schulze ,&nbsp;Mayya Gogina ,&nbsp;Christian von Dorrien ,&nbsp;Daniel Oesterwind ,&nbsp;Peter Feldens","doi":"10.1016/j.ecoinf.2026.103638","DOIUrl":"10.1016/j.ecoinf.2026.103638","url":null,"abstract":"<div><div>This study evaluates bottom trawling intensity and its ecological effects in the Fehmarn Belt (southern Baltic Sea) between 2020 and 2024. The region is dominated by small-scale fishing vessels (<span><math><mo>&lt;</mo></math></span>12 m length) and therefore conventional Vessel Monitoring System (VMS) data are unavailable. We compare changes in seafloor integrity caused by bottom trawling with fishing activity inferred from Automatic Identification System (AIS) tracking. Trawling intensity was quantified using a previously developed trawling index (TI) based on furrow volume derived from multibeam echosounder (MBES) data. A pronounced alteration in seafloor integrity was observed between 2021 and 2022, with furrow volumes decreasing from 5067 m³ to 1108 m³ over an area of 3.4 km². This trend was not recorded by AIS-derived fishing activity, which showed only slight changes in vessel track counts. Spatial and temporal fluctuations in abundance, biomass and community structure were revealed through repeated macrofauna sampling. The fluctuations are likely linked to shifting trawling pressure related to the ban of a fishery targeting cod in the Western Baltic. These biological responses did not follow a linear trend but suggest a dynamic equilibrium may be reached over time. Although MBES data cannot replace AIS for tracking fishing effort, it can supplement and improve the AIS information, providing insights into physical impacts and benthic responses in regions of interest. Integrating MBES-derived indicators identifies the spatial extent of the seabed affected by bottom trawling, thereby strengthening ecological monitoring frameworks and supporting sustainable seabed management, including in marine spatial planning.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103638"},"PeriodicalIF":7.3,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174422","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":"Prediction of stand-level growing stock by using a spatial regression model in an Austrian protection forest","authors":"Valentin Sarkleti,&nbsp;Tobias Ofner-Graff,&nbsp;Andreas Tockner,&nbsp;Sarah Witzmann,&nbsp;Ralf Kassnitzer,&nbsp;Christoph Gollob,&nbsp;Tim Ritter,&nbsp;Arne Nothdurft","doi":"10.1016/j.ecoinf.2026.103641","DOIUrl":"10.1016/j.ecoinf.2026.103641","url":null,"abstract":"<div><div>A digital forest inventory is proposed to estimate growing stock in a mountainous protection forest near Ebensee, Austria. As protection forests cover 42% of Austria's forest area and safeguard against natural hazards, continuous monitoring is essential but challenging due to steep terrain and coarse sampling in the Austrian National Forest Inventory. This study proposes a monitoring system combining airborne laser scanning and ground-based personal laser scanning (PLS). ALS data supplement spatial regression models that interpolate inventory data collected on 273 sample plots via PLS. Spatially varying intercept and coefficient models were developed to predict growing stock at both total and stand levels within the 4898-ha Ebensee forest district. Models were fitted under a Bayesian framework using Markov Chain Monte Carlo (MCMC) methods. Compared to non-spatial modeling, this spatial approach significantly improves precision; compared to traditional design-based inventories, it enables high-resolution stand-level estimates and reduces fieldwork and costs. Model performance was evaluated via leave-one-out cross-validation, yielding a root mean squared error of 89.0 m³/ha and a bias of 0.392 m³/ha. This study highlights the efficiency of integrating ALS, PLS, and spatial models in forest inventory, supporting both ecological and economic assessments.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103641"},"PeriodicalIF":7.3,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174413","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":"Context-dependent relationships between street-level surface heat intensity, the sky view factor, and landscape patterns: Examples from the coastal city of Vancouver, Canada","authors":"Baifei Ren,&nbsp;Luke Bergmann","doi":"10.1016/j.ecoinf.2026.103637","DOIUrl":"10.1016/j.ecoinf.2026.103637","url":null,"abstract":"<div><div>With climate change, some coastal urban regions once characterized by mild oceanic climates, are becoming increasingly hot in the summer. Urban design can modify urban landscapes to mitigate the Urban Heat Island (UHI) effect, but many strategies are constrained in high-density urban centers where large-scale layouts are difficult to alter. Yet noting that streets are among the more modifiable public spaces in high-density urban areas, this paper examines how relationships between street-level Sky View Factors (SVF), other indicators of urban morphology, and UHI are interconnected in different parts of a mid-latitude coastal urban area, Metro Vancouver. This study found an expected positive correlation coefficient of 0.484 (<em>p</em> &lt; 0.05) between SVF and UHI intensity before considering other variables and spatial context. In areas that are equally distant from water bodies, have similar forest cover near streets, and possess comparable urban patch sizes, a 0.2 decrease in SVF (which ranges from 0 to 1) corresponds to a reduction of 0.08 °C–0.15 °C in urban heat island intensity (measured in ∆LST). Yet when supplementing aspatial OLS regression with geographically weighted regression (GWR), the study is able to identify how a number of commonly understood individual relationships between SVF, urban morphology, and UHI are actually substantially and consequentially variable in effect and significance depending on geographical context. In areas closer to the coast, SVF's effects on UHI are not significant, but with increasing distance to the sea, SVF has significant and greater influence on UHI intensity. Additionally, scale matters–water has a weak negative correlation (−0.291) with UHI intensity at a more granular 150 m scale but moderate negative correlation (0.463) at the coarser scale of 900 m gridded data; forest cover provides stronger heat island mitigation at small scales (0.73 at 150 m; while 0.62 at 900 m). The study illustrates how methods attentive to geographical context and spatial interactions can serve as the basis for more locally appropriate planning recommendations as well as for more robust generalizations about what can cause and mitigate UHI. Our findings suggest creating more street shading and promoting accessibility to heat sinks, especially in urban areas farther from the coast, while also offering guidance on integrating societal contexts more directly into UHI research as concerns about climate inequalities grow.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103637"},"PeriodicalIF":7.3,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174003","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":"Real-time hyperspectral decision support for precision herbicide management in Maize: Optimizing herbicide efficacy and plant response","authors":"Sk Asraful Ali ,&nbsp;Ramanjit Kaur ,&nbsp;Sudhir Kumar ,&nbsp;Allimuthu Elangovan ,&nbsp;Rahul Kumar ,&nbsp;Arjun Shreepad Hegde ,&nbsp;Rashmi Sharma ,&nbsp;Yogeshwar Singh ,&nbsp;Shiv Vendra Singh","doi":"10.1016/j.ecoinf.2026.103642","DOIUrl":"10.1016/j.ecoinf.2026.103642","url":null,"abstract":"<div><div>Hyperspectral VNIR imaging (400–1000 nm) offers a swift, non-invasive method for identifying early herbicide-induced stress in maize and its accompanying weed flora. Unlike traditional visual scoring and biomass measurements, this technology captures subtle changes in pigment content, water status, and canopy structure with high precision and accuracy. The present study employed hyperspectral vegetation indices and multivariate analysis to identify spectral responses to sequential pre- and post-emergence herbicide combinations, measure the dynamics of chlorophyll, carotenoid, and anthocyanin-related pigments under herbicide stress, and differentiate treatment efficacy patterns to enhance precision weed management. Hyperspectral reflectance data collected before and after herbicide application were used to calculate indices, including NDVI, CIgreen, CIred-edge, NPQI, CRI1, CRI2, ARI1, and ARI2. This was shown by a drop in CIred-edge (26.2%) and CIgreen (8.8%), and a considerable increase in NPQI (+68.4%), CRI2 (+63.4%), and ARI1 (+824.1%) within four days of application, indicating that pigments break down quickly and weed species are sensitive. In contrast, combinations based on halosulfuron methyl showed very little spectral divergence and mostly resembled the weedy check because <em>Cyperus</em> spp., the main target of the herbicide, was not present. Principal Component Analysis showed that the first two components explained 78.5% of the total variance (PC1:56.9%; PC2:21.6%), successfully distinguished tembotrione-based combinations from other regimens, whereas hierarchical clustering categorised treatments based on their temporal spectral response patterns. These results show that hyperspectral imaging and multivariate analysis can provide an objective and early indication of herbicide efficacy. This study presents a real-time decision-support framework that improves precision herbicide management, reduces dependence on subjective evaluations, and fosters more sustainable maize production methodologies.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103642"},"PeriodicalIF":7.3,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174424","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":"Functional trait reorganization buffers the negative effects of grazing on plant species turnover in alpine grasslands","authors":"Wenting Liu ,&nbsp;Yuzhen Liu ,&nbsp;Yang Yu ,&nbsp;Xiaoxia Yang ,&nbsp;Chunping Zhang ,&nbsp;Quanmin Dong","doi":"10.1016/j.ecoinf.2026.103630","DOIUrl":"10.1016/j.ecoinf.2026.103630","url":null,"abstract":"<div><div>Livestock grazing is the most pervasive biological filter in global grasslands and is central to local livelihoods. A trait-based perspective is crucial for understanding plant strategies and species turnover under grazing pressure, yet current theories struggle to reconcile species turnover with often weak changes in functional diversity. Moreover, little attention has been given to the distinct filtering roles of different herbivores and their influence on trait coordination. We conducted a controlled grazing experiment in the alpine meadows of the northeastern Qinghai–Tibetan Plateau, in which moderate grazing with yaks, Tibetan sheep, and their combination was applied. We assessed how these grazing assemblages shaped community-weighted mean traits (CWMs), functional trait networks, and functional diversity and how such changes mediated species turnover. Livestock types exerted contrasting filtering effects on the CWMs. Grazing consistently reduced reproductive branch height, with the smallest decrease occurring under yak–sheep mixed grazing. Sheep alone and sheep-dominated grazing resulted in the greatest increase in vegetative and reproductive branch weights, revealing adaptive strategies that coupled reduced stature with compensatory biomass allocation. Grazing also reshaped trait networks, enhancing integration and coordination while leaving functional richness largely unchanged. Structural equation modeling revealed that grazing strongly negatively affected species turnover, which was partly offset by grazing-induced shifts in CWMs. Our findings establish a multilevel framework that links traits, diversity, networks, and species turnover under grazing. We show that plant communities respond primarily through trait coordination and CWM restructuring rather than functional diversity loss, offering new insights for biodiversity conservation and sustainable management of alpine grasslands.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103630"},"PeriodicalIF":7.3,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173897","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":"Benchmarking remote sensing methods to capture plant functional diversity from space","authors":"Javier Pacheco-Labrador ,&nbsp;Ulisse Gomarasca ,&nbsp;Daniel E. Pabon-Moreno ,&nbsp;Wantong Li ,&nbsp;Mirco Migliavacca ,&nbsp;Martin Jung ,&nbsp;Gregory Duveiller","doi":"10.1016/j.ecoinf.2026.103636","DOIUrl":"10.1016/j.ecoinf.2026.103636","url":null,"abstract":"<div><div>The development of remote sensing methods to estimate plant functional diversity is hindered by mismatches between ecology and remote sensing sampling schemes and the limited representativeness of local field campaigns. The Biodiversity Observing System Simulation Experiment (BOSSE) provides a modeling framework for benchmarking new methodologies. We used BOSSE to simulate 180 different synthetic “Scenes” spanning a two-year-long time series of plant trait maps and imagery of hyperspectral reflectance factors, spectral indices, sun-induced chlorophyll fluorescence, land surface temperature, and estimates of foliar and structural plant traits (optical traits). We used these simulations to answer five fundamental, yet unsolved, questions:</div><div><em>Q1. How should remote sensing characterize functional diversity in large surfaces (sites)?</em> Diversity metric values saturate with the number of pixels involved, hampering comparisons between plant traits and remote sensing estimates in large areas. The average value of metrics computed over small samples (e.g., 3-by-3 pixel windows) should be used instead.</div><div><em>Q2. Which sources of spectral information (or combinations thereof) can best capture plant functional diversity at the site scale?</em> Accounting for background effects is the key. Optical traits are the best estimators for plant functional diversity. Other variables succeed when allowed to remove soil pixels, but their combination did not yield significant advantages.</div><div><em>Q3. How should remote sensing estimates be validated/compared with plant functional diversity measurements?</em> Leaf area index (LAI) is a better proxy of abundance than the pixel for <em>Q</em>_Rao, but not for variance-based partitioning. It is more sensitive to sample size, but also more resistant to suboptimal spatial resolution.</div><div><em>Q4. When (in the phenological year) can remote sensing best capture site-scale plant functional diversity?</em> The estimation error decreased with LAI and stabilized at values above 1 m²/m².</div><div><em>Q5. Which approaches and remote sensing variables are more resistant to the effects of suboptimal spatial resolution?</em> Optical traits and fluorescence were the most robust variables. Still, field data resolution needs to be degraded to match the sensor's resolution. We found a relative spatial resolution threshold of ∼30% (where the pixel is approximately three times the size of the plants).</div><div>Simulation frameworks like BOSSE enable testing methodologies beyond local contexts and address the current shortage of suitable global datasets, supporting the application and development of methods for assessing plant functional diversity with remote sensing. In the future, BOSSE could contribute to understanding observational results, refining and pre-testing new methodologies, and supporting the development of comparable experimental datasets.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103636"},"PeriodicalIF":7.3,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174423","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 conceptual architecture for AI-assisted Digital Twins in natural resource management","authors":"Félix Iglesias ,&nbsp;Frédéric Ros ,&nbsp;Lynh Hoang Vy Thuy ,&nbsp;Laurence Gourcy ,&nbsp;Jean-Sébastien Moquet ,&nbsp;Véronique Daële ,&nbsp;Sébastien Dupraz","doi":"10.1016/j.ecoinf.2026.103635","DOIUrl":"10.1016/j.ecoinf.2026.103635","url":null,"abstract":"<div><div>The management of natural resources is increasingly critical and challenging due to complex interactions among environmental, industrial, and societal processes. Traditional approaches often fail to integrate heterogeneous data, limiting predictive and decision-support capabilities. This study presents a conceptual architecture for an Artificial Intelligence (AI)-assisted Digital Twin (DT) of the Centre-Val de Loire region, designed to unify time-dependent multi-source data. Based on the ENVRI Reference Model, it covers Science, Information, Computational, Engineering, and Technology layers, defining standardized data exchange, communication protocols, and prototype functionalities. A proof of concept FIWARE implementation supports ingestion, monitoring and analytical services for piezometric and meteorological data, exemplified through groundwater dynamics in the Beauce aquifer. It integrates daily observations from 53 piezometric stations over more than five years, managing approximately 2.8 million records in a containerized environment.</div><div>Results show that the proposed DT architecture can enhance sustainability-oriented decision making, integrating heterogeneous data and predictive analyses while enabling collaboration across scientific and technical domains. Its modular design offers a replicable template for future AI-assisted environmental DTs, scalable to larger regions. Hence, this work illustrates how DTs can improve environmental monitoring and understanding, providing a pathway toward resilient, data-driven management of natural resources.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"94 ","pages":"Article 103635"},"PeriodicalIF":7.3,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080074","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}