Ecological Informatics最新文献

{"title":"Assessing urban vegetation inequalities: Methodological insights and evidence","authors":"Alicia González-Marín,&nbsp;Marco Garrido-Cumbrera","doi":"10.1016/j.ecoinf.2024.102987","DOIUrl":"10.1016/j.ecoinf.2024.102987","url":null,"abstract":"<div><div>Vegetation indixes have become increasingly popular in analyzing urban inequalities in access to and use of green spaces. However, the methodologies employed have been heterogeneous, leading to inconclusive or contradictory results. This study aims to conduct a scoping literature review of research that evaluates methodologies used to estimate the inequal distribution of vegetation in cities, providing evidence to establish standardized guidelines for the selection of data sources, methodologies and indicators. The review includes 66 articles published between 2004 and 2023 from various global regions. We identified 10 vegetation indixes, with the Normalized Difference Vegetation Index (NDVI) being the most frequently used, typically derived from Landsat satellite data. The review highlights the importance of image acquisition times and temporal resolution in capturing dynamic urban environments. The spatial scale most adopted is the census block group, suitable for assessing urban inequalities. We observed substantial heterogeneity in the methodologies and statistical tools employed, with spatial autocorrelation analysis being the most common, followed by Pearson's and Spearman's correlation coefficients. ArcGIS was the most widely used GIS platform, closely followed by the cloud-based geospatial analysis platform Google Earth Engine, while R-Studio and Statistical Package for the Social Sciences (SPSS) were popular for statistical analysis. This study underscores the need for standardized methodologies to enhance the comparability and reliability of research on urban vegetation inequalities.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 102987"},"PeriodicalIF":5.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350553","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":"Identification and characterization of long-term meteorological drought events in the Yellow River Basin","authors":"Jiepeng Li ,&nbsp;Lajiao Chen ,&nbsp;Geli Zhang ,&nbsp;Hui Liu ,&nbsp;Hongchang Hu ,&nbsp;Mengzhen Xu ,&nbsp;Xingyan Guo ,&nbsp;Zibo Meng ,&nbsp;Zhiqiang Dong","doi":"10.1016/j.ecoinf.2025.102992","DOIUrl":"10.1016/j.ecoinf.2025.102992","url":null,"abstract":"<div><div>The Yellow River Basin (YRB) is one of the regions most severely affected by droughts in China. Understanding spatiotemporal variations in droughts in the YRB has become a research hotspot. Despite the attention being paid to droughts in the YRB, most studies have identified drought events separately in terms of space and time. Such simplified methods cannot accurately describe the spatiotemporal structure of droughts or analyze their occurrence patterns. Therefore, this study used a three-dimensional drought identification method to extract meteorological drought events in the YRB from 1901 to 2022 based on their spatiotemporal structure. Drought duration, area, and severity were used to characterize meteorological drought events. Copula functions were used for multivariate frequency analysis of droughts and for calculating return periods. The results indicated that the drought events identified in this study aligned well with the recorded historical drought events. Droughts in the YRB are frequent and periodic, with high-severity droughts covering the entire basin during major events. The most severe drought occurred between February 1962 and April 1963. Drought evolution patterns exhibited high spatiotemporal heterogeneity. The center of the YRB, including Ningxia, Gansu, and Shaanxi, is the region most severely affected by drought, with high-severity droughts and a high frequency of droughts. Droughts are relatively more common during summer and autumn in the YRB. Over an extended period, the drought center in the YRB exhibited a clear migration trajectory, with the risk of meteorological droughts showing a noticeably declining trend after 2000. The findings of this study provide a scientific basis for ecological conservation and sustainable development of the YRB.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 102992"},"PeriodicalIF":5.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101601","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":"Comparative analysis of Sentinel-2 and PlanetScope imagery for chlorophyll-a prediction using machine learning models","authors":"Eden T. Wasehun ,&nbsp;Leila Hashemi Beni ,&nbsp;Courtney A. Di Vittorio ,&nbsp;Christopher M. Zarzar ,&nbsp;Kyana R.L. Young","doi":"10.1016/j.ecoinf.2024.102988","DOIUrl":"10.1016/j.ecoinf.2024.102988","url":null,"abstract":"<div><div>The application of high spatial resolution remote sensing technology enables the detailed capture of information from water bodies for water quality assessment. In this study, we compare two satellite remote sensing data on water quality assessment, focusing on chlorophyll-a (Chl-a) due to its importance in monitoring eutrophication and algal boom potential. We developed three scenarios to select key features, aiming to optimize the retrieval of Chl-a for a lake in North Carolina, USA. Utilizing five machine learning models, namely linear regression (LR), least absolute shrinkage and selection operator (LASSO), extreme gradient boosting (XGBoost), random forest (RF), and support vector regression (SVR), we constructed inversion models. The results revealed that the XGBoost model exhibited the highest prediction capacity for Chl-a concentration retrieval using Sentinel-2 (S2) data (R² = 0.64, RMSE = 8.58 micrograms per liter (μg/l), bias = −0.09). On the other hand, the SVR model demonstrated better predictive performance for Chl-a concentration retrieval using PlanetScope (PS) data (R² = 0.71, RMSE = 8.15 μg/l, bias = 0.46). Consequently, spatiotemporal maps of Chl-a concentration across the reservoir were generated using the best-performing machine learning models: XGBoost for S2 data and SVR for PS data. These maps were created to visualize the distribution and variation of Chl-a concentrations over time and space. This study contributes valuable insights into the difference between two satellite sensors with varying spatial resolution in assessing inland water quality and offers a comparative analysis of multiple inversion methods. The outcomes of our research provide guidance for enhancing inland water quality monitoring practices on small water bodies, emphasizing the importance of selecting optimal inversion models based on satellite data sources. The findings contribute to advancing our understanding of the complexities associated with remote sensing technologies and their applications in water quality assessments, ultimately facilitating improved monitoring and management strategies for small inland water bodies.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102988"},"PeriodicalIF":5.8,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137525","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":"Centroid-AME: An open-source software for estimating avian migration trajectories using population centroids movement in the annual cycle","authors":"Shi Feng ,&nbsp;Alice C. Hughes ,&nbsp;Qinmin Yang ,&nbsp;Leyi Li ,&nbsp;Chao Li","doi":"10.1016/j.ecoinf.2024.102983","DOIUrl":"10.1016/j.ecoinf.2024.102983","url":null,"abstract":"<div><div>Migration is a critical aspect of many birds' annual life cycles, with up to 40 % of bird species engaging in migratory behavior. However, understanding the migration dynamics, particularly in small birds, presents challenges due to both financial and physical constraints. The growth of citizen science observation databases is creating unique opportunities to estimate avian migration trajectories at the population level, across species and without the need for expensive additional data. Centroid-AME is a Python-based tool designed to estimate avian migration trajectories using the spatiotemporal locations of population centroids. In this paper, we propose a general framework for trajectory estimation, and explore the practicality of Centroid-AME as a tool for analyzing observation data at the population level. Our approach consists of three core components: data preprocessing, migration trajectory estimation, and the computation of dynamic indicators within the annual cycle. To address the inherent spatial and temporal biases of observations, the preprocessing steps include the interpolation of missing values, the application of sliding window, and the detection of outliers, which will address gaps and errors. We apply an unsupervised Mean-Shift clustering algorithm to extract dense clusters of observations and identify subgroups of the species population. The centroids are then grouped using a shortest path with the lowest cost and migration trajectories are estimated by fitting them respectively. Finally, we compute three key metrics to assess population-level migration dynamics: migration speed, migration offset distance, and population centroids distribution. The information provided by these metrics complements traditional individual-level assessments, enhancing our understanding of the migration process. To verify the feasibility of our estimation framework, we apply it to the observation data of Spragues' pipit (<em>Anthus spragueii</em>, Audubon) from eBird, and analyze its moving dynamics during the migration cycle as a case study.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102983"},"PeriodicalIF":5.8,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137586","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":"Bayesian calibration and uncertainty quantification for a large nutrient load impact model","authors":"Karel Kaurila ,&nbsp;Risto Lignell ,&nbsp;Frede Thingstad ,&nbsp;Harri Kuosa ,&nbsp;Jarno Vanhatalo","doi":"10.1016/j.ecoinf.2024.102976","DOIUrl":"10.1016/j.ecoinf.2024.102976","url":null,"abstract":"<div><div>Nutrient load simulators are large, deterministic, models that simulate the hydrodynamics and biogeochemical processes in aquatic ecosystems. They are central tools for planning cost-efficient actions to fight eutrophication since they allow scenario predictions on impacts of nutrient load reductions to, e.g., harmful algal biomass growth. Due to being computationally heavy, the uncertainties related to these predictions are typically not rigorously assessed though. In this work, we developed a novel Bayesian computational approach for estimating the uncertainties in predictions of the Finnish coastal nutrient load model FICOS. First, we constructed a likelihood function for the multivariate spatio-temporal outputs of the FICOS model. Then, we used Bayesian optimization to locate the posterior mode for the model parameters conditional on long term monitoring data. After that, we constructed a space-filling design for FICOS model runs around the posterior mode and used it to train a Gaussian process emulator for the (log) posterior density of the model parameters. We then integrated over this (approximate) parameter posterior to produce probabilistic predictions for algal biomass and chlorophyll <span><math><mi>a</mi></math></span> concentration under alternative nutrient load reduction scenarios. Our computational algorithm allowed for fast posterior inference and the Gaussian process emulator had good predictive accuracy within the highest posterior probability mass region. The posterior predictive scenarios showed that the probability to reach the EU’s Water Framework Directive objectives in the Finnish Archipelago Sea is generally low even under large load reductions.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102976"},"PeriodicalIF":5.8,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137584","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":"Spatiotemporal analysis of surface Urban Heat Island intensity and the role of vegetation in six major Pakistani cities","authors":"Shoaib Ahmad Anees ,&nbsp;Kaleem Mehmood ,&nbsp;Syed Imran Haider Raza ,&nbsp;Sebastian Pfautsch ,&nbsp;Munawar Shah ,&nbsp;Punyawi Jamjareegulgarn ,&nbsp;Fahad Shahzad ,&nbsp;Abdullah A. Alarfaj ,&nbsp;Sulaiman Ali Alharbi ,&nbsp;Waseem Razzaq Khan ,&nbsp;Timothy Dube","doi":"10.1016/j.ecoinf.2024.102986","DOIUrl":"10.1016/j.ecoinf.2024.102986","url":null,"abstract":"<div><div>The Urban Heat Island (UHI) phenomenon exacerbates thermal discomfort in urban areas and significantly contributes to urban overheating when combined with climate change. This study investigates the spatiotemporal patterns of Surface Urban Heat Island Intensity (SUHII) in six major cities of Pakistan, focusing on the interplay between urban expansion, vegetation cover, and SUHII. To quantify SUHII dynamics, the impact of urban sprawl and vegetation changes was analyzed. The study offers critical insights into the implications for urban planning and policymaking in Pakistan. Using remote sensing data from Landsat satellites, analyzed with Geographic Information Systems (GIS) techniques, estimates of SUHII, urban expansion, and vegetation cover were derived. Specifically, imagery from Landsat-5 (2010−2013) and Landsat-8 (2014–2022), obtained from the US Geological Survey (USGS), was employed. Statistical analyses, including Pearson's correlation and linear regression, were conducted to assess relationships between these variables from 2010 to 2022. <strong>SUHII</strong> was found to increase annually by 0.18 °C in Islamabad and 0.19 °C in Peshawar, with corresponding urban expansion rates of 8.07 km² (8967.75 pixels) and 1.67 km² (1860.42 pixels) per year, respectively. Vegetation indices such as the Normalized Difference Vegetation Index (NDVI) and Fractional Vegetation Cover (FVC) were inversely correlated with SUHII, explaining up to 50 % of the variance in Peshawar. However, weaker correlations in Lahore suggest the presence of additional factors influencing <strong>SUHII</strong>. A distinct spatial relationship between increased vegetation and cooler areas was observed. For instance, Islamabad has greater vegetation cover and cool zones over 41.5 km². In contrast, Lahore's hot spots spanned 127.1 km², compared to Abbottabad's 10.4 km², underscoring the thermal impact of reduced vegetation. The findings emphasize the effectiveness of urban greening, particularly in Islamabad's neutral thermal regions, in mitigating <strong>SUHII</strong>. This study offers important insights for urban planners in developing sustainable, climate-resilient cities within similar urban contexts. While the results are specific to Pakistani cities, the role of vegetation in mitigating <strong>SUHII</strong> may hold broader relevance for urban planning strategies in comparable settings.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102986"},"PeriodicalIF":5.8,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137491","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":"Hierarchical deep learning framework for automated marine vegetation and fauna analysis using ROV video data","authors":"Bjørn Christian Weinbach ,&nbsp;Rajendra Akerkar ,&nbsp;Marianne Nilsen ,&nbsp;Reza Arghandeh","doi":"10.1016/j.ecoinf.2024.102966","DOIUrl":"10.1016/j.ecoinf.2024.102966","url":null,"abstract":"<div><div>The integration of deep learning with Remotely Operated Vehicles (ROVs) has advanced scalable, detailed marine biodiversity monitoring. This study presents the Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) and FjordVision, a framework designed for automated analysis of marine vegetation and fauna in natural habitats. FjordVision combines state-of-the-art object detection, iterative dataset refinement, and a taxonomy-aware hierarchical reclassification framework that enhances accuracy across four taxonomic levels: binary, class, genus, and species. Although YOLOv8 was initially employed for instance segmentation, results showed Mask R-CNN to be more effective across hierarchical levels. FjordVision’s hierarchical classification supports marine biodiversity assessments, offering critical insights for conservation applications in fjord ecosystems.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102966"},"PeriodicalIF":5.8,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137565","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":"Spatial mismatch and congruence in the taxonomic, functional, and phylogenetic diversities of fish assemblages in China's water diversion lakes","authors":"Zhice Liang ,&nbsp;Rodolphe Elie Gozlan ,&nbsp;Chenyi Kuang ,&nbsp;Jiashou Liu ,&nbsp;Chuanbo Guo","doi":"10.1016/j.ecoinf.2024.102985","DOIUrl":"10.1016/j.ecoinf.2024.102985","url":null,"abstract":"<div><div>The interplay of evolutionary, ecological, and anthropogenic processes is critical in shaping species distributions and biodiversity patterns. Recent studies highlight the importance of examining functional and phylogenetic traits to gain a more comprehensive understanding of these patterns. However, significant knowledge gaps remain regarding functional and phylogenetic diversity patterns among freshwater fish, particularly in the context of large-scale hydrological alterations such as the South-to-North Water Diversion Project (SNWDP). In this study, we investigated the spatial patterns of fish taxonomic, functional, and phylogenetic diversities and community assemblage, alongside their environmental drivers, within five impounded lakes of SNWDP. Our analysis sought to identify relationships between different aspects of diversity, assessing patterns of mismatch or congruence, and evaluating the efficacy of using one aspect as a proxy for another. Our results revealed that: 1) fish diversity and community assembly showed no longitudinal gradient, with spatial mismatches across diversity dimensions; 2) functional diversity was negatively correlated with both taxonomic and phylogenetic diversities, while the latter two showed no correlation; and 3) the SNWDP primarily affected taxonomic and functional diversities by altering water depth, nutrient status and promoting non-native species invasion, while phylogenetic diversity was mainly influenced by changes in water temperature and dissolved oxygen. These findings underscore the distinct contributions of various diversity measures and emphasize that no single measure can reliably predict another, highlighting the necessity of selecting diversity measures tailored to specific questions (e.g., for conservation or fisheries management).</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102985"},"PeriodicalIF":5.8,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137564","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":"Enhancing prediction of wildfire occurrence and behavior in Alaska using spatio-temporal clustering and ensemble machine learning","authors":"A. Ahajjam ,&nbsp;M. Allgaier ,&nbsp;R. Chance ,&nbsp;E. Chukwuemeka ,&nbsp;J. Putkonen ,&nbsp;T. Pasch","doi":"10.1016/j.ecoinf.2024.102963","DOIUrl":"10.1016/j.ecoinf.2024.102963","url":null,"abstract":"<div><div>Wildfires are an integral part of Alaska’s ecological landscape, shaping its boreal forests and tundra. However, recent shifts in wildfire frequency, intensity, and seasonality pose unprecedented challenges for fire management in Alaska’s remote and ecologically vulnerable regions. This study addresses the challenge of wildfire occurrence and behavior prediction in Alaska by developing a comprehensive framework that leverages satellite-based data, geospatial features, advanced optimization, and machine learning (ML). First, NASA’s Fire Information for Resource Management System (FIRMS) dataset spanning +20 years is processed using a spatio-temporal clustering algorithm to create refined wildfire datasets. A sequential Genetic Algorithm (GA) is employed for cost-effective feature selection from 49 geospatial features, including remote sensing and reanalysis data. Histogram Gradient Boosting (HistGB) is then used for predictive modeling of wildfire occurrence, burnt area, and wildfire duration. This ensemble model’s performance is benchmarked across four prediction horizons (same-day, +7 days, +30 days, +90 days) and against various conventional ML and deep learning techniques. Results highlight key factors influencing wildfire dynamics in Alaska and demonstrate substantial improvements in prediction accuracy (e.g., an average improvement of 72.62<span><math><mtext>%</mtext></math></span> in wildfire occurrence accuracy regardless of prediction horizon), offering valuable insights for risk assessment and resource allocation in wildfire management in Alaska.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"85 ","pages":"Article 102963"},"PeriodicalIF":5.8,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137585","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":"The dynamic driving mechanisms of wetland change from an asynchrony-spatiotemporal perspective: A case study in Pearl River Delta, China","authors":"Xiaoqing Yi ,&nbsp;Yuhang Wang ,&nbsp;Changjun Gao ,&nbsp;Jiaojiao Ma ,&nbsp;Demin Zhou ,&nbsp;Christian J. Sanders ,&nbsp;Guangjia Jiang ,&nbsp;Zhongwen Hu ,&nbsp;Junjie Wang ,&nbsp;Haichao Zhou ,&nbsp;Wei Li","doi":"10.1016/j.ecoinf.2024.102979","DOIUrl":"10.1016/j.ecoinf.2024.102979","url":null,"abstract":"<div><div>The mechanism of wetland distribution (WD) has been well studied, but further research is needed on the mechanism of wetland change (WC). This study developed a model of the impact of changes in human activity (HA) and natural environment factors on WC from an asynchronous–spatiotemporal perspective, integrating remote sensing technologies and partial least squares–structural equation modeling (PLS–SEM). In the model, HA was reflected by economic and population data. The natural environment was reflected by the fundamental natural environment (FNE), which was mainly based on terrain, and the non-stable natural environment (NNE), which was mainly based on hydrological and temperature conditions. The model met the accuracy requirements in the Pearl River Delta (PRD). The results showed that there were differences in the response of WD and WC to driving factors from 1980 to 2020 in the PRD. FNE had a negative impact on WD, however, FNE changes (FNEC) had a positive impact on WC (mainly wetlands decrease). HA could affect NNE and subsequently WD, but NNE changes (NNEC) only began to affect WC after 2010. HA had a negative impact on WD and WC from 1980 to 2010, but both negative and positive impacts existed after 2010. By coupling areas of HA changes (HAC) with wetland decrease, it was found that HA should be restricted in the southeast of Foshan (areas where HA increase led to wetland decrease) to protect wetlands; The junction between Zhaoqing and Foshan (areas where HA decrease lead to wetland decrease) requires investment in improving the natural environment. The model proposed in this study can be applied to other areas with severe wetland degradation from HA and natural conditions, to assist in local wetland restoration and management.</div></div>","PeriodicalId":51024,"journal":{"name":"Ecological Informatics","volume":"86 ","pages":"Article 102979"},"PeriodicalIF":5.8,"publicationDate":"2024-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101817","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}