Environmental Modelling & Software最新文献_第6页

Multimodal air-quality prediction: A multimodal feature fusion network based on shared-specific modal feature decoupling 多模态空气质量预测：基于共享特定模态特征解耦的多模态特征融合网络

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-17 DOI: 10.1016/j.envsoft.2025.106553

Xiaoxia Chen , Zhen Wang , Fangyan Dong , Kaoru Hirota

{"title":"Multimodal air-quality prediction: A multimodal feature fusion network based on shared-specific modal feature decoupling","authors":"Xiaoxia Chen , Zhen Wang , Fangyan Dong , Kaoru Hirota","doi":"10.1016/j.envsoft.2025.106553","DOIUrl":"10.1016/j.envsoft.2025.106553","url":null,"abstract":"<div><div>Severe air pollution degrades air quality and threatens human health, necessitating accurate prediction for pollution control. While spatiotemporal networks integrating sequence models and graph structures dominate current methods, prior work neglects multimodal data fusion to enhance feature representation. This study addresses the spatial limitations of single-perspective ground monitoring by synergizing remote sensing data, which provides global air quality distribution, with ground observations. We propose a Shared-Specific Modality Decoupling-based Spatiotemporal Multimodal Fusion Network for air-quality prediction, comprising: (1) feature extractors for remote sensing images and ground monitoring data, (2) a decoupling module separating shared and modality-specific features, and (3) a hierarchical attention-graph convolution fusion module. This framework achieves effective multimodal fusion by disentangling cross-modal dependencies while preserving unique characteristics. Evaluations on two real-world datasets demonstrate superior performance over baseline models, validating the efficacy of multimodal integration for spatial–temporal air quality forecasting.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106553"},"PeriodicalIF":4.8,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144312780","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}

引用次数: 0

HydroBOT: an integrated toolkit for assessment of hydrology-dependent outcomes HydroBOT：用于评估水文相关结果的综合工具包

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-16 DOI: 10.1016/j.envsoft.2025.106579

Galen Holt , Georgia K. Dwyer , David Robertson , Martin Job , Rebecca E. Lester

{"title":"HydroBOT: an integrated toolkit for assessment of hydrology-dependent outcomes","authors":"Galen Holt , Georgia K. Dwyer , David Robertson , Martin Job , Rebecca E. Lester","doi":"10.1016/j.envsoft.2025.106579","DOIUrl":"10.1016/j.envsoft.2025.106579","url":null,"abstract":"<div><div>Water management rarely focuses only on water; instead, management targets values across many water-dependent responses. To assess past performance and plan future actions, water managers need to understand how changes to hydrology (over which they typically have most control) affect water-dependent values. Models relating values to hydrology can be difficult to integrate into management processes; they are often developed for other uses and target subsets of values. We describe and demonstrate HydroBOT (Hydrology-dependent Basin Outcomes Toolkit), a modeling toolkit co-designed with the primary federal water management agency in the Murray-Darling Basin, Australia. HydroBOT can integrate disparate response models and scale and synthesize those results across space, time, and groups of values. Outputs target water management needs and can be tailored to a range of questions, from local, short-term evaluation to basin-scale climate assessment. HydroBOT provides new capacity to move beyond hydrology to assess outcomes across diverse target values.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106579"},"PeriodicalIF":4.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322906","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}

引用次数: 0

Soil organic matter mapping in complex terrains considering spatial heterogeneity 考虑空间异质性的复杂地形土壤有机质制图

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-14 DOI: 10.1016/j.envsoft.2025.106569

Yue Yin , Bingbo Gao , Hao Xu , Yuxue Wang , Dongkai Xie , Yanqing Liu , Chenyi Wang

{"title":"Soil organic matter mapping in complex terrains considering spatial heterogeneity","authors":"Yue Yin , Bingbo Gao , Hao Xu , Yuxue Wang , Dongkai Xie , Yanqing Liu , Chenyi Wang","doi":"10.1016/j.envsoft.2025.106569","DOIUrl":"10.1016/j.envsoft.2025.106569","url":null,"abstract":"<div><div>The intricate topography and weak spatial autocorrelation in mountainous areas contribute to strong local and directional heterogeneity in the spatial distribution of soil organic matter (SOM). The relationships between SOM and auxiliary variables also exhibit spatial disparities. This mixed heterogeneity seriously affects the prediction accuracy of SOM's spatial distribution. Furthermore, the high cost and challenges associated with sampling in mountainous areas result in limited availability, sparseness, and uneven spatial distribution of soil samples, thereby intensifying the difficulty of precise spatial prediction. The newly developed two-point machine learning method (TPML) adeptly manages local heterogeneity and heterogeneous relationships by a two-step modeling approach, but its application in addressing directional heterogeneity remains unexplored. This study investigates whether explicitly integrating directional information between two points as an auxiliary variable in the TPML modeling process can enhance the prediction accuracy of SOM in complex terrains characterized by small sample sizes. In this study, multiple sets of comparative experiments were conducted to assess the accuracy of various methodologies, including TPML, ordinary kriging, random forest, and random forest regression kriging. The results indicate that (1) TPML can capture the local and directional heterogeneity in the distribution of SOM in mountainous areas, addressing the spatially varying relationship between SOM and auxiliary variables. (2) TPML demonstrates the capacity to characterize the directional heterogeneity of SOM even without the inclusion of directional information as an auxiliary variable. (3) Through cross-validation, TPML emerges as the most accurate predictive method. Mapping outcomes reveal that TPML can produce precise and coherent spatial distribution maps of SOM with fine spatial details.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106569"},"PeriodicalIF":4.8,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144304863","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}

引用次数: 0

Evaluating IMERG-F precipitation for SWAT hydrologic modeling in data-rich and sparse watersheds 基于数据丰富和稀疏流域SWAT水文模拟的imergf降水评价

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-14 DOI: 10.1016/j.envsoft.2025.106574

Fernando Jarrin-Perez , Jaehak Jeong , Katrin Bieger , Jean-Claude Roger , Soonkun Choi

{"title":"Evaluating IMERG-F precipitation for SWAT hydrologic modeling in data-rich and sparse watersheds","authors":"Fernando Jarrin-Perez , Jaehak Jeong , Katrin Bieger , Jean-Claude Roger , Soonkun Choi","doi":"10.1016/j.envsoft.2025.106574","DOIUrl":"10.1016/j.envsoft.2025.106574","url":null,"abstract":"<div><div>This study evaluates the potential of Satellite-derived Rainfall Estimates (SREs), specifically IMERG-F data, as substitutes for ground-based precipitation in hydrological modeling. Two contrasting watersheds were analyzed: the well-gauged Little River Experimental Watershed (USA) and the data-scarce Wami Subbasin (Africa). This research compares streamflow simulations driven by ground-based and SRE-based precipitation data with the SWAT model. In the intensively monitored Little River Experimental Watershed, ground-based data outperformed SREs, particularly with higher rain gauge density. However, when gauge density dropped below 300 km<sup>2</sup> per station, the performance of SRE-based models improved, highlighting SREs as a viable alternative in sparsely gauged regions. In the Wami Subbasin in Africa, SRE-driven models offered comparable or superior streamflow predictions, demonstrating their value in regions with scarce or unreliable precipitation data. Overall, the study confirms that SREs can enhance hydrological modeling accuracy, particularly in data-scarce areas, while emphasizing the continued preference for ground-based data in well-monitored regions.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106574"},"PeriodicalIF":4.8,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144304883","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}

引用次数: 0

The SPIChanges R-package: Improving the interpretation of the standardized precipitation index under changing climate conditions SPIChanges R-package：在气候变化条件下改进标准化降水指数的解译

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-14 DOI: 10.1016/j.envsoft.2025.106573

Gabriel Constantino Blain , Graciela da Rocha Sobierajski , Letícia Lopes Martins , Adam H. Sparks

{"title":"The SPIChanges R-package: Improving the interpretation of the standardized precipitation index under changing climate conditions","authors":"Gabriel Constantino Blain , Graciela da Rocha Sobierajski , Letícia Lopes Martins , Adam H. Sparks","doi":"10.1016/j.envsoft.2025.106573","DOIUrl":"10.1016/j.envsoft.2025.106573","url":null,"abstract":"<div><div>The Standardized Precipitation Index (SPI) assumes the frequency of droughts remains constant over time. Given that climate change may violate this assumption, nonstationary versions of the SPI (NSPI) have been proposed. However, the NSPI presents a contradictory behavior, which may indicate fewer drought events under changes towards drier conditions. To overcome this issue, the SPIChanges package uses nonstationary distributions to quantify the effect of changes in precipitation patterns on the probability of SPI estimates. The package includes 16 candidate models that can describe a wide range of changes in precipitation patterns. The selected model calculates the probability of precipitation amounts under altered climate conditions and compares them with those of the SPI algorithm, revealing how the frequency of droughts has changed over time. The results of Monte Carlo simulations and case study applications allowed us to conclude that the package enhances the interpretation of SPI estimates under climate change conditions.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106573"},"PeriodicalIF":4.8,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144304861","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}

引用次数: 0

Connecting Landscapes: A decision support system to facilitate conservation led development 连接景观：促进以保护为主导的发展的决策支持系统

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-13 DOI: 10.1016/j.envsoft.2025.106576

Patrick Jantz , David W. Macdonald , Ivan Gonzalez , Andrew J. Hearn , Żaneta Kaszta , Erin L. Landguth , Dawn Burnham , Scott J. Goetz , Katherine A. Zeller , Andrew J. Loveridge , Samuel Cushman

{"title":"Connecting Landscapes: A decision support system to facilitate conservation led development","authors":"Patrick Jantz , David W. Macdonald , Ivan Gonzalez , Andrew J. Hearn , Żaneta Kaszta , Erin L. Landguth , Dawn Burnham , Scott J. Goetz , Katherine A. Zeller , Andrew J. Loveridge , Samuel Cushman","doi":"10.1016/j.envsoft.2025.106576","DOIUrl":"10.1016/j.envsoft.2025.106576","url":null,"abstract":"<div><div>Unsustainable development continues to fragment natural landscapes and wildlife populations, contributing to declining global biodiversity. Advances in computation have enabled ever more sophisticated assessment of development and conservation impacts on functional landscape connectivity. However, accessibility of these advances to non-expert users has lagged. Here we present Connecting Landscapes (CoLa), an integration and expansion of existing software applications that model functional connectivity, population dynamics, and genetic exchange across landscapes. CoLa is a cloud-based or locally installable conservation decision-support system (DSS) that enables user-friendly assessment of the trade-offs between development and conservation in a data-driven framework. We describe the origins of the CoLa DSS, its functionality, and present two case studies at different spatial scales illustrating its use. We expect the CoLa DSS will be particularly useful to decision makers attempting to reconcile economic growth and biodiversity conservation, supporting the transition to conservation-led development needed to stem the ongoing loss of biodiversity.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106576"},"PeriodicalIF":4.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144304889","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}

引用次数: 0

Exploring the key meteorological drivers of air pollution by intrinsically interpretable deep learning 通过内在可解释的深度学习探索空气污染的关键气象驱动因素

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-13 DOI: 10.1016/j.envsoft.2025.106571

Chang Yan , Xuanming Zhang , Yan Yu , Yuelin Liu , Xiaodong Wu , Xin Zheng , Guangming Shi , Fumo Yang

{"title":"Exploring the key meteorological drivers of air pollution by intrinsically interpretable deep learning","authors":"Chang Yan , Xuanming Zhang , Yan Yu , Yuelin Liu , Xiaodong Wu , Xin Zheng , Guangming Shi , Fumo Yang","doi":"10.1016/j.envsoft.2025.106571","DOIUrl":"10.1016/j.envsoft.2025.106571","url":null,"abstract":"<div><div>To address interpretability limitations in environmental data-driven models, this study presents an inherently interpretable Multi-Task Auto-Encoder (MTAE). Distinct from post-hoc explanation approaches such as Shapley Additive Explanations (SHAP), MTAE directly decodes abstract features into physically meaningful representations (e.g. meteorological drivers) via specialized decoders, thereby explicitly uncovering PM<sub>2.5</sub> variation mechanisms. Experimental results based on Gradient-weighted Class Activation Mapping (Grad-CAM) and SHAP demonstrate that MTAE is effective in identifying the key meteorological factors influencing PM<sub>2.5</sub> variations and quantifying the impacts of weather anomalies and emission patterns. By converting latent features into interpretable physical variables during the feature extraction process, the framework establishes a novel paradigm for analyzing the complex meteorology-air quality interactions. This work promotes the design of interpretable models in environmental sciences, providing a benchmark for transparent pollution mechanism analysis while maintaining predictive performance. The methodology narrows the gap between post-hoc explanations and intrinsic interpretability, offering actionable insights for atmospheric research and policy-making.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106571"},"PeriodicalIF":4.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280633","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}

引用次数: 0

Transformer-LSTM-KOA: A novel approach for prediction of chlorophyll in the South China Sea 变压器- lstm - koa：一种预测南海叶绿素的新方法

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-12 DOI: 10.1016/j.envsoft.2025.106575

Gang Chen , Zhenzhong Liu , Runfeng Zhang , Guobin Zhang , Jutao Wang , Tongrui Zhang

{"title":"Transformer-LSTM-KOA: A novel approach for prediction of chlorophyll in the South China Sea","authors":"Gang Chen , Zhenzhong Liu , Runfeng Zhang , Guobin Zhang , Jutao Wang , Tongrui Zhang","doi":"10.1016/j.envsoft.2025.106575","DOIUrl":"10.1016/j.envsoft.2025.106575","url":null,"abstract":"<div><div>Chlorophyll is a critical indicator of marine primary productivity and is essential in assessing aquatic ecosystem health. To address the limitations of current prediction models regarding accuracy, mobility, and reliability, this study proposes a novel Transformer-LSTM-KOA model for Chlorophyll prediction. Leveraging remote sensing data from the South China Sea, the model synergistically integrates Transformer's global analytical capabilities via self-attention and multi-head attention mechanisms with LSTM's proficiency in capturing long-term dependencies through gated mechanisms. The Kepler Optimization Algorithm (KOA) is subsequently employed to systematically optimize both global and local model parameters, thereby enhancing adaptability and robustness across diverse prediction datasets. Experimental results demonstrate superior performance with MSE and MAE values of 0.00011 and 0.00685, respectively, outperforming benchmark models. This enhanced modeling framework provides crucial technical support for marine ecological forecasting and early warning systems.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106575"},"PeriodicalIF":4.8,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291484","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}

引用次数: 0

Improved Biome-BGC model for simulating spatiotemporal dynamics of gross primary productivity in evergreen broadleaf forests of the karst region 喀斯特地区常绿阔叶林总初级生产力时空动态模拟的改进Biome-BGC模型

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-12 DOI: 10.1016/j.envsoft.2025.106563

Hengyuan Liu , Qian Ding , Yuechen Li , Lei Fan , Long Zhao , Mingguo Ma

{"title":"Improved Biome-BGC model for simulating spatiotemporal dynamics of gross primary productivity in evergreen broadleaf forests of the karst region","authors":"Hengyuan Liu , Qian Ding , Yuechen Li , Lei Fan , Long Zhao , Mingguo Ma","doi":"10.1016/j.envsoft.2025.106563","DOIUrl":"10.1016/j.envsoft.2025.106563","url":null,"abstract":"<div><div>Accurately estimating gross primary productivity (GPP) is crucial for carbon cycle modeling, yet the karst landscape of southwest China poses challenges due to persistent cloud cover, rugged topography, and limited observations. This study enhances the Biome-BGC model for evergreen broadleaf forests (EBF) by optimizing key ecophysiological parameters and introducing a phase-specific bias correction method. A GPP dataset (1 km, daily; 2001–2019) was developed by integrating multi-source data. Validation with flux tower data confirmed significant improvements over the default model, with R increasing by 7 % and RMSE decreasing by 28 %. Compared to existing remote sensing products, the optimized model achieved a 75 % increase in R<sup>2</sup> and a 28 % reduction in RMSE. Trend analysis reveals seasonal fluctuations and an overall decline in GPP, with 35 % of the area projected to transition from a decreasing to an increasing trend in the future. This study provides enhanced GPP estimates for carbon cycle assessments.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106563"},"PeriodicalIF":4.8,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297424","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}

引用次数: 0

Coupled machine learning and data assimilation for efficient characterization of multi-contaminant groundwater sites 耦合机器学习和数据同化用于多污染物地下水场地的有效表征

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-12 DOI: 10.1016/j.envsoft.2025.106577

Haijian Xie , Yanhao Wu , Yanghui Shi , Mengcheng Zhang , Yang Chen , Mei Li , Dengdeng Jiang , Wenyi Xie

{"title":"Coupled machine learning and data assimilation for efficient characterization of multi-contaminant groundwater sites","authors":"Haijian Xie , Yanhao Wu , Yanghui Shi , Mengcheng Zhang , Yang Chen , Mei Li , Dengdeng Jiang , Wenyi Xie","doi":"10.1016/j.envsoft.2025.106577","DOIUrl":"10.1016/j.envsoft.2025.106577","url":null,"abstract":"<div><div>Accurate and rapid characterization of contaminated groundwater sites is crucial for the development of effective remediation strategies. The inherent complexity of subsurface contamination and the variability in hydrogeological structures add to the challenges of this task. This study introduces an innovative framework that integrates data assimilation with machine learning to efficiently and effectively characterize contaminated groundwater sites, even in the presence of limited data. This study uses real data from a multi-contaminant contaminated landfill site in Suzhou, Jiangsu Province, China, as a case study. Comprehensive hydrogeological data and contaminant levels exceeding regulatory thresholds were obtained through extensive field surveys and laboratory analyses. These data facilitated the construction of models for groundwater flow and solute transport. The effectiveness of the Ensemble Smoother with Multiple Data Assimilation (ES-MDA) algorithm was evaluated in realistic scenarios. Subsequently, a surrogate groundwater model utilizing the Imputation Self-Organizing Map (ImpSOM) network was developed and integrated into the ES-MDA framework. The results demonstrate that the ES-MDA algorithm accurately identified the sources of contaminants—specifically 2,4,6-trichlorophenol, chloride, and nitrate nitrogen—within eight iterations and effectively captured the heterogeneity of the hydraulic conductivity field. Utilizing sparse data from observation wells, the ES-MDA-ImpSOM framework mapped the temporal and spatial variations of contaminants, achieving an 85.6 % improvement in computational efficiency. These findings underscore the framework's potential for applications in early warning systems and emergency management at real-world contamination sites.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106577"},"PeriodicalIF":4.8,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144304864","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}

引用次数: 0