{"title":"STGCN-WQ: A new Spatio-Temporal Graph Convolutional Network for predicting beach Water Quality","authors":"Peisen Li , Zhenduo Zhu","doi":"10.1016/j.envsoft.2025.106731","DOIUrl":"10.1016/j.envsoft.2025.106731","url":null,"abstract":"<div><div>Polluted waters pose significant health risks to beachgoers. While monitoring Fecal Indicator Bacteria (FIB) is a slow process, predictive models can serve as valuable tools for beach management by facilitating timely public health advisories. However, previous studies often overlook the spatiotemporal characteristics of beach water quality in their predictive models. This study addresses this gap by introducing a new Spatio-Temporal Graph Convolutional Network for predicting beach Water Quality (STGCN-WQ). Additionally, we propose a Spatio-Then-Temporal (STT) imputation strategy to handle missing data, which first leverages spatial correlations among neighboring beaches to estimate missing values and subsequently applies temporal interpolation to refine predictions. This two-step approach improves robustness against both irregular sampling and data sparsity. The STGCN-WQ model is applied to 24 beaches along the southern shoreline of Lake Erie, collecting 18,519 FIB sample records from 2009 to 2020. Results indicate that the STGCN-WQ model achieves significant improvements in performance metrics, with F1 score and AUC value increasing by 78% and 19%, respectively, compared to the baseline “Persistence Method”, which solely relies on the most recent observation collected prior to the current day for nowcasting FIB conditions. This study provides valuable insights and new tools for effective beach water quality management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106731"},"PeriodicalIF":4.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314965","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":"Explainable AI for rule reduction in fuzzy models for air pollution measurement adjustment","authors":"Piotr A. Kowalski , Martina Casari , Laura Po","doi":"10.1016/j.envsoft.2025.106734","DOIUrl":"10.1016/j.envsoft.2025.106734","url":null,"abstract":"<div><div>Air quality monitoring using low-cost sensors has become increasingly important, yet their measurements are often inaccurate. Traditional adjustment methods face limitations in both applicability and explainability. This paper presents an explainable artificial intelligence approach for rule reduction in adaptive neuro-fuzzy inference systems, to improve the interpretability and efficiency of fuzzy models for fine particulate matter (PM<sub>2.5</sub>) measurement adjustment. We introduce two novel algorithms, the Binary Activation Method and the Weighted Activation Method, to assess and eliminate redundant rules while maintaining predictive performance, validating the approaches in multiple geographic locations. On average, rule pruning results in an increase in MAE of 0.2 on the training set and 0.1 on the test set. The simplified models retain strong correlation, with Pearson’s correlation coefficients ranging from 0.73 to 0.96 in the test set. These results support the development of reliable and interpretable artificial intelligence systems for environmental monitoring.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106734"},"PeriodicalIF":4.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314962","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}
Dichen Liu , Fengyuan Zhang , Kai Xu , Daniel P. Ames , Albert J. Kettner , C. Michael Barton , Anthony J. Jakeman , Min Chen
{"title":"Academic influence index evaluation report of geographic simulation models (2023)","authors":"Dichen Liu , Fengyuan Zhang , Kai Xu , Daniel P. Ames , Albert J. Kettner , C. Michael Barton , Anthony J. Jakeman , Min Chen","doi":"10.1016/j.envsoft.2025.106737","DOIUrl":"10.1016/j.envsoft.2025.106737","url":null,"abstract":"<div><div>As the availability and number of geographic simulation models across various domains have surged, evaluating their relative value has become increasingly challenging. Traditional model evaluation typically involves comparing simulation results with measured data or outputs from other models. In contrast to these traditional approaches, this report continues the application of the “Model Academic Influence Index (MAI)” method from the previous year, which assesses the relative value of the model from the perspective of academic influence, emphasizing its academic contributions. We evaluate the MAI of 207 models and 22 methods collected from credible digital repositories in 2023 and establish a model leaderboard. Based on this ranking, we briefly explore the proportional representation of open-source versus closed-source models and further investigate the distribution of models across different open-source licenses. These findings provide support for model selection and optimization within the academic community and beyond, while offering new insights into the development of the open-source ecosystem.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106737"},"PeriodicalIF":4.6,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314961","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}
Yu Ding , Jiaxin Dong , Mengfan Teng , Shiyao Meng , Jie Yang , Siwei Li
{"title":"A feature-level ensemble framework for improving daily PM2.5 estimation across the contiguous United States (2000–2023)","authors":"Yu Ding , Jiaxin Dong , Mengfan Teng , Shiyao Meng , Jie Yang , Siwei Li","doi":"10.1016/j.envsoft.2025.106733","DOIUrl":"10.1016/j.envsoft.2025.106733","url":null,"abstract":"<div><div>Accurate PM<sub>2.5</sub> surface concentration estimates are vital for air quality management and exposure assessment. This study introduces a novel feature-level ensemble framework to enhance daily PM<sub>2.5</sub> estimation across the contiguous United States from 2000 to 2023. The framework integrates multiple XGBoost models trained with diverse temporal features, including calendar encodings and physically derived indicators like rolling averages and change rates from reanalysis PM<sub>2.5</sub>. By capturing complementary pollution dynamics, the ensemble outperforms models using only calendar features. Under spatial cross-validation, R<sup>2</sup> increases from 0.64 to 0.70 and RMSE drops from 7.87 to 7.31 μg/m<sup>3</sup>. Temporal extrapolation also improves, with △R<sup>2</sup> gains of 0.08 (historical backcasting) and 0.07 (future forecasting). These results demonstrate the framework's robustness, generalizability, and value for long-term PM<sub>2.5</sub> monitoring, epidemiological research, and data-driven air quality policymaking.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106733"},"PeriodicalIF":4.6,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262077","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}
Jiajia Huang , Wenyan Wu , Holger R. Maier , Justin Hughes , Quan J. Wang , Yuan Cao
{"title":"Comprehensive framework for long-term reservoir management under deep uncertainty","authors":"Jiajia Huang , Wenyan Wu , Holger R. Maier , Justin Hughes , Quan J. Wang , Yuan Cao","doi":"10.1016/j.envsoft.2025.106740","DOIUrl":"10.1016/j.envsoft.2025.106740","url":null,"abstract":"<div><div>Reservoir systems play a crucial role in providing essential services such as water supply, flood protection, and energy generation. However, reservoir management is highly complex due to (i) multiple conflicting management goals, (ii) long-term changes in water availability and demand over the long life span of these systems, and (iii) deep uncertainty. While some of these challenges have been addressed in previous studies, there is a lack of a comprehensive framework that can maximize the co-benefits of addressing these challenges in an integrated manner. Such an optimization framework has been developed in this study. By incorporating deep uncertainty, the causal relationships between decisions, system performance, and robustness can be explored. By adapting both operation policy and infrastructure upgrade decisions to long-term changes, infrastructure investments can be reduced without compromising system performance. By explicitly accounting for multiple conflicting objectives, the framework also provides a platform for negotiation during the decision-making process.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106740"},"PeriodicalIF":4.6,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262075","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}
Giang V. Nguyen , Chien Pham Van , Vinh Ngoc Tran , Linh Nguyen Van , Giha Lee
{"title":"Toward real-time high-resolution fluvial flood forecasting: A robust surrogate approach based on overland flow models","authors":"Giang V. Nguyen , Chien Pham Van , Vinh Ngoc Tran , Linh Nguyen Van , Giha Lee","doi":"10.1016/j.envsoft.2025.106716","DOIUrl":"10.1016/j.envsoft.2025.106716","url":null,"abstract":"<div><div>Timely flood prediction is critical for mitigating risks under the growing impacts of climate change. Traditional physics-based hydrodynamic models, while effective at capturing flood dynamics, are limited by high computational demands, restricting real-time applicability. This study presents a hybrid framework that integrates machine learning (ML) with physics-based modeling to enable efficient real-time flood forecasting. Physics-based simulations provide detailed inundation information, while ML models serve as fast surrogate predictors. Applied to the Cambodia floodplain — a region highly prone to seasonal flooding — the surrogate models were trained on outputs from TELEMAC simulations. Explainable AI was employed to interpret model decision-making. Results show that the hybrid approach achieves substantial computational efficiency while preserving accuracy. The best surrogate attained R <span><math><mo>=</mo></math></span> 0.97 and KGE <span><math><mo>=</mo></math></span> 0.91, reducing simulation time by over 70-fold compared with TELEMAC. Incorporating geographic features such as latitude and longitude further enhanced predictive skill, particularly in flat floodplain settings.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106716"},"PeriodicalIF":4.6,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314964","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}
Hongfei Li , Jun Yang , Jiaxing Xin , Wenbo Yu , Jiayi Ren , Huisheng Yu , Xiangming Xiao , Jianhong (Cecilia) Xia
{"title":"Investigating the effect of urban form on land surface temperature at block and grid scales based on XGBoost-SHAP","authors":"Hongfei Li , Jun Yang , Jiaxing Xin , Wenbo Yu , Jiayi Ren , Huisheng Yu , Xiangming Xiao , Jianhong (Cecilia) Xia","doi":"10.1016/j.envsoft.2025.106738","DOIUrl":"10.1016/j.envsoft.2025.106738","url":null,"abstract":"<div><div>The urban thermal environment is becoming increasingly severe. In this study, we integrated eXtreme Gradient Boosting with the SHapley Additive exPlanations method to investigate the effects of various urban factor indexes (UFIs) on land surface temperature (LST) at both block and grid scales. Additionally, we examined the differences in LST and its driving factors across local climate zones (LCZs) at the grid scale. The results show that LST is higher in central areas than in peripheral ones during summer and autumn, but this pattern is reversed in spring and winter. LST varies significantly across LCZs, with the normalized difference built-up index, normalized difference vegetation index (NDVI), and Shannon's diversity index (SHDI) identified as the main contributors. The sky view factor inhibits LST at the block scale but promotes it at the grid scale. The impacts of UFIs follow the seasonal trend: summer > spring > autumn > winter. LST responses to UFIs exhibit similar trends across scales, showing specific warming or cooling thresholds—for example, a cooling effect when SHDI exceeds 0.65, and a warming effect when building density exceeds 20 % (summer and autumn) or 40 % (spring and winter). Significant cooling occurs only when NDVI exceeds 0.4; however, NDVI generally remains low in all seasons except summer. High-contribution UFIs typically exhibit the strongest interaction effects with artificial factor indicators.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106738"},"PeriodicalIF":4.6,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314963","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}
Adrian Huerta , Stefan Brönnimann , Martín de Luis , Santiago Beguería , Roberto Serrano-Notivoli
{"title":"Enhancing daily precipitation reconstruction: An improved version of the reddPrec R package","authors":"Adrian Huerta , Stefan Brönnimann , Martín de Luis , Santiago Beguería , Roberto Serrano-Notivoli","doi":"10.1016/j.envsoft.2025.106717","DOIUrl":"10.1016/j.envsoft.2025.106717","url":null,"abstract":"<div><div>Reconstructing high-quality daily precipitation series is essential for climate studies, hydrological modeling, and environmental applications. This work presents a new version of reddPrec, a versatile and flexible R package designed to reconstruct precipitation datasets through standard quality control, gap-filling, and grid creation procedures. The update introduces greater flexibility in spatial modeling, inclusion of dynamic covariates, and new modules for enhanced quality control and homogenization. Daily precipitation can now be predicted using machine learning approaches within a flexible, user-friendly framework, allowing users to select modeling approaches and customize settings. We demonstrate its capabilities through case studies in Switzerland and Spain, evaluating improvements in reconstruction accuracy, quality control, and homogenization. Enhanced quality control and homogenization procedures were specifically validated to ensure reliable adjustment and consistency of precipitation series. Overall, reddPrec provides a comprehensive and reliable tool for reconstructing precipitation series, supporting the creation of high-quality datasets for climate research and related fields.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106717"},"PeriodicalIF":4.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314966","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}
Yusheng Qin , Xin Han , Hanwen Shi , Xiangxian Li , Jingjing Tong , Minguang Gao , Yujun Zhang
{"title":"DSTMA-BLSTM algorithm for roadside air pollutant time series prediction and sensitivity analysis","authors":"Yusheng Qin , Xin Han , Hanwen Shi , Xiangxian Li , Jingjing Tong , Minguang Gao , Yujun Zhang","doi":"10.1016/j.envsoft.2025.106730","DOIUrl":"10.1016/j.envsoft.2025.106730","url":null,"abstract":"<div><div>Road traffic pollution greatly affects urban air quality, making accurate prediction of roadside pollutant concentrations essential for effective environmental management. This study presents a novel DSTMA-BLSTM algorithm, which combines Dynamic Shared and Task-specific Multi-head Attention (DSTMA) with Bidirectional Long Short-Term Memory (BLSTM) networks, to forecast temporal changes in roadside pollutants and analyze their sensitivity. Using real monitoring data, the study identifies wind speed and the counts of gasoline and diesel vehicles as critical factors influencing roadside pollutant levels. The model achieved outstanding predictive performance for NO, NO<sub>2</sub>, and CO<sub>2</sub>, with R<sup>2</sup> values of 0.959, 0.944, and 0.949, respectively, demonstrating its exceptional ability to capture the dynamics of traffic-related pollutants. This work not only establishes the DSTMA-BLSTM model as a powerful tool for multi-pollutant forecasting but also proposes a fresh perspective for jointly predicting traffic and non-traffic-related pollutants in future research.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106730"},"PeriodicalIF":4.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262079","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":"An acoustic inversion-based flow measurement model in 3D hydrodynamic systems","authors":"Jiwei Li , Lingyun Qiu , Zhongjing Wang , Hui Yu","doi":"10.1016/j.envsoft.2025.106714","DOIUrl":"10.1016/j.envsoft.2025.106714","url":null,"abstract":"<div><div>This study extends an established two-dimensional flow measurement approach to three-dimensional scenarios, addressing the growing need for accurate and efficient non-contact measurement techniques in complex hydrodynamic environments. Compared to conventional Acoustic Doppler Current Profilers (ADCPs) and remote sensing-based flow monitoring, the proposed method enables high-resolution, continuous water velocity measurement, making it well-suited for hazardous environments such as floods, strong currents, and sediment-laden rivers. Building upon the original approach, we develop an enhanced model that incorporates multiple emission directions and flexible configurations of receivers. These advancements improve the adaptability and accuracy of the method when applied to three-dimensional flow fields. To evaluate its feasibility, extensive numerical simulations are conducted to mimic real-world hydrodynamic conditions. The results demonstrate that the proposed method effectively handles diverse and complex flow field configurations, highlighting its potential for practical applications in water resource management and hydraulic engineering.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"195 ","pages":"Article 106714"},"PeriodicalIF":4.6,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262081","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}