Environmental Modelling & Software最新文献

{"title":"sGs UnMix: a web application for spatial prediction and mixture modeling with a case study on volcanic soil CO2 fluxes","authors":"Giulio Bini,&nbsp;Giancarlo Tamburello,&nbsp;Stefano Cacciaguerra,&nbsp;Paolo Perfetti","doi":"10.1016/j.envsoft.2025.106652","DOIUrl":"10.1016/j.envsoft.2025.106652","url":null,"abstract":"<div><div>Spatial data analysis and prediction are fundamental in geoscience for mapping continuous variables and supporting decision-making. However, traditional geostatistical tools often require programming skills or involve manual, subjective steps. Here, we developed sGs UnMix, an interactive web application that simplifies spatial prediction workflows and reduces subjectivity in statistical analysis, making it accessible to the entire geoscience community. sGs UnMix (available online at <span><span>https://apps.bo.ingv.it/sgs-unmix</span><svg><path></path></svg></span>) is built with the shiny package for R and is organized into four main panels, which allow data loading and coordinate projection, data separation through mixture modeling, variogram modeling, and spatial prediction using sequential Gaussian simulation (sGs). Automated variogram fitting and mixture modeling reduce user bias, while dynamically updated heat maps enable real-time visualization of spatial patterns. sGs UnMix provides not only a standardized approach for estimating volcanic volatile fluxes (e.g., soil CO₂ emissions) but also applications in ore deposit mapping, hydrocarbon exploration, environmental monitoring, and climatology. Compared to existing geostatistical tools, it offers automation, interactivity, and a platform-independent, standalone web-based solution for geoscientists.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106652"},"PeriodicalIF":4.6,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144898567","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":"Next-generation techniques for parameter reduction for BMP multiobjective optimization in watershed planning","authors":"Hoda S. Razavi ,&nbsp;Gregorio Toscano ,&nbsp;A. Pouyan Nejadhashemi ,&nbsp;Kalyanmoy Deb ,&nbsp;Lewis Linker","doi":"10.1016/j.envsoft.2025.106651","DOIUrl":"10.1016/j.envsoft.2025.106651","url":null,"abstract":"<div><div>Best Management Practices (BMPs) reduce pollutants, but cost, efficiency, and site-specific constraints limit implementation in water resources planning. This study optimized BMP selection in West Virginia's Chesapeake Bay watershed, where nutrient pollution, sedimentation, runoff, and urbanization are major challenges. The Chesapeake Assessment Scenario Tool was integrated with a multiobjective optimization algorithm to identify cost-effective BMP strategies. Four BMP groups were evaluated: agricultural, developed, septic, and natural, targeting nitrogen reduction. The optimization involved 205 BMPs and up to 65,260 variables. The variables consist of four key components: land-river segment, agency, load source, and BMP type. Three land-use-based techniques were developed using innovization to enhance optimization efficiency by extracting knowledge from optimization results to reduce variables. The best method achieved a 97 % reduction in variables without compromising solution quality. These findings demonstrate that large, complex watershed optimization problems can now be solved efficiently, enabling more scalable and effective regional water management strategies.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106651"},"PeriodicalIF":4.6,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144885801","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":"Estimating natural streamflow using a combined extension and routing approach","authors":"Ganggang Zuo,&nbsp;Yani Lian,&nbsp;Ni Wang,&nbsp;Jiancang Xie","doi":"10.1016/j.envsoft.2025.106650","DOIUrl":"10.1016/j.envsoft.2025.106650","url":null,"abstract":"<div><div>Extension-based streamflow naturalization methods struggle with identifying mutations and selecting key features, while routing methods overlook the contribution of interstation runoff. This study proposes a Combined Extension and Routing (CER) approach to address these issues. The CER approach employs multiple change detection techniques to identify the earliest significant mutation and a multiple linear factors reconstruction method to select key features influencing natural flow. The CER models, implemented using extreme gradient boosting, Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Convolutional Neural Networks, and multiple linear regression, were evaluated in two snow-dominated catchments in the Yellow River, China. Results show that CER models effectively captured both peak and low flow events, achieving Nash–Sutcliffe efficiency of about 0.9 when comparing the estimation results from a water balance model. This study highlights the importance of stable land conditions for the CER approach's effectiveness, providing a reliable framework for natural streamflow estimation.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106650"},"PeriodicalIF":4.6,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861250","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 enhanced 2D model with the HLLC method utilized for local multi-layer SWEs for partial obstructed flows","authors":"Chengzhi Xiao ,&nbsp;Feng Peng ,&nbsp;Chunhong Hu ,&nbsp;Hongping Zhang","doi":"10.1016/j.envsoft.2025.106641","DOIUrl":"10.1016/j.envsoft.2025.106641","url":null,"abstract":"<div><div>Traditional two-dimensional (2D) hydrodynamic models mostly rely on empirical methods to calculate the flow discharge through hydraulic structures such as bridges, dams, weirs, and sluices, often compromising the precision and stability of simulations. In this study, a Harten-Lax-van Leer-Contact (HLLC) method based on a local implementation of multi-layer shallow water equations (SWEs) for flow through structures was developed in a 2D hydrodynamic model to achieve precise and stable simulations for flow fields involving hydraulic structures. With this new method, the flux computational interface where the hydraulic structures were located was stratified vertically into multiple layers according to the dimensions of the structures, and the flux through each layer was solved with an HLLC solver for the SWEs. The model demonstrated excellent performance that was validated with flume experiments and analytical solutions. When applied to Nansi Lake, the method was used to effectively simulate large-scale flows with complex structures, offering a robust tool for flood management and infrastructure planning.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106641"},"PeriodicalIF":4.6,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144858200","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":"Exploring Kolmogorov-Arnold neural networks for hybrid and transparent hydrological modeling","authors":"Xin Jing,&nbsp;Xue Yang,&nbsp;Jungang Luo,&nbsp;Ganggang Zuo","doi":"10.1016/j.envsoft.2025.106648","DOIUrl":"10.1016/j.envsoft.2025.106648","url":null,"abstract":"<div><div>The limited interpretability of deep learning models poses challenges for their integration into process-based hydrological frameworks. To explore potential solutions, we develop K50, a hybrid model that incorporates Kolmogorov–Arnold Networks (KAN) into the Exp-Hydro model. Based on the CAMELS dataset, this study undertakes the following investigations. First, we compare the predictive performance of K50 with that of the Multilayer Perceptron (MLP)-based hybrid model. Second, we visualize the KAN's activation functions to reveal the functional relationships between key input variables and runoff generation. Third, we apply symbolic regression to these functions to derive basin-specific empirical formulas. The results indicate that K50 achieves predictive accuracy comparable to the MLP-based model, while offering an interpretable representation of internal processes. The empirical functions derived from KAN can provide simplified expressions that support physical reasoning. These findings suggest that KAN has the potential to contribute to more interpretable and transparent hybrid hydrological modeling.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106648"},"PeriodicalIF":4.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829019","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":"Uncertainty propagation analysis of remote sensing data in a coupled crop-radiative transfer model using particle filter and winding stairs","authors":"Amit Weinman ,&nbsp;Raphael Linker ,&nbsp;Offer Rozenstein","doi":"10.1016/j.envsoft.2025.106645","DOIUrl":"10.1016/j.envsoft.2025.106645","url":null,"abstract":"<div><div>Crop models can serve as decision-support tools, but their uncertainty must be accounted for. While previous research has shown effective calibration of crop models using remote sensing (RS) data, the remaining uncertainty is rarely quantified. This study investigated the propagation of errors associated with RS data in a coupled crop-radiative transfer model in two steps. First, the results of a Particle Filter (PF) process were examined to assess the uncertainty of the model parameters and outputs. Next, the Winding Stairs (WS) method was used to quantify the contribution of crop model parameters uncertainty to the total model uncertainty. The results show that parameters related to crop growth rate contribute more to the variance of simulated Leaf Area Index (LAI) and yield than the phenology-related parameters. These findings can guide future research to improve the model reliability by focusing on calibrating the parameters with a higher impact on model outcome uncertainty.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106645"},"PeriodicalIF":4.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144863459","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":"Comparative performance of AI and numerical models in forecasting typhoon-induced waves","authors":"Chunxiao Wang ,&nbsp;Huaming Yu ,&nbsp;Fuxin Niu ,&nbsp;Xun Gong ,&nbsp;Shouwen Qiao ,&nbsp;Xin Qi","doi":"10.1016/j.envsoft.2025.106646","DOIUrl":"10.1016/j.envsoft.2025.106646","url":null,"abstract":"<div><div>Accurately forecasting typhoon-induced waves remains a significant challenge in marine disaster prevention and mitigation. Traditional numerical models, based on the Navier-Stokes equations, face inherent limitations in accurately capturing wave dynamics, particularly under complex conditions like typhoons. These models struggle with wind data inaccuracies and complex ocean topography. In contrast, this study designs a novel AI-driven deep learning model (LSTM-Self Attention-Dense), leveraging four decades of satellite altimeter data to significantly enhance prediction accuracy. Through three deep learning experiments and four numerical simulations, the model's performance is evaluated against traditional methods. The results demonstrate that the deep learning model significantly reduces prediction errors, achieving a 26.63 % reduction in root mean square error (RMSE) and an 87.91 % reduction in bias, particularly in high sea conditions. These findings underscore the clear advantages of AI-driven approaches over traditional numerical models, providing a valuable enhancement for improving the accuracy and reliability of marine forecasting.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106646"},"PeriodicalIF":4.6,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144863460","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":"Multi-step ahead probabilistic runoff forecasting with SHAP interpretability: a GPR-enhanced deep learning ensemble approach integrating teleconnection factors","authors":"Feilin Zhu ,&nbsp;Tiantian Hou ,&nbsp;Ou Zhu ,&nbsp;Yitong Sun ,&nbsp;Weifeng Liu ,&nbsp;Lingqi Zhao ,&nbsp;Xuning Guo ,&nbsp;Min Li ,&nbsp;Ping-an Zhong","doi":"10.1016/j.envsoft.2025.106647","DOIUrl":"10.1016/j.envsoft.2025.106647","url":null,"abstract":"<div><div>Accurate medium and long-term runoff forecasting is of paramount importance for scientific water reservoir scheduling, mitigating flood and drought disasters, and promoting water resource planning and management. To enhance forecasting accuracy in river basins, this study introduces an integrated framework for probabilistic forecasting based on a multi-deep learning model ensemble with interpretable analysis. Initially, a multi-round iterative selection method identifies pivotal predictors from 130 climate circulation indices, with SHAP (SHapley Additive exPlanations) analysis revealing ENSO indices as dominant hydrological controls. Recognizing the limitations of single deep learning models in capturing runoff nonlinearity, an enhanced Bidirectional Long Short-Term Memory (BiLSTM) architecture is developed from the LSTM foundation. Subsequently, Convolutional Neural Networks (CNNs) and Attention mechanisms are progressively integrated, where the dominance of ENSO indices enables targeted extraction of high-impact climate signals, substantially improving prediction robustness. The screened teleconnection factors and runoff series serve as inputs to the CNN-BiLSTM-Attention ensemble model, generating deterministic runoff forecasts for 1–12 months ahead. Gaussian Process Regression (GPR) quantifies prediction uncertainty to produce interval probabilistic forecasts, while SHAP deciphers key driving factors, demonstrating that ENSO contributions are central to reducing prediction errors through interpretable feature attribution. Evaluated via comprehensive deterministic and probabilistic metrics in China's Yalong River Basin, the ensemble model achieves superior accuracy with highly reliable probabilistic intervals. Critically, the interpretable linkage between ENSO dominance and model performance validates that climate-informed deep learning synthesizes physical insights with data-driven advantages. This synergy—spanning dynamic factor screening, hybrid architecture design, uncertainty quantification, and explainable AI—provides actionable insights for climate-resilient flood control, water allocation, and ecosystem management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106647"},"PeriodicalIF":4.6,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144809588","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":"Impact of drought on de facto reuse and water quality in Lake Mead: Insights from hydrodynamic modeling versus machine learning","authors":"Charlotte van der Nagel ,&nbsp;Emily Clements ,&nbsp;Carissa Wilkerson ,&nbsp;Deena Hannoun ,&nbsp;Todd Tietjen","doi":"10.1016/j.envsoft.2025.106649","DOIUrl":"10.1016/j.envsoft.2025.106649","url":null,"abstract":"<div><div>De facto reuse (DFR), where wastewater effluent is present at a drinking water source, can elevate levels of anthropogenic chemicals and pathogens. Wastewater effluent can travel through the water column as a well-defined plume, owing to density differences. This study evaluated the complex effects of drought on plume behavior and water quality in Lake Mead, an arid reservoir in the southwestern United States, using a hydrodynamic model, and compared its performance to a simpler machine learning model. Water quality remained high despite lake elevation declines if in-and outflow rates were maintained. DFR fluctuated seasonally following the plume entrainment depth in the lake thermal structure, with decreased lake elevation shifting peak DFR to occur earlier in the year. Though the hydrodynamic model (relative root mean square error (RRMSE) = 6.7 %) slightly outperformed the machine learning model (RRMSE = 10.8 %), both models can aid treatment and management decisions by predicting DFR at (drinking) water infrastructure.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106649"},"PeriodicalIF":4.6,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861251","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":"Moving from single values to trade-off curves for assessing the performance of water resources systems under uncertainty","authors":"Yuan Cao ,&nbsp;Wenyan Wu ,&nbsp;Holger R. Maier ,&nbsp;Matt S. Gibbs","doi":"10.1016/j.envsoft.2025.106644","DOIUrl":"10.1016/j.envsoft.2025.106644","url":null,"abstract":"<div><div>Water resources management under uncertainty is made difficult by the subjective judgements that have to be made using current methods. This paper addresses this issue by introducing a method that eliminates the need to pre-select performance values of water resources systems from a distribution based on risk appetite. Instead, the entire trade-off curve between risk appetite and performance is considered. This enables more informed decision-making, as it will identify whether (i) a solution is always better/worse than another, irrespective of risk appetite, thereby removing any subjectivity or doubt from the decision-making process, or (ii) a solution performs better than another for some risk appetite levels but worse for others, enabling a more informed solution choice based on full knowledge of the nature of the trade-off between risk appetite and performance. The utility of the proposed approach is confirmed via a case study of a reservoir system in China.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106644"},"PeriodicalIF":4.6,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144809575","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}