Environmental Modelling & Software最新文献_第2页

A physics-constrained deep learning framework for actual evapotranspiration estimation using ground station observations and remote sensing data 使用地面站观测和遥感数据估算实际蒸散发的物理约束深度学习框架

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-19 DOI: 10.1016/j.envsoft.2025.106585

Lingyue Wang , Ping Hu , Hongwei Zheng , Jie Bai , Ying Liu , Xingwen Cao , Olaf Hellwich , Tie Liu , Anming Bao , Xi Chen

{"title":"A physics-constrained deep learning framework for actual evapotranspiration estimation using ground station observations and remote sensing data","authors":"Lingyue Wang , Ping Hu , Hongwei Zheng , Jie Bai , Ying Liu , Xingwen Cao , Olaf Hellwich , Tie Liu , Anming Bao , Xi Chen","doi":"10.1016/j.envsoft.2025.106585","DOIUrl":"10.1016/j.envsoft.2025.106585","url":null,"abstract":"<div><div>Evapotranspiration (ET) is a key process in the water cycle. While machine learning-based methods have been increasingly applied to ET estimation, they typically neglect physical mechanisms and ecological impacts. This study proposes a physics-constrained hybrid model (TST-PHY) that incorporates Penman-Monteith-derived physical knowledge into the time series transformer (TST). The framework integrates Bayesian optimization to automatically determine optimal weights for physical mechanisms within the data-driven modeling workflow. The arid and semi-arid regions of Northern China (ASNC) were chosen as the study area, and our results show that the proposed framework optimally balances estimation error and the physical law, with value and trend constraint weights of 0.26 and 0.41, respectively. Moreover, proper physical constraints can improve the prediction accuracy, generalization, and physical consistency of TST-PHY at various spatiotemporal scales. In conclusion, this study establishes a novel paradigm for evapotranspiration estimation in data-sparse regions through the synergistic integration of data-driven and knowledge-based models.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106585"},"PeriodicalIF":4.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337848","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

Machine learning-driven regional prediction of PM2.5 concentrations in the eastern mediterranean bridging spatial data gaps in air quality monitoring 机器学习驱动的东地中海PM2.5浓度区域预测弥合空气质量监测的空间数据差距

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-19 DOI: 10.1016/j.envsoft.2025.106586

İrde Çeti̇ntürk Gürtepe , İsmail Tarık Şenkal , Alper Ünal , Gülen Güllü , Yeşer Aslanoğlu , Julian D. Marshall

{"title":"Machine learning-driven regional prediction of PM2.5 concentrations in the eastern mediterranean bridging spatial data gaps in air quality monitoring","authors":"İrde Çeti̇ntürk Gürtepe , İsmail Tarık Şenkal , Alper Ünal , Gülen Güllü , Yeşer Aslanoğlu , Julian D. Marshall","doi":"10.1016/j.envsoft.2025.106586","DOIUrl":"10.1016/j.envsoft.2025.106586","url":null,"abstract":"<div><div>Fine particulate matter (PM<sub>2.5</sub>) posing significant risks due to its ability to penetrate deep into the respiratory system. This study introduces the Regional PM<sub>2.5</sub> Predictor (RPP), a machine learning-based framework designed to estimate PM<sub>2.5</sub> concentrations across Turkiye, especially in regions with limited PM<sub>2.5</sub> monitoring infrastructure. Leveraging satellite-derived Aerosol Optical Thickness (AOT) data, meteorological variables from ERA-5, and ground-based air quality measurements, the model integrates diverse datasets spanning 2018 to 2023, the RPP employs XGBoost algorithms to address spatial monitoring gaps. The model demonstrates strong predictive performance across multiple evaluation scenarios: the seasonal analysis yielded RMSE values of 4.39–10.01 μg/m<sup>3</sup> and R<sup>2</sup> values of 0.66–0.84; temporal evaluations achieved an average RMSE of 8.28 μg/m<sup>3</sup> and R<sup>2</sup> of 0.76; spatial (station-blinded) cross-validation maintained reliable predictions with average RMSE of 9.21 μg/m<sup>3</sup> and R<sup>2</sup> of 0.71; while random sampling achieved RMSE of 6.82 μg/m<sup>3</sup> and R<sup>2</sup> of 0.85 with an 80-20 % split. The framework successfully captured Turkiye's air quality trend, with PM<sub>2.5</sub> levels decreasing from 25.52 μg/m<sup>3</sup> (2018) to 18.88 μg/m<sup>3</sup> (2023), while identifying performance variations across diverse topographical regions. The model demonstrated remarkable stability during the COVID-19 pandemic period, achieving its best performance in 2020 (RMSE: 7.54 μg/m<sup>3</sup>, R<sup>2</sup>: 0.80). This approach demonstrates how machine learning can complement traditional monitoring networks, providing cost-effective air quality assessments for public health interventions and environmental policy evaluation.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106586"},"PeriodicalIF":4.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337847","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

New GIS tools for wind fetch analysis: A case study of changes in wave exposure in Isfjorden (Svalbard) due to reduced fast ice coverage 用于风获取分析的新GIS工具：Isfjorden （Svalbard）因快速冰覆盖减少而导致的波浪暴露变化的案例研究

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-19 DOI: 10.1016/j.envsoft.2025.106584

Jacek Andrzej Urbański

引用次数: 0

Integrating remote sensing data with watershed-scale ecohydrological modeling in diverse forest and agricultural landscapes of the Upper Mississippi River Basin 遥感与流域尺度生态水文模型在密西西比河上游不同森林和农业景观中的整合

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-19 DOI: 10.1016/j.envsoft.2025.106588

Avay Risal , Ritesh Karki , Junyu Qi

{"title":"Integrating remote sensing data with watershed-scale ecohydrological modeling in diverse forest and agricultural landscapes of the Upper Mississippi River Basin","authors":"Avay Risal , Ritesh Karki , Junyu Qi","doi":"10.1016/j.envsoft.2025.106588","DOIUrl":"10.1016/j.envsoft.2025.106588","url":null,"abstract":"<div><div>The spatial misalignment between natural watershed boundaries and grid-based remote sensing data poses challenges for incorporating spatially distributed observations into watershed-scale modeling frameworks. To tackle this, we developed a comprehensive SWAT model for the Upper Mississippi River Basin, utilizing USDA-delineated HUC (Hydrologic Unit Code)-12 subbasins (∼100 km<sup>2</sup>), to enable effective integration of remotely sensed evapotranspiration (ET), leaf area index (LAI), and net primary productivity (NPP). To improve accuracy, land use types—forests, crops, and grasslands—were clustered based on climatic and geological characteristics. Following calibration and validation from 1990 to 2020, the model exhibited robust performance, achieving R<sup>2</sup> and NSE values greater than 0.75 and maintaining percent bias below 25 % for ET, LAI, and NPP across nearly 5,000 subbasins. Additionally, simulated crop yields closely matched USDA observations. These findings highlight the effectivenes of a HUC-12-based model for simulating water and carbon fluxes across diverse landscapes using remote sensing data.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106588"},"PeriodicalIF":4.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337846","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

Improving current forecast by Leveraging Measured Data and numerical models via LiESNs 通过LiESNs利用测量数据和数值模型改进当前预测

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-18 DOI: 10.1016/j.envsoft.2025.106556

Felipe M. Moreno , Marcel R. de Barros , Artur Jordão , Marlon S. Mathias , Marcelo Dottori , Anna H. Reali Costa , Edson S. Gomi , Fabio G. Cozman , Eduardo A. Tannuri

引用次数: 0

Improved TDS forecasting in data-scarce regions using CEEMDAN and AI-driven hydro-climatic analysis 利用CEEMDAN和人工智能驱动的水文气候分析改进数据稀缺地区TDS预测

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-06-18 DOI: 10.1016/j.envsoft.2025.106560

Maryam Sayadi , Behzad Hessari , Majid Montaseri , Amir Naghibi

{"title":"Improved TDS forecasting in data-scarce regions using CEEMDAN and AI-driven hydro-climatic analysis","authors":"Maryam Sayadi , Behzad Hessari , Majid Montaseri , Amir Naghibi","doi":"10.1016/j.envsoft.2025.106560","DOIUrl":"10.1016/j.envsoft.2025.106560","url":null,"abstract":"<div><div>Total dissolved solids (TDS) are a key water quality parameter, reflecting the concentration of dissolved salts in aquatic systems. Accurate TDS forecasting is essential for sustainable water resource management, particularly in data-scarce regions. This study proposes a novel and generalized AI-based framework to forecast TDS up to six months ahead using a limited set of hydro-climatic input variables. The methodology combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for signal denoising and pattern extraction with advanced machine learning models, including Random Forest (RF) and a hybrid Grey Wolf Optimization–Support Vector Machine (GWO-SVM). To enhance model transferability, only four widely available input variables—precipitation, evaporation, discharge, and chloride concentration—were used. Historical data from 1975 to 2016 were collected from three hydrometric stations representing distinct climatic conditions. Forecasting was conducted both with and without the inclusion of lagged TDS values. The CEEMDAN-GWO-Linear SVM model achieved high accuracy (R<sup>2</sup> = 0.70–0.96) across different forecast horizons. Additionally, CEEMDAN significantly improved the predictive performance of both SVM and RF models. Feature importance analysis using RF ranked chloride concentration, discharge, precipitation, and evaporation as the most influential variables in TDS prediction. The proposed framework offers a robust, data-efficient solution for mid-term water quality forecasting.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106560"},"PeriodicalIF":4.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337850","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

Generating three-dimensional soil organic carbon density dataset by soil depth function and correction methods in Yangtze River Delta, China 基于土壤深度函数和校正方法的长三角三维土壤有机碳密度数据集

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.2025.106582

Shurui Lin , Qing Zhu , Beini Yin , Guishan Yang , Kaihua Liao , Xiaoming Lai , Changqiang Guo

{"title":"Generating three-dimensional soil organic carbon density dataset by soil depth function and correction methods in Yangtze River Delta, China","authors":"Shurui Lin , Qing Zhu , Beini Yin , Guishan Yang , Kaihua Liao , Xiaoming Lai , Changqiang Guo","doi":"10.1016/j.envsoft.2025.106582","DOIUrl":"10.1016/j.envsoft.2025.106582","url":null,"abstract":"<div><div>Accurate, high resolution, and depth continuous soil organic carbon density (SOCD) dataset is crucial for various research and management practices. Based on 593 soil samples, we tested different soil depth functions and correction methods for generating the 0–1.0 m three-dimensional SOCD dataset with the spatial resolution of 90-m in the Yangtze River Delta region. Depth functions (power function, exponential decay function, logarithmic function and inverse function) were fitted for different samples in the training set, and their obtained parameters were mapped by random forest based on ancillary variables. Then three correction methods, including coefficient scaling, data fusion and residual correction, were applied in the validation set to correct the predictions of depth functions. After correcting, the prediction accuracies have been significantly improved at all depths. Our dataset can generate accurate SOCD maps at any specific depth interval by constructing the vertical continuous distribution of the corrected coefficients.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106582"},"PeriodicalIF":4.8,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331412","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

FIMserv v.1.0: A tool for streamlining Flood Inundation Mapping (FIM) using the United States operational hydrological forecasting framework FIMserv .1.0：使用美国业务水文预报框架简化洪水淹没制图（FIM）的工具

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.2025.106581

Anupal Baruah , Supath Dhital , Sagy Cohen , Thanh Nhan Duc Tran , Hesham Elhaddad , C. Lyn Watts , Dipsikha Devi , Yixian Chen , Carson Pruitt

{"title":"FIMserv v.1.0: A tool for streamlining Flood Inundation Mapping (FIM) using the United States operational hydrological forecasting framework","authors":"Anupal Baruah , Supath Dhital , Sagy Cohen , Thanh Nhan Duc Tran , Hesham Elhaddad , C. Lyn Watts , Dipsikha Devi , Yixian Chen , Carson Pruitt","doi":"10.1016/j.envsoft.2025.106581","DOIUrl":"10.1016/j.envsoft.2025.106581","url":null,"abstract":"<div><div>In the United States, the National Oceanic and Atmospheric Administration-Office of Water Prediction (NOAA-OWP) utilizes the National Water Model (NWM) for operational hydrological forecasting. Its Flood Inundation Mapping (FIM) framework translates NWM discharge to inundation extent using the Height Above the Nearest Drainage (HAND) approach. The simplicity of the OWP HAND-FIM framework enables rapid, large-scale FIM predictions across the U.S., fostering a growing user and developer community beyond NOAA. In this paper, we introduce “FIM as a Service (FIMserv)”, an open-source toolset that streamlines OWP HAND-FIM predictions with enhanced functionalities: (1) FIM generation from retrospective and forecasted NWM discharge, (2) Simultaneous simulations of multiple watersheds for various flood events, (3) FIM from Group on Earth Observations Global Water Sustainability (GeoGLOWS) discharge, (4) evaluation of NWM and GeoGLOWS discharge against USGS observations. FIMserv operates as a standalone notebook on local/cloud systems and as a Community Resource within the CIROH cloud cyberinfrastructure.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106581"},"PeriodicalIF":4.8,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331413","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

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