Environmental Modelling & Software最新文献_第6页

Bayesian calibration of a 2D hydraulic model using a convolutional neural network emulator 基于卷积神经网络仿真器的二维水工模型贝叶斯校正

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-23 DOI: 10.1016/j.envsoft.2025.106621

Jose Zevallos , Eduardo Chávarri-Velarde , Ronald R. Gutierrez , Waldo Lavado-Casimiro

{"title":"Bayesian calibration of a 2D hydraulic model using a convolutional neural network emulator","authors":"Jose Zevallos , Eduardo Chávarri-Velarde , Ronald R. Gutierrez , Waldo Lavado-Casimiro","doi":"10.1016/j.envsoft.2025.106621","DOIUrl":"10.1016/j.envsoft.2025.106621","url":null,"abstract":"<div><div>This study presents a Bayesian calibration framework for 2D hydraulic models using convolutional neural networks (CNNs) as surrogate emulators of TELEMAC-2D. Applied to the Lower Piura River Basin in northern Peru, the method estimates spatially distributed Manning’s roughness coefficients while accounting for structural model error. A CNN trained on a simulation ensemble predicts flood depth under varying roughness scenarios, enabling substantial computational savings. The emulator is embedded in a Bayesian inference scheme with a Gaussian Process discrepancy model to capture systematic deviations. Validation with synthetic scenarios demonstrates accurate roughness retrieval in hydraulically sensitive areas. Additionally, a real-case validation was performed using PeruSAT-1, a high-resolution Earth observation satellite operated by the Peruvian Space Agency (CONIDA), acquired during the 04/10/2017 flood. This confirmed the framework’s ability to reproduce observed depth patterns under data scarcity. The method provides a scalable solution for parameter inference in flood-prone regions where conventional validation approaches remain limited.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106621"},"PeriodicalIF":4.8,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703881","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

A review of economic calibrated mathematical programming models for agricultural water reallocation 农业用水再分配的经济校准数学规划模型综述

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-19 DOI: 10.1016/j.envsoft.2025.106628

Giammauro Soriano , Francesco Sapino , C. Dionisio Pérez-Blanco

引用次数: 0

A novel salient object detection network for burned area segmentation in high-resolution remote sensing images 一种新的高分辨率遥感图像烧伤区域分割显著目标检测网络

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-19 DOI: 10.1016/j.envsoft.2025.106629

Yuxiang Fu, Wei Fang

{"title":"A novel salient object detection network for burned area segmentation in high-resolution remote sensing images","authors":"Yuxiang Fu, Wei Fang","doi":"10.1016/j.envsoft.2025.106629","DOIUrl":"10.1016/j.envsoft.2025.106629","url":null,"abstract":"<div><div>Burned area segmentation (BAS) in remote sensing images (RSIs) is critical for forest fire monitoring, as it helps locate and extract damaged areas, providing a scientific basis for post-disaster recovery. However, existing BAS methods underperform on high-resolution RSIs due to diluted location information and blurred edges during sampling. To this, we propose PANet, a novel salient object detection (SOD) network designed for BAS in high-resolution RSIs. PANet introduces two key modules: Path Aggregation Decoder (PAD) and Progressive Multi-level Aggregation Predictor (PMAP). PAD integrates multi-level features for richer semantics, using detail feature flow to enhance edge quality and refined location feature flow to improve spatial accuracy. PMAP progressively fuses features from PAD to predict saliency maps, leveraging higher-level features to complement lower-level ones. We also constructed a new dataset for high-resolution BAS. Experiments on two BAS datasets show that PANet outperforms state-of-the-art methods. Code is available at: <span><span>https://github.com/Voruarn/PANet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106629"},"PeriodicalIF":4.8,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664916","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

Agent-Based Modelling of food systems: A scoping review on incorporation of behavioural insights 基于主体的粮食系统建模：对纳入行为见解的范围审查

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-18 DOI: 10.1016/j.envsoft.2025.106617

Alexander Öttl, Mette Termansen

引用次数: 0

Monitoring carbon dynamics and driving forces in arid and semi-arid river basin: A case study of China's West Liao river Basin 干旱区半干旱区河流流域碳动态及驱动力监测——以中国西辽河流域为例

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-15 DOI: 10.1016/j.envsoft.2025.106625

Yuxia Hu , Jirui Gong , Siqi Zhang , Weiyuan Zhang , Xuede Dong , Guisen Yang , Chenyi Yan , Yingying Liu

{"title":"Monitoring carbon dynamics and driving forces in arid and semi-arid river basin: A case study of China's West Liao river Basin","authors":"Yuxia Hu , Jirui Gong , Siqi Zhang , Weiyuan Zhang , Xuede Dong , Guisen Yang , Chenyi Yan , Yingying Liu","doi":"10.1016/j.envsoft.2025.106625","DOIUrl":"10.1016/j.envsoft.2025.106625","url":null,"abstract":"<div><div>Accurate estimation of ecosystem carbon stocks and their dynamics and exploration of their drivers will contribute to the sustainable management of carbon neutrality. We combined field measurements in China's West Liao River Basin with the improved Terrestrial Ecosystem Regional (TECO-R) model to quantify the carbon pools and carbon turnover time from 2000 to 2021. Ecosystem carbon density averaged 3.65 kg C m<sup>−2</sup>; soil carbon pools accounted for about 80 %. Forests are major contributors to carbon sinks. The turnover times in the leaf, root, and soil carbon pools and the whole ecosystem were 0.54, 5.26, 42.76, and 23.31 years, respectively, depended on elevation and vegetation type. Although warming and increased precipitation promoted vegetation carbon accumulation, this increase was offset by a more substantial loss of soil organic carbon, the entire ecosystem (e<sub>c</sub>) decreased at an average rate of 84.21 g C m<sup>−2</sup> yr<sup>−1</sup>, mainly due to enhanced soil carbon loss. Precipitation significantly affects the e<sub>c</sub> in arid and semi-arid river basin; human activities and the natural environment also directly or indirectly influenced the evolution of e<sub>c</sub>. Our hybrid modeling framework enables spatially explicit assessment of carbon dynamics and provides a transferable approach for management, and guide nature-based climate solutions in fragile ecosystems.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106625"},"PeriodicalIF":4.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664921","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

Unravelling spatiotemporal patterns of event-based surface rainfall-runoff response using a cellular automata approach 利用元胞自动机方法揭示基于事件的地表降雨径流响应的时空模式

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-15 DOI: 10.1016/j.envsoft.2025.106623

Lidan Zhang , Yuming Wang , Xiaohong Chen

{"title":"Unravelling spatiotemporal patterns of event-based surface rainfall-runoff response using a cellular automata approach","authors":"Lidan Zhang , Yuming Wang , Xiaohong Chen","doi":"10.1016/j.envsoft.2025.106623","DOIUrl":"10.1016/j.envsoft.2025.106623","url":null,"abstract":"<div><div>Understanding surface water flow is critical for hydrological modeling and water resource management. Distributed hydrological models capture spatial heterogeneity in surface runoff, yet their full potential, especially in simulating surface flow complexities, requires further exploration. To bridge this gap, we developed the Surface Rainfall-Runoff Cellular Automata (SRRCA) model, a distributed hydrological framework featuring a Local-Finer Iteration (LFI) strategy to mitigate evolution errors from varying iteration steps. Implemented in a watershed in Wharfedale, England, the SRRCA model leverages multi-scale capabilities to resolve catchment-scale runoff dynamics and grid-scale flow interactions. Results indicated significant infiltration fluctuations in early rainfall due to spatial heterogeneity, alongside a strong correlation between peak flow and catchment size. Cells near confluence points exhibit delayed peaks, highlighting the influence of spatial position on runoff. This study systematically evaluates the strengths and limitations of cellular automata in hydrological modeling, and introduces a novel paradigm for investigating spatial heterogeneity in hydrology.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106623"},"PeriodicalIF":4.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664772","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

VegRecoverAI: A deep learning-based system for automated vegetation recovery assessment and prediction with demonstration case study on gas pipeline construction VegRecoverAI：基于深度学习的自动植被恢复评估和预测系统，并以天然气管道建设为例进行了示范研究

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-15 DOI: 10.1016/j.envsoft.2025.106601

Alessandro Galdelli , Simone Pesaresi , Giacomo Quattrini , Roberto Pierdicca , Amal Benson Thaliath , Adriano Mancini

{"title":"VegRecoverAI: A deep learning-based system for automated vegetation recovery assessment and prediction with demonstration case study on gas pipeline construction","authors":"Alessandro Galdelli , Simone Pesaresi , Giacomo Quattrini , Roberto Pierdicca , Amal Benson Thaliath , Adriano Mancini","doi":"10.1016/j.envsoft.2025.106601","DOIUrl":"10.1016/j.envsoft.2025.106601","url":null,"abstract":"<div><div>Vegetation restoration is crucial for environmental conservation and maintaining ecosystem services. Traditional methods, such as manual inspections and expert photo interpretation, have been widely used to assess vegetation recovery but are labor-intensive, time-consuming, and prone to human bias. In contrast, modern Artificial Intelligence (AI) based methods use satellite imagery for efficient vegetation analysis, enabling large-scale monitoring with minimal human effort. This paper introduces VegRecoverAI, a comprehensive system that leverages multisource satellite data from Landsat, Sentinel-2, and PlanetScope. VegRecoverAI autonomously detects both subtle and significant vegetation changes, providing a reliable alternative to manual assessment. The system extracts NDVI time series data, detects vegetation change and uses an ensemble of forecasting models to predict future vegetation restoration. The system is demonstrated as a case study following gas pipeline construction in Italy. The results indicate that VegRecoverAI is automated and a scalable solution complementary to traditional techniques to support proactive environmental management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106601"},"PeriodicalIF":4.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664728","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

FloodSformer: A transformer-based data-driven model for predicting the 2-D dynamics of fluvial floods flooddsformer：一个基于变压器的数据驱动模型，用于预测河流洪水的二维动态

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-15 DOI: 10.1016/j.envsoft.2025.106599

Matteo Pianforini , Susanna Dazzi , Andrea Pilzer , Renato Vacondio

引用次数: 0

Introducing ‘miniRECgap’ R package for simple gap-filling of missing eddy covariance CO2 flux measurements with classic nonlinear environmental response functions via GUI-supported R-scripts (case-study: In-sample gap-filling with ‘miniRECgap’ vs. MDS and an optimised shallow ANN in a ‘challenging’ peatland ecosystem) 通过gui支持的R脚本，引入“miniRECgap”R包，用于通过经典非线性环境响应函数对缺失的涡流相关CO2通量测量进行简单的间隙填充（案例研究：在“具有挑战性的”泥炭地生态系统中使用“miniRECgap”与MDS和优化的浅神经网络进行样本间隙填充）

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-14 DOI: 10.1016/j.envsoft.2025.106611

Alina Premrov , Jagadeesh Yeluripati , Richard Slevin , Adam Bates , Magdalena Matysek , Stephen Barry , Kenneth A. Byrne , Rowan Fealy , Bernard Hyde , Gary Lanigan , Mark McCorry , Rachael Murphy , Florence Renou-Wilson , Amey Tilak , David Wilson , Matthew Saunders

{"title":"Introducing ‘miniRECgap’ R package for simple gap-filling of missing eddy covariance CO2 flux measurements with classic nonlinear environmental response functions via GUI-supported R-scripts (case-study: In-sample gap-filling with ‘miniRECgap’ vs. MDS and an optimised shallow ANN in a ‘challenging’ peatland ecosystem)","authors":"Alina Premrov , Jagadeesh Yeluripati , Richard Slevin , Adam Bates , Magdalena Matysek , Stephen Barry , Kenneth A. Byrne , Rowan Fealy , Bernard Hyde , Gary Lanigan , Mark McCorry , Rachael Murphy , Florence Renou-Wilson , Amey Tilak , David Wilson , Matthew Saunders","doi":"10.1016/j.envsoft.2025.106611","DOIUrl":"10.1016/j.envsoft.2025.106611","url":null,"abstract":"<div><div>Numerous tools/software exist to gap-fill missing eddy covariance (EC) data, with varying performance depending on study-site dynamics. Disturbed ecosystems like former cutaway-peatlands may be challenging for gap-filling. Researchers using gap-filling spreadsheets may benefit from transitioning to R, but may face challenges if they lack programming skills. To address these, we introduce ‘miniRECgap’, a user-friendly tool in R for effortless gap-filling of <span>EC</span> carbon dioxide flux data using well-known temperature- and light-response functions. ‘miniRECgap’ can model net ecosystem exchange (NEE) via GUI-supported scripts with only five code-lines and minimal inputs. A case-study on one ‘classic’ (forest) and one ‘challenging’ (rehabilitating cutaway-peatland) ecosystem indicated that standard gap-filling (MDS) performed better for the ‘classic’, but not for the ‘challenging’ ecosystem (MDS R<sup>2</sup> = 0.24; ‘miniRECgap’ R<sup>2</sup> = 0.57). For the rehabilitating-peatland, an optimised shallow Artificial Neural Network outperformed other two approaches (R<sup>2</sup> = 0.68). These findings demonstrate the importance of NEE gap-filling for assessing ecosystem-level carbon-dynamics, important for rehabilitating-peatlands.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"193 ","pages":"Article 106611"},"PeriodicalIF":4.8,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664729","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

A mangrove lifecycle ecosystem analysis and forecasting (LEAF) model 红树林生命周期生态系统分析与预测（LEAF）模型

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-07-12 DOI: 10.1016/j.envsoft.2025.106619

Thomas Dunlop , Stefan Felder , William Glamore

引用次数: 0