Environmental Modelling & Software最新文献

英文中文

Revealing the causal response in landslide hydrology with MT-InSAR and spatial-temporal CCM: A case study in Jinsha River

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-20 DOI: 10.1016/j.envsoft.2025.106434

Xiao Ling , Dongping Ming , Zhi Zhang , Jianao Cai , Wenyi Zhao , Mingzhi Zhang , Yongshuang Zhang , Bingbo Gao

Convergent Cross Mapping (CCM) is a powerful tool for analyzing causality in complex dynamic systems. However, standard CCM and Geographical CCM (GCCM) focus exclusively on temporal or spatial attributes, failing to integrate both dimensions. This study introduces a spatial-temporal CCM that quantifies the state of convergence to enable batched analyses of large-scale spatial datasets. The proposed method captures variations in causality and delayed responses across different spatial locations, thereby enhancing spatial-temporal data utility and the efficiency of causal inference. Using this model, we analyzed the relationship between landslides and hydrology. The results revealed that Areas with High Displacement (AHDs) responded more rapidly to hydrological factors than stable regions, with deep-layer soil moisture (100–289 cm depth) exhibiting the strongest causality and the fastest response. Building on these findings, we identified zones of minimal instability within each AHD (areas that displayed the quickest response to hydrological changes).

{"title":"Revealing the causal response in landslide hydrology with MT-InSAR and spatial-temporal CCM: A case study in Jinsha River","authors":"Xiao Ling , Dongping Ming , Zhi Zhang , Jianao Cai , Wenyi Zhao , Mingzhi Zhang , Yongshuang Zhang , Bingbo Gao","doi":"10.1016/j.envsoft.2025.106434","DOIUrl":"10.1016/j.envsoft.2025.106434","url":null,"abstract":"<div><div>Convergent Cross Mapping (CCM) is a powerful tool for analyzing causality in complex dynamic systems. However, standard CCM and Geographical CCM (GCCM) focus exclusively on temporal or spatial attributes, failing to integrate both dimensions. This study introduces a spatial-temporal CCM that quantifies the state of convergence to enable batched analyses of large-scale spatial datasets. The proposed method captures variations in causality and delayed responses across different spatial locations, thereby enhancing spatial-temporal data utility and the efficiency of causal inference. Using this model, we analyzed the relationship between landslides and hydrology. The results revealed that Areas with High Displacement (AHDs) responded more rapidly to hydrological factors than stable regions, with deep-layer soil moisture (100–289 cm depth) exhibiting the strongest causality and the fastest response. Building on these findings, we identified zones of minimal instability within each AHD (areas that displayed the quickest response to hydrological changes).</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106434"},"PeriodicalIF":4.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705314","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

pytRIBS: An open, modular, and reproducible python-based framework for distributed hydrologic modeling

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-19 DOI: 10.1016/j.envsoft.2025.106432

L. Wren Raming , Enrique R. Vivoni , C. Josh Cederstrom , M. Akram Hossain , Jose A. Becerra

Distributed hydrologic models (DHM) are essential tools for understanding how and where water moves through a landscape. However, DHMs can be time-consuming and challenging to setup, limiting their application. Here, we present pytRIBS, a tool that addresses these challenges for the TIN-based Real-time Integrated Basin Simulator (tRIBS). pytRIBS is an open-source Python package with an object-oriented design intended to initialize, execute, and analyze tRIBS simulations. This package mirrors a tRIBS workflow with five preprocessing classes (Project, Mesh, Soil, Land, and Met) that can be used together or separately to obtain and convert data into a tRIBS format. Finally, the Results class manages outputs, provides analytical tools, and visualizes results. We illustrate these capabilities with an example case study of the Newman Canyon watershed, AZ, USA.

引用次数: 0

A machine learning model integrating spatiotemporal attention and residual learning for predicting periodic air pollutant concentrations

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-18 DOI: 10.1016/j.envsoft.2025.106438

Farun An , Dong Yang , Xiaoyue Sun , Haibin Wei , Feilong Chen

The variations in pollutant concentrations during tunnel construction, in urban atmosphere, and along pedestrian paths exhibit distinct periodicity. Accurate prediction of pollutant concentrations is crucial for improving the quality of the construction and living environments. Using tunnel construction scenarios as a case, this study proposes a Convolutional Neural Network and Bidirectional Long Short-Term Memory model (CNN-BiLSTM) integrating spatiotemporal attention mechanisms and residual learning. The model employs experimental and field measurement data, with Pearson correlation analysis used for preliminary data screening. The proposed model was evaluated using eight specific metrics and compared against eight baseline models. The model exhibited strong predictive performance, with R² of 0.9826 for CO and 0.9844 for PM_2.5. For 15-step CO predictions, R² was 0.9584 with MSE of 0.031. Urban-scale predictions showed R² of 0.9599 for CO and 0.9774 for PM_2.5, while traffic-related predictions were 0.9316 for CO and 0.9525 for PM_2.5, indicating improved accuracy and applicability.

{"title":"A machine learning model integrating spatiotemporal attention and residual learning for predicting periodic air pollutant concentrations","authors":"Farun An , Dong Yang , Xiaoyue Sun , Haibin Wei , Feilong Chen","doi":"10.1016/j.envsoft.2025.106438","DOIUrl":"10.1016/j.envsoft.2025.106438","url":null,"abstract":"<div><div>The variations in pollutant concentrations during tunnel construction, in urban atmosphere, and along pedestrian paths exhibit distinct periodicity. Accurate prediction of pollutant concentrations is crucial for improving the quality of the construction and living environments. Using tunnel construction scenarios as a case, this study proposes a Convolutional Neural Network and Bidirectional Long Short-Term Memory model (CNN-BiLSTM) integrating spatiotemporal attention mechanisms and residual learning. The model employs experimental and field measurement data, with Pearson correlation analysis used for preliminary data screening. The proposed model was evaluated using eight specific metrics and compared against eight baseline models. The model exhibited strong predictive performance, with R<sup>2</sup> of 0.9826 for CO and 0.9844 for PM<sub>2.5</sub>. For 15-step CO predictions, R<sup>2</sup> was 0.9584 with MSE of 0.031. Urban-scale predictions showed R<sup>2</sup> of 0.9599 for CO and 0.9774 for PM<sub>2.5</sub>, while traffic-related predictions were 0.9316 for CO and 0.9525 for PM<sub>2.5</sub>, indicating improved accuracy and applicability.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106438"},"PeriodicalIF":4.8,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678381","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

Carbon emissions prediction based on ensemble models: An empirical analysis from China

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-18 DOI: 10.1016/j.envsoft.2025.106437

Song Hu , Shixuan Li , Lin Gong , Dan Liu , Zhe Wang , Gangyan Xu

The global warming problem has seriously threatened the sustainable development of human society. In order to effectively control carbon emissions, this study integrates economic, social, energy, and environment (ESEE) factors to develop a comprehensive, multi-dimensional carbon emissions prediction (CEP) index system, crucial for analyzing the determinants of carbon emissions and forecasting future emissions. Then employ a grey correlation analysis (GRA), followed by a genetic algorithm-based (GA-based) feature extraction method to demonstrate the strong correlation between selected factors and carbon emissions and refine the input of single and ensemble machine learning models for predicting carbon emissions in China. The number of selected economic factors is the highest, followed by energy factors, with only one social and environmental factors being selected. Meanwhile, the prediction results show that Bagging-ANN outperforms other algorithms with the lowest R² value of 0.8792, followed by Voting, Stacking, ANN, Bagging-SVR and SVR.

{"title":"Carbon emissions prediction based on ensemble models: An empirical analysis from China","authors":"Song Hu , Shixuan Li , Lin Gong , Dan Liu , Zhe Wang , Gangyan Xu","doi":"10.1016/j.envsoft.2025.106437","DOIUrl":"10.1016/j.envsoft.2025.106437","url":null,"abstract":"<div><div>The global warming problem has seriously threatened the sustainable development of human society. In order to effectively control carbon emissions, this study integrates economic, social, energy, and environment (ESEE) factors to develop a comprehensive, multi-dimensional carbon emissions prediction (CEP) index system, crucial for analyzing the determinants of carbon emissions and forecasting future emissions. Then employ a grey correlation analysis (GRA), followed by a genetic algorithm-based (GA-based) feature extraction method to demonstrate the strong correlation between selected factors and carbon emissions and refine the input of single and ensemble machine learning models for predicting carbon emissions in China. The number of selected economic factors is the highest, followed by energy factors, with only one social and environmental factors being selected. Meanwhile, the prediction results show that Bagging-ANN outperforms other algorithms with the lowest R<sup>2</sup> value of 0.8792, followed by Voting, Stacking, ANN, Bagging-SVR and SVR.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106437"},"PeriodicalIF":4.8,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143684795","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 Australian forest fire rate of spread models using VIIRS satellite observations 利用 VIIRS 卫星观测数据评估澳大利亚森林火灾蔓延速度模型

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-17 DOI: 10.1016/j.envsoft.2025.106436

Matthew G. Gale, Geoffrey J. Cary

Accurate prediction of head-fire rate of spread is essential to fire management decisions during wildfires, however, evaluation of existing models is limited. Acquisition of reliable rate of spread observations for model evaluation is a key challenge, since wildfires are typically rare and difficult to monitor. We applied recent advances in satellite active fire remote sensing to generate a novel set of inferred rate of spread observations. Using these observations, we evaluated four commonly used Australian forest fire behaviour models. The Project Vesta Mk1 and Mk2 models provided the best agreement with satellite observations, although these models overpredicted at lower rates of spread. Model prediction error was mostly attributed to windspeed, suggesting that wind characteristics at the fire grounds were not fully characterised under some circumstances using station or gridded observations. We suggest that ongoing advancements in satellite active fire detection provide opportunities to evaluate and develop fire behaviour models.

引用次数: 0

AquaNutriOpt II: A multi-period bi-objective nutrient optimization python tool for controlling harmful algal blooms — A case study of Lake Okeechobee

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-16 DOI: 10.1016/j.envsoft.2025.106428

Ashim Khanal , Osama M. Tarabih , Mauricio E. Arias , Qiong Zhang , Hadi Charkhgard

We introduce a significantly enhanced version of AquaNutriOpt, now equipped with advanced mathematical optimization capabilities absent in its initial release (Khanal et al., 2024). AquaNutriOpt II is a user-friendly, free, open-source Python tool designed to address the complex challenge of optimizing nutrient management for controlling harmful algal blooms. In this latest version, users gain the flexibility to incorporate multiple time periods into their analyses. Moreover, they can now optimize the management of two nutrients concurrently (primarily phosphorus and nitrogen) through an innovative multi-objective optimization framework. Building upon its predecessor, AquaNutriOpt II continues to streamline the identification of optimal Best Management Practices (BMPs) and Treatment Technologies (TTs), including determining the most suitable locations for implementation while considering budgetary constraints. To showcase the efficacy and advantages of AquaNutriOpt II, we apply it to a real-world case study centered on Lake Okeechobee in Florida, USA.

{"title":"AquaNutriOpt II: A multi-period bi-objective nutrient optimization python tool for controlling harmful algal blooms — A case study of Lake Okeechobee","authors":"Ashim Khanal , Osama M. Tarabih , Mauricio E. Arias , Qiong Zhang , Hadi Charkhgard","doi":"10.1016/j.envsoft.2025.106428","DOIUrl":"10.1016/j.envsoft.2025.106428","url":null,"abstract":"<div><div>We introduce a significantly enhanced version of AquaNutriOpt, now equipped with advanced mathematical optimization capabilities absent in its initial release (Khanal et al., 2024). AquaNutriOpt II is a user-friendly, free, open-source Python tool designed to address the complex challenge of optimizing nutrient management for controlling harmful algal blooms. In this latest version, users gain the flexibility to incorporate multiple time periods into their analyses. Moreover, they can now optimize the management of two nutrients concurrently (primarily phosphorus and nitrogen) through an innovative multi-objective optimization framework. Building upon its predecessor, AquaNutriOpt II continues to streamline the identification of optimal Best Management Practices (BMPs) and Treatment Technologies (TTs), including determining the most suitable locations for implementation while considering budgetary constraints. To showcase the efficacy and advantages of AquaNutriOpt II, we apply it to a real-world case study centered on Lake Okeechobee in Florida, USA.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106428"},"PeriodicalIF":4.8,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643037","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

WigglyRivers: A tool to characterize the multiscale nature of meandering channels

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-14 DOI: 10.1016/j.envsoft.2025.106423

Daniel Gonzalez-Duque , Jesus D. Gomez-Velez

Channel sinuosity is ubiquitous along river networks, producing complex patterns that encapsulate and influence morphodynamic processes and ecosystem services. Accurately characterizing these patterns is challenging with traditional curvature-based algorithms. Here, we present WigglyRivers, a Python package that builds on existing wavelet-based methods to create an unsupervised meander identification and characterization tool. The package uses planimetric information the user provides or from the USGS’s High-Resolution National Hydrography Dataset to characterize individual reaches or entire river networks. WigglyRivers also includes a supervised river identification tool for manually selecting individual meandering features. Here, we provide examples of idealized river transects and show the capabilities of WigglyRivers. We also use the supervised identification tool to validate the unsupervised identification on river transects across the continental US. WigglyRivers is a tool to understand better the multiscale characteristics of river networks and the link between river geomorphology and river corridor connectivity.

{"title":"WigglyRivers: A tool to characterize the multiscale nature of meandering channels","authors":"Daniel Gonzalez-Duque , Jesus D. Gomez-Velez","doi":"10.1016/j.envsoft.2025.106423","DOIUrl":"10.1016/j.envsoft.2025.106423","url":null,"abstract":"<div><div>Channel sinuosity is ubiquitous along river networks, producing complex patterns that encapsulate and influence morphodynamic processes and ecosystem services. Accurately characterizing these patterns is challenging with traditional curvature-based algorithms. Here, we present WigglyRivers, a Python package that builds on existing wavelet-based methods to create an unsupervised meander identification and characterization tool. The package uses planimetric information the user provides or from the USGS’s High-Resolution National Hydrography Dataset to characterize individual reaches or entire river networks. WigglyRivers also includes a supervised river identification tool for manually selecting individual meandering features. Here, we provide examples of idealized river transects and show the capabilities of WigglyRivers. We also use the supervised identification tool to validate the unsupervised identification on river transects across the continental US. WigglyRivers is a tool to understand better the multiscale characteristics of river networks and the link between river geomorphology and river corridor connectivity.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106423"},"PeriodicalIF":4.8,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642324","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 new conditional generative adversarial neural network approach for statistical downscaling of the ERA5 reanalysis over the Italian Peninsula

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-14 DOI: 10.1016/j.envsoft.2025.106427

Ilenia Manco , Walter Riviera , Andrea Zanetti , Marco Briscolini , Paola Mercogliano , Antonio Navarra

State-of-the-art General Circulation Models (GCMs) typically operate at a coarse spatial resolution, requiring a refinement to assess regional climate changes and their impacts. This weakness is mainly known for representing regional-scale topography and meteorological processes, particularly those responsible for extreme events. Dynamical downscaling methods are computationally demanding. In contrast, though computationally efficient, statistical approaches often sacrifice spatial consistency. To address these limitations, this work introduces an innovative and robust Conditional Generative Adversarial Neural Network (cGAN) architecture for statistical downscaling, discussing the methodology, advantages, and contributions to refining predictions at a finer scale. By leveraging a generator-discriminator architecture, the cGAN developed permits to downscale ERA5 reanalysis at the local scale to obtain a new high-resolution dataset (∼2.2 km), ERA5-DownGAN. The results obtained show the cGAN's architecture presented accurately reproduces the patterns, value range, and extreme values generated by dynamical models for the 2-m temperature over the Italian Peninsula.

{"title":"A new conditional generative adversarial neural network approach for statistical downscaling of the ERA5 reanalysis over the Italian Peninsula","authors":"Ilenia Manco , Walter Riviera , Andrea Zanetti , Marco Briscolini , Paola Mercogliano , Antonio Navarra","doi":"10.1016/j.envsoft.2025.106427","DOIUrl":"10.1016/j.envsoft.2025.106427","url":null,"abstract":"<div><div>State-of-the-art General Circulation Models (GCMs) typically operate at a coarse spatial resolution, requiring a refinement to assess regional climate changes and their impacts. This weakness is mainly known for representing regional-scale topography and meteorological processes, particularly those responsible for extreme events. Dynamical downscaling methods are computationally demanding. In contrast, though computationally efficient, statistical approaches often sacrifice spatial consistency. To address these limitations, this work introduces an innovative and robust Conditional Generative Adversarial Neural Network (cGAN) architecture for statistical downscaling, discussing the methodology, advantages, and contributions to refining predictions at a finer scale. By leveraging a generator-discriminator architecture, the cGAN developed permits to downscale ERA5 reanalysis at the local scale to obtain a new high-resolution dataset (∼2.2 km), ERA5-DownGAN. The results obtained show the cGAN's architecture presented accurately reproduces the patterns, value range, and extreme values generated by dynamical models for the 2-m temperature over the Italian Peninsula.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106427"},"PeriodicalIF":4.8,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the future of hydroecological models of everywhere

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-13 DOI: 10.1016/j.envsoft.2025.106431

Keith Beven

This paper addresses the potential for hydroecological models of everywhere to be used, in conjunction with interaction with local stakeholders, as a way of learning about places as well as being used as predictive tools. The importance of facilitating stakeholder involvement in defining assumptions and uncertainties, and in model evaluation is stressed. The potential for using data science and real-time updating in using the internet of things to contribute to a models of everywhere framework is also discussed.

引用次数: 0

Innovative knowledge-based system for streamflow hindcasting: A comparative assessment of Gaussian Process-Integrated Neural Network with LSTM and GRU models

IF 4.8 2区环境科学与生态学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Environmental Modelling & Software

Pub Date : 2025-03-13 DOI: 10.1016/j.envsoft.2025.106433

Arathy Nair G R , Adarsh S

Lack of historical data is a major bottleneck for hydrologists to proceed with reliable climate change studies. This work proposes Gaussian Process-Integrated Neural Network (GAUSNET) technique for streamflow hindcasting by considering significant hydrological variables and Global climatic oscillations (GCO) identified by Variance Inflation Factor as system inputs. Dynamic Time Warping based Interpolation is utilized to align monthly GCOs with daily streamflows, followed by feature selection and auto-correlation using Gradient Boosting Machines. On applying for streamflow hindcasting of Greater Pamba, Kerala, India, GAUSNET consistently outperformed Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) across all of the input scenarios with an average Nash-Sutcliffe Efficiency (NSE) of 0.93. GAUSNET based hindcasting can overcome issues of data shortage, fill the data gaps and capture extreme events. Moreover, its ability for uncertainty quantification enhances the reliability and make it as robust tool for hydrological modeling, flood risk assessment, and sustainable water management.

{"title":"Innovative knowledge-based system for streamflow hindcasting: A comparative assessment of Gaussian Process-Integrated Neural Network with LSTM and GRU models","authors":"Arathy Nair G R , Adarsh S","doi":"10.1016/j.envsoft.2025.106433","DOIUrl":"10.1016/j.envsoft.2025.106433","url":null,"abstract":"<div><div>Lack of historical data is a major bottleneck for hydrologists to proceed with reliable climate change studies. This work proposes Gaussian Process-Integrated Neural Network (GAUSNET) technique for streamflow hindcasting by considering significant hydrological variables and Global climatic oscillations (GCO) identified by Variance Inflation Factor as system inputs. Dynamic Time Warping based Interpolation is utilized to align monthly GCOs with daily streamflows, followed by feature selection and auto-correlation using Gradient Boosting Machines. On applying for streamflow hindcasting of Greater Pamba, Kerala, India, GAUSNET consistently outperformed Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) across all of the input scenarios with an average Nash-Sutcliffe Efficiency (NSE) of 0.93. GAUSNET based hindcasting can overcome issues of data shortage, fill the data gaps and capture extreme events. Moreover, its ability for uncertainty quantification enhances the reliability and make it as robust tool for hydrological modeling, flood risk assessment, and sustainable water management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"188 ","pages":"Article 106433"},"PeriodicalIF":4.8,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678382","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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Environmental Modelling & Software

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀