Pub Date : 2024-10-18DOI: 10.1016/j.envsoft.2024.106247
Marie-Philine Gross , Riccardo Taormina , Andrea Cominola
Recent research highlights the potential of consumption-based feedback for water conservation, emphasizing the need for Non Intrusive Water Monitoring (NIWM). However, existing NIWM studies often rely on small datasets, a pre-selected class of models, and inaccessible software. Here, we introduce PyNIWM, a machine learning-based open-source Python framework for NIWM. PyNIWM enables water end-use classification via (i) data characterization and feature engineering, (ii) water end-use event classification with four machine learning classifiers, and (iii) performance assessment. We demonstrate PyNIWM on a real-world dataset containing around 800,000 labeled end-use events from 762 homes across the USA and Canada. The four PyNIWM classifiers achieve F1 scores above 0.85, indicating high suitability for water end-use classification. However, a tradeoff between accuracy and computational cost exists. Finally, data balancing through oversampling enhances classification of low-represented end-use classes, but does not improve overall classification. We release PyNIWM as an open-source software, aiming for collaborative and reproducible research.
{"title":"A Machine Learning-based framework and open-source software for Non Intrusive Water Monitoring","authors":"Marie-Philine Gross , Riccardo Taormina , Andrea Cominola","doi":"10.1016/j.envsoft.2024.106247","DOIUrl":"10.1016/j.envsoft.2024.106247","url":null,"abstract":"<div><div>Recent research highlights the potential of consumption-based feedback for water conservation, emphasizing the need for Non Intrusive Water Monitoring (NIWM). However, existing NIWM studies often rely on small datasets, a pre-selected class of models, and inaccessible software. Here, we introduce PyNIWM, a machine learning-based open-source Python framework for NIWM. PyNIWM enables water end-use classification via (i) data characterization and feature engineering, (ii) water end-use event classification with four machine learning classifiers, and (iii) performance assessment. We demonstrate PyNIWM on a real-world dataset containing around 800,000 labeled end-use events from 762 homes across the USA and Canada. The four PyNIWM classifiers achieve F1 scores above 0.85, indicating high suitability for water end-use classification. However, a tradeoff between accuracy and computational cost exists. Finally, data balancing through oversampling enhances classification of low-represented end-use classes, but does not improve overall classification. We release PyNIWM as an open-source software, aiming for collaborative and reproducible research.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106247"},"PeriodicalIF":4.8,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571524","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}
Pub Date : 2024-10-17DOI: 10.1016/j.envsoft.2024.106249
Gaetano Daniele Fiorese , Gabriella Balacco , Giovanni Bruno , Nikolaos Nikolaidis
The complexity of modelling in karst environments necessitates substantial adjustments to existing hydrogeological models, with particular emphasis on accurately representing surface and deep processes.
This study proposes an advanced methodology for modelling regional coastal karst aquifers using an integrated SWAT-MODFLOW approach. The focus is on the regional coastal karst aquifer of Salento (Italy), which is characterised by significant heterogeneity, anisotropy and data scarcity, such as limited discharge measurements and water levels over time.
The integrated SWAT - MODFLOW approach allows an accurate description of both surface and subsurface hydrological processes specific to karst environments and demonstrates the adaptability of the models to karst-specific features such as sinkholes, dolines and fault permeability. The study successfully addresses the challenges posed by the distinctive characteristics of karst systems through the integration of SWAT-MODFLOW. Additionally, incorporating of satellite data enhances the precision and dependability of the model by augmenting the traditional datasets.
The entire simulation period, which included both the calibration and validation phases, extended from 2008 to 2018. The calibration phase occurred between 2008 and 2011, followed by the validation phase between 2015 and 2018. The temporal choices were exclusively based on the availability of meteorological and hydrogeological data. During calibration, satellite data, previous study results, and groundwater level measurements were used to optimize the SWAT and MODFLOW models. Validation subsequently confirmed model accuracy by comparing simulated groundwater levels with observed data, demonstrating a satisfactory root mean square error (RMSE) of 0.22 m. Modelling results indicate that evapotranspiration is the predominant hydrological process, and excessive withdrawals could lead to a water deficit. Simulated piezometric maps provide crucial information on recharge areas and hydraulic compartments delineated by faults. The study not only advances the understanding of the hydrogeology of the specific case study but also provides a valuable reference for future modelling of karst aquifers. Additionally, it highlights the crucial need for ongoing enhancement in the management and monitoring of coastal karst aquifers.
{"title":"Hydrogeological modelling of a coastal karst aquifer using an integrated SWAT-MODFLOW approach","authors":"Gaetano Daniele Fiorese , Gabriella Balacco , Giovanni Bruno , Nikolaos Nikolaidis","doi":"10.1016/j.envsoft.2024.106249","DOIUrl":"10.1016/j.envsoft.2024.106249","url":null,"abstract":"<div><div>The complexity of modelling in karst environments necessitates substantial adjustments to existing hydrogeological models, with particular emphasis on accurately representing surface and deep processes.</div><div>This study proposes an advanced methodology for modelling regional coastal karst aquifers using an integrated SWAT-MODFLOW approach. The focus is on the regional coastal karst aquifer of Salento (Italy), which is characterised by significant heterogeneity, anisotropy and data scarcity, such as limited discharge measurements and water levels over time.</div><div>The integrated SWAT - MODFLOW approach allows an accurate description of both surface and subsurface hydrological processes specific to karst environments and demonstrates the adaptability of the models to karst-specific features such as sinkholes, dolines and fault permeability. The study successfully addresses the challenges posed by the distinctive characteristics of karst systems through the integration of SWAT-MODFLOW. Additionally, incorporating of satellite data enhances the precision and dependability of the model by augmenting the traditional datasets.</div><div>The entire simulation period, which included both the calibration and validation phases, extended from 2008 to 2018. The calibration phase occurred between 2008 and 2011, followed by the validation phase between 2015 and 2018. The temporal choices were exclusively based on the availability of meteorological and hydrogeological data. During calibration, satellite data, previous study results, and groundwater level measurements were used to optimize the SWAT and MODFLOW models. Validation subsequently confirmed model accuracy by comparing simulated groundwater levels with observed data, demonstrating a satisfactory root mean square error (RMSE) of 0.22 m. Modelling results indicate that evapotranspiration is the predominant hydrological process, and excessive withdrawals could lead to a water deficit. Simulated piezometric maps provide crucial information on recharge areas and hydraulic compartments delineated by faults. The study not only advances the understanding of the hydrogeology of the specific case study but also provides a valuable reference for future modelling of karst aquifers. Additionally, it highlights the crucial need for ongoing enhancement in the management and monitoring of coastal karst aquifers.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106249"},"PeriodicalIF":4.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529740","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}
Pub Date : 2024-10-15DOI: 10.1016/j.envsoft.2024.106245
Maiken Baumberger , Bettina Haas , Walter Tewes , Benjamin Risse , Nele Meyer , Hanna Meyer
Soil temperature and moisture are important variables controlling ecological processes, but continuous high-resolution data are rarely available. Therefore, we used the correlation with widely accessible meteorological variables, including air temperature and precipitation, to develop models that predict time series of soil temperature and moisture. To model high-resolution time series, predictor and target variables had a temporal resolution of 1 h. We tested the applicability of Gated Recurrent Units with time series from one exemplary site. The models showed a high predictability on the four years test set with a mean absolute error of 0.87°C for soil temperature and 3.20% volumetric water content for soil moisture. We further investigated the plausibility of the models by passing simplified synthetic data to the trained models and thereby proved their ability to reflect known processes. Finally, we showed the potential to apply the models to other sites and soil depths using transfer learning.
{"title":"Gated recurrent units for modelling time series of soil temperature and moisture: An assessment of performance and process reflectivity","authors":"Maiken Baumberger , Bettina Haas , Walter Tewes , Benjamin Risse , Nele Meyer , Hanna Meyer","doi":"10.1016/j.envsoft.2024.106245","DOIUrl":"10.1016/j.envsoft.2024.106245","url":null,"abstract":"<div><div>Soil temperature and moisture are important variables controlling ecological processes, but continuous high-resolution data are rarely available. Therefore, we used the correlation with widely accessible meteorological variables, including air temperature and precipitation, to develop models that predict time series of soil temperature and moisture. To model high-resolution time series, predictor and target variables had a temporal resolution of 1 h. We tested the applicability of Gated Recurrent Units with time series from one exemplary site. The models showed a high predictability on the four years test set with a mean absolute error of 0.87°C for soil temperature and 3.20% volumetric water content for soil moisture. We further investigated the plausibility of the models by passing simplified synthetic data to the trained models and thereby proved their ability to reflect known processes. Finally, we showed the potential to apply the models to other sites and soil depths using transfer learning.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106245"},"PeriodicalIF":4.8,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529817","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}
Pub Date : 2024-10-12DOI: 10.1016/j.envsoft.2024.106239
Young-Don Choi , Iman Maghami , Jonathan L. Goodall , Lawrence Band , Ayman Nassar , Laurence Lin , Linnea Saby , Zhiyu Li , Shaowen Wang , Chris Calloway , Hong Yi , Martin Seul , Daniel P. Ames , David G. Tarboton
Reproducible environmental modelling often relies on spatial datasets as inputs, typically manually subset for specific areas. Yet, models can benefit from a data distribution approach facilitated by online repositories, and automating processes to foster reproducibility. This study introduces a method leveraging diverse state-scale spatial datasets to create cohesive packages for GIS-based environmental modelling. These datasets were generated and shared via GeoServer and THREDDS Data Server connected to HydroShare, contrasting with conventional distribution methods. Using the Regional Hydro-Ecologic Simulation System (RHESSys) across three U.S. catchment-scale watersheds, we demonstrate minimal errors in spatial inputs and model streamflow outputs compared to traditional approaches. This spatial data-sharing method facilitates consistent model creation, fostering reproducibility. Its broader impact allows scientists to tailor the method to various use cases, such as exploring different scales beyond state-scale or applying it to other online repositories using existing data distribution systems, eliminating the need to develop their own.
{"title":"Toward reproducible and interoperable environmental modeling: Integration of HydroShare with server-side methods for exposing large-extent spatial datasets to models","authors":"Young-Don Choi , Iman Maghami , Jonathan L. Goodall , Lawrence Band , Ayman Nassar , Laurence Lin , Linnea Saby , Zhiyu Li , Shaowen Wang , Chris Calloway , Hong Yi , Martin Seul , Daniel P. Ames , David G. Tarboton","doi":"10.1016/j.envsoft.2024.106239","DOIUrl":"10.1016/j.envsoft.2024.106239","url":null,"abstract":"<div><div>Reproducible environmental modelling often relies on spatial datasets as inputs, typically manually subset for specific areas. Yet, models can benefit from a data distribution approach facilitated by online repositories, and automating processes to foster reproducibility. This study introduces a method leveraging diverse state-scale spatial datasets to create cohesive packages for GIS-based environmental modelling. These datasets were generated and shared via GeoServer and THREDDS Data Server connected to HydroShare, contrasting with conventional distribution methods. Using the Regional Hydro-Ecologic Simulation System (RHESSys) across three U.S. catchment-scale watersheds, we demonstrate minimal errors in spatial inputs and model streamflow outputs compared to traditional approaches. This spatial data-sharing method facilitates consistent model creation, fostering reproducibility. Its broader impact allows scientists to tailor the method to various use cases, such as exploring different scales beyond state-scale or applying it to other online repositories using existing data distribution systems, eliminating the need to develop their own.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106239"},"PeriodicalIF":4.8,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529741","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}
In statistical applications, choosing a suitable data distribution or likelihood that matches the nature of the response variable is required. To spatially predict the planimetric area of a landslide population, the most tested likelihood corresponds to the Log-Gaussian case. This causes a limitation that hinders the ability to accurately model both very small and very large landslides, with the latter potentially leading to a dangerous underestimation of the hazard. Here, we test a distribution-agnostic solution via a Graph Transformer Neural Network (GTNN) and implement a loss function capable of forcing the model to capture both the bulk and the right tail of the landslide area distribution. An additional problem with this type of data-driven hazard assessment is that one often excludes slopes with landslide areas equal to zero from the regression procedure, as this may bias the prediction towards small values. Due to the nature of GTNNs, we present a solution where all the landslide area information is passed to the model, as one would expect for architectures built for image analysis. The results are promising, with the landslide area distribution generated by the Wenchuan earthquake being suitably estimated, including both zeros, the bulk and the extremely large cases. We consider this a step forward in the landslide hazard modelling literature, with implications for what the scientific community could achieve in light of a future space–time and/or risk assessment extension of the current protocol.
{"title":"Distribution-agnostic landslide hazard modelling via Graph Transformers","authors":"Gabriele Belvederesi , Hakan Tanyas , Aldo Lipani , Ashok Dahal , Luigi Lombardo","doi":"10.1016/j.envsoft.2024.106231","DOIUrl":"10.1016/j.envsoft.2024.106231","url":null,"abstract":"<div><div>In statistical applications, choosing a suitable data distribution or likelihood that matches the nature of the response variable is required. To spatially predict the planimetric area of a landslide population, the most tested likelihood corresponds to the Log-Gaussian case. This causes a limitation that hinders the ability to accurately model both very small and very large landslides, with the latter potentially leading to a dangerous underestimation of the hazard. Here, we test a distribution-agnostic solution via a Graph Transformer Neural Network (GTNN) and implement a loss function capable of forcing the model to capture both the bulk and the right tail of the landslide area distribution. An additional problem with this type of data-driven hazard assessment is that one often excludes slopes with landslide areas equal to zero from the regression procedure, as this may bias the prediction towards small values. Due to the nature of GTNNs, we present a solution where all the landslide area information is passed to the model, as one would expect for architectures built for image analysis. The results are promising, with the landslide area distribution generated by the Wenchuan earthquake being suitably estimated, including both zeros, the bulk and the extremely large cases. We consider this a step forward in the landslide hazard modelling literature, with implications for what the scientific community could achieve in light of a future space–time and/or risk assessment extension of the current protocol.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106231"},"PeriodicalIF":4.8,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142445081","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}
Pub Date : 2024-10-10DOI: 10.1016/j.envsoft.2024.106246
Thanh Quang Dang , Ba Hoang Tran , Quyen Ngoc Le , Ahad Hasan Tanim , Van Hieu Bui , Son T. Mai , Phong Nguyen Thanh , Duong Tran Anh
The urban drainage system constantly facing flooding issues in coastal and urban areas. Robust and accurate urban flood management, particularly considering fast-moving compound floods, is crucial to minimize the impact of flood disasters in coastal cities. Till now, Ho Chi Minh City (HCMC) lacks an effective means of urban flood management because of flood risk communication among residents. Existing flood risk communication tools rely on post-disaster flood model outcomes and data. Therefore, this research proposes a real-time Early Urban Flooding Warning System (EUFWS) integrated with a user-friendly web and app interface. The backbone of this system consists of flood models developed using machine learning (ML) algorithms, combined with big data and Web-GIS visualization, with ML serving as the core for constructing the EUFWS. EUFWS offer several key advantages: they are available at all times, accessible from anywhere, and provide a real-time, multi-user working platform. Additionally, the system is flexible, allowing for the easy addition of components and services and scalable, adjusting to workload demands. EUFWS have been successfully deployed in Thu Duc City, Vietnam, as a case study and are operating effectively. EUFWS have been successfully deployed in Thu Duc City, Vietnam, as a case study and are operating effectively. Research results indicate that EUFWS supported decision-makers to be effectively risk informed and make intelligent decisions during urban flood emergencies. This underscores the significant potential of integrating ML and information technology to enhance the management of smart urban drainage systems in flood-prone cities worldwide.
城市排水系统一直面临着沿海和城市地区的洪水问题。稳健而准确的城市洪水管理，尤其是考虑到快速移动的复合洪水，对于最大限度地减少洪水灾害对沿海城市的影响至关重要。迄今为止，胡志明市（HCMC）还缺乏有效的城市洪水管理手段，原因是居民之间的洪水风险沟通。现有的洪水风险交流工具依赖于灾后洪水模型结果和数据。因此，本研究提出了一个实时城市洪水预警系统（EUFWS），该系统集成了用户友好的网络和应用程序界面。该系统的骨干包括利用机器学习（ML）算法开发的洪水模型，结合大数据和 Web-GIS 可视化，以 ML 作为构建 EUFWS 的核心。EUFWS 具有几个主要优势：随时可用、随时随地访问，并提供了一个实时、多用户的工作平台。此外，该系统还具有灵活性，可轻松添加组件和服务，并可根据工作量需求进行扩展。作为案例研究，EUFWS 已在越南 Thu Duc 市成功部署并有效运行。作为案例研究，EUFWS 已在越南 Thu Duc 市成功部署并有效运行。研究结果表明，EUFWS 支持决策者在城市洪水紧急情况下有效了解风险并做出明智决策。这突出表明，在全球易受洪水侵袭的城市中，集成 ML 和信息技术以加强智能城市排水系统管理的潜力巨大。
{"title":"Integrating Intelligent Hydro-informatics into an effective Early Warning System for risk-informed urban flood management","authors":"Thanh Quang Dang , Ba Hoang Tran , Quyen Ngoc Le , Ahad Hasan Tanim , Van Hieu Bui , Son T. Mai , Phong Nguyen Thanh , Duong Tran Anh","doi":"10.1016/j.envsoft.2024.106246","DOIUrl":"10.1016/j.envsoft.2024.106246","url":null,"abstract":"<div><div>The urban drainage system constantly facing flooding issues in coastal and urban areas. Robust and accurate urban flood management, particularly considering fast-moving compound floods, is crucial to minimize the impact of flood disasters in coastal cities. Till now, Ho Chi Minh City (HCMC) lacks an effective means of urban flood management because of flood risk communication among residents. Existing flood risk communication tools rely on post-disaster flood model outcomes and data. Therefore, this research proposes a real-time Early Urban Flooding Warning System (EUFWS) integrated with a user-friendly web and app interface. The backbone of this system consists of flood models developed using machine learning (ML) algorithms, combined with big data and Web-GIS visualization, with ML serving as the core for constructing the EUFWS. EUFWS offer several key advantages: they are available at all times, accessible from anywhere, and provide a real-time, multi-user working platform. Additionally, the system is flexible, allowing for the easy addition of components and services and scalable, adjusting to workload demands. EUFWS have been successfully deployed in Thu Duc City, Vietnam, as a case study and are operating effectively. EUFWS have been successfully deployed in Thu Duc City, Vietnam, as a case study and are operating effectively. Research results indicate that EUFWS supported decision-makers to be effectively risk informed and make intelligent decisions during urban flood emergencies. This underscores the significant potential of integrating ML and information technology to enhance the management of smart urban drainage systems in flood-prone cities worldwide.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106246"},"PeriodicalIF":4.8,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142432620","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}
Pub Date : 2024-10-09DOI: 10.1016/j.envsoft.2024.106241
Jeffery S. Horsburgh , Kenneth Lippold , Daniel L. Slaugh
Software is critical in managing environmental sensor data. The Open Geospatial Consortium (OGC) developed the “OGC SensorThings API” (STA) standard to address variability across sensors, observed variables, platforms, and protocols, facilitating development of sensing and Internet of Things applications. This paper details a Python/Django implementation of the STA application programming interface (API) and a PostgreSQL/Timescale implementation of the STA data model, enhancing availability of robust software for management and sharing of environmental sensor data. STA offers a RESTful interface with JSON data encoding, aligning with modern development patterns and facilitating interoperability. Integration of metadata from the Observations Data Model ensures data can be adequately described and interpreted. STA’s flexibility allows lightweight query responses or comprehensive metadata inclusion, and a complementary data management API enhances use of STA within multi-user systems. Open-source code and deployment instructions in GitHub enable standalone or cloud deployments, enhancing accessibility and usability for researchers and practitioners.
{"title":"Adapting OGC’s SensorThings API and Data Model to Support Data Management and Sharing for Environmental Sensors","authors":"Jeffery S. Horsburgh , Kenneth Lippold , Daniel L. Slaugh","doi":"10.1016/j.envsoft.2024.106241","DOIUrl":"10.1016/j.envsoft.2024.106241","url":null,"abstract":"<div><div>Software is critical in managing environmental sensor data. The Open Geospatial Consortium (OGC) developed the “OGC SensorThings API” (STA) standard to address variability across sensors, observed variables, platforms, and protocols, facilitating development of sensing and Internet of Things applications. This paper details a Python/Django implementation of the STA application programming interface (API) and a PostgreSQL/Timescale implementation of the STA data model, enhancing availability of robust software for management and sharing of environmental sensor data. STA offers a RESTful interface with JSON data encoding, aligning with modern development patterns and facilitating interoperability. Integration of metadata from the Observations Data Model ensures data can be adequately described and interpreted. STA’s flexibility allows lightweight query responses or comprehensive metadata inclusion, and a complementary data management API enhances use of STA within multi-user systems. Open-source code and deployment instructions in GitHub enable standalone or cloud deployments, enhancing accessibility and usability for researchers and practitioners.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106241"},"PeriodicalIF":4.8,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142427017","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}
Pub Date : 2024-10-09DOI: 10.1016/j.envsoft.2024.106243
Sourav Mukherjee , Sudhanshu Panda , Devendra M. Amatya , Mariana Dobre , John L. Campbell , Roger Lew , Peter Caldwell , Kelly Elder , Johnny M. Grace , Sherri L. Johnson
Intense precipitation events pose growing threats to forest infrastructure causing flooding, and soil erosion and deposition, creating bottlenecks at road-stream crossing structures (RSCS). We describe a hillslope-scale ensemble hydro-geomorphological vulnerability assessment integrating geospatial Streambank Erosion Vulnerability Assessment (SBEVA), Modified Revised Soil Loss Equation (MRUSLE), and process-based Water Erosion Prediction Project (WEPP) model into an ensemble hydro-geomorphologic vulnerability index (EHVI) for USDA Forest Service (USFS) managed 194 road-culverts at the Hubbard Brook Experimental Forest (HBR-EF) in New Hampshire, USA. The results revealed that five and one culvert with diameters of 0.46m and 0.61m, respectively, have extreme EHVI values between 4 and 5, and fifteen and three culverts with diameters of 0.46m and 0.61m, respectively, have severe EHVI values between 3 and 4, some of which were previously identified as hydrologically vulnerable (undersized) to floods. This knowledge will inform USFS efforts to improve the resilience of the RSCS and protect aquatic habitats.
{"title":"Hydro-geomorphological assessment of culvert vulnerability to flood-induced soil erosion using an ensemble modeling approach","authors":"Sourav Mukherjee , Sudhanshu Panda , Devendra M. Amatya , Mariana Dobre , John L. Campbell , Roger Lew , Peter Caldwell , Kelly Elder , Johnny M. Grace , Sherri L. Johnson","doi":"10.1016/j.envsoft.2024.106243","DOIUrl":"10.1016/j.envsoft.2024.106243","url":null,"abstract":"<div><div>Intense precipitation events pose growing threats to forest infrastructure causing flooding, and soil erosion and deposition, creating bottlenecks at road-stream crossing structures (RSCS). We describe a hillslope-scale ensemble hydro-geomorphological vulnerability assessment integrating geospatial Streambank Erosion Vulnerability Assessment (SBEVA), Modified Revised Soil Loss Equation (MRUSLE), and process-based Water Erosion Prediction Project (WEPP) model into an ensemble hydro-geomorphologic vulnerability index (EHVI) for USDA Forest Service (USFS) managed 194 road-culverts at the Hubbard Brook Experimental Forest (HBR-EF) in New Hampshire, USA. The results revealed that five and one culvert with diameters of 0.46m and 0.61m, respectively, have extreme EHVI values between 4 and 5, and fifteen and three culverts with diameters of 0.46m and 0.61m, respectively, have severe EHVI values between 3 and 4, some of which were previously identified as hydrologically vulnerable (undersized) to floods. This knowledge will inform USFS efforts to improve the resilience of the RSCS and protect aquatic habitats.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106243"},"PeriodicalIF":4.8,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142432622","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}
Pub Date : 2024-10-09DOI: 10.1016/j.envsoft.2024.106240
Venkatesh Merwade , Ibrahim Demir , Marian Muste , Amanda L. Cox , J. Toby Minear , Yusuf Sermet , Sayan Dey , Chung-Yuan Liang
The objective of this paper is to present the initial illustration of a cyberinfrastructure named the RIver MORPHology Information System (RIMORPHIS) that addresses the current limitations related to river morphology data and tools. RIMORPHIS is supported by a data model for storing river morphology data. A new specification for data and semantics on river morphology datasets has been developed to support the web-based platform for discovering and visualization of river morphology data. Several geoprocessing tools are developed that enable scientific analysis and practical studies, including the coordinate transformation, cross-section generation and bathymetry mesh generation. Our vision for RIMORPHIS is to create a self-sustained community platform with tools to support scientific discoveries on river morphology and to enable multidisciplinary research for riverine environments. To accomplish this vision, we created a community to gather input and build partnerships. The RIMORPHIS cyberinfrastructure addresses the community needs related to data access, processing and visualization. The current implementation of RIMORPHIS is scalable for new data and tools.
{"title":"Towards an Open and Integrated Cyberinfrastructure for River Morphology Research in the Big Data Era","authors":"Venkatesh Merwade , Ibrahim Demir , Marian Muste , Amanda L. Cox , J. Toby Minear , Yusuf Sermet , Sayan Dey , Chung-Yuan Liang","doi":"10.1016/j.envsoft.2024.106240","DOIUrl":"10.1016/j.envsoft.2024.106240","url":null,"abstract":"<div><div>The objective of this paper is to present the initial illustration of a cyberinfrastructure named the RIver MORPHology Information System (RIMORPHIS) that addresses the current limitations related to river morphology data and tools. RIMORPHIS is supported by a data model for storing river morphology data. A new specification for data and semantics on river morphology datasets has been developed to support the web-based platform for discovering and visualization of river morphology data. Several geoprocessing tools are developed that enable scientific analysis and practical studies, including the coordinate transformation, cross-section generation and bathymetry mesh generation. Our vision for RIMORPHIS is to create a self-sustained community platform with tools to support scientific discoveries on river morphology and to enable multidisciplinary research for riverine environments. To accomplish this vision, we created a community to gather input and build partnerships. The RIMORPHIS cyberinfrastructure addresses the community needs related to data access, processing and visualization. The current implementation of RIMORPHIS is scalable for new data and tools.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106240"},"PeriodicalIF":4.8,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142427016","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}
Pub Date : 2024-10-05DOI: 10.1016/j.envsoft.2024.106228
Luca Piciullo, Minu Treesa Abraham, Ida Norderhaug Drøsdal, Erling Singstad Paulsen
<div><div>The paper investigates the combined use of real-time hydrological monitoring, publicly available meteorological data and hydrological and geotechnical numerical modelling, to develop data-driven models to forecast the stability of a slope. This study showcases a first attempt to integrate these critical aspects into a fully automatic Internet of Thing (IoT)-based local landslide early warning system (Lo-LEWS).</div><div>The paper uses a validated hydrological numerical model, back-calculated over real monitored conditions, to evaluate the slope stability. The factor of safety (<span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span>) was computed coupling the commercial package GeoStudio, using transient SEEP/W and Slope. The analyses were conducted for 5 different 1-year datasets encompassing both historical (2019–2020, 2021–2022, 2022–2023) and future projections (2064–2065, 2095–2096) of meteorological variables. Daily variation of hydrological and meteorological variables, along with vegetation indicators were used as inputs to train data-driven models, using polynomial regression (PR) and Random Forest (RF), to forecast daily <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span> values. The trained models proved to be effective and were employed to forecast slope stability for the rolling three days. To accurately forecast the <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span>, it was essential to incorporate forecasted hydrological, meteorological and vegetation variables into the analysis. The hydrological variables used as inputs for the data-driven models are forecasted using an open-source Python package for the analysis of hydrogeological time series, called Pastas (Collenteur et al., 2019). This model uses historical and forecasted meteorological and vegetation conditions to, specifically, replicate and forecast the time series of volumetric water content (VWC) and pore water pressure (PWP). The forecasted hydrological variables from Pastas, the forecasted meteorological variables as well as Leaf Area Index (<span><math><mrow><mi>L</mi><mi>A</mi><mi>I</mi></mrow></math></span>) are used as inputs for the trained data-driven models to forecast the <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span> values.</div><div>Finally, a web-based platform (WBP) has been created that automatically runs once a day and perform the following actions: 1) fetches measured and forecasted data using APIs, 2) runs rolling three days forecast based on collected hydrological, meteorological and vegetation variables, and 3) sends the forecasted values back to the Norwegian Geotechnical Institute (NGI) data platform, NGI Live, making them available for real-time visualization in online dashboards. If <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span>, VWC or PWP threshold values are exceeded, text messages and emails are sent to the system managers, enabling them t
{"title":"An operational IoT-based slope stability forecast using a digital twin","authors":"Luca Piciullo, Minu Treesa Abraham, Ida Norderhaug Drøsdal, Erling Singstad Paulsen","doi":"10.1016/j.envsoft.2024.106228","DOIUrl":"10.1016/j.envsoft.2024.106228","url":null,"abstract":"<div><div>The paper investigates the combined use of real-time hydrological monitoring, publicly available meteorological data and hydrological and geotechnical numerical modelling, to develop data-driven models to forecast the stability of a slope. This study showcases a first attempt to integrate these critical aspects into a fully automatic Internet of Thing (IoT)-based local landslide early warning system (Lo-LEWS).</div><div>The paper uses a validated hydrological numerical model, back-calculated over real monitored conditions, to evaluate the slope stability. The factor of safety (<span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span>) was computed coupling the commercial package GeoStudio, using transient SEEP/W and Slope. The analyses were conducted for 5 different 1-year datasets encompassing both historical (2019–2020, 2021–2022, 2022–2023) and future projections (2064–2065, 2095–2096) of meteorological variables. Daily variation of hydrological and meteorological variables, along with vegetation indicators were used as inputs to train data-driven models, using polynomial regression (PR) and Random Forest (RF), to forecast daily <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span> values. The trained models proved to be effective and were employed to forecast slope stability for the rolling three days. To accurately forecast the <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span>, it was essential to incorporate forecasted hydrological, meteorological and vegetation variables into the analysis. The hydrological variables used as inputs for the data-driven models are forecasted using an open-source Python package for the analysis of hydrogeological time series, called Pastas (Collenteur et al., 2019). This model uses historical and forecasted meteorological and vegetation conditions to, specifically, replicate and forecast the time series of volumetric water content (VWC) and pore water pressure (PWP). The forecasted hydrological variables from Pastas, the forecasted meteorological variables as well as Leaf Area Index (<span><math><mrow><mi>L</mi><mi>A</mi><mi>I</mi></mrow></math></span>) are used as inputs for the trained data-driven models to forecast the <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span> values.</div><div>Finally, a web-based platform (WBP) has been created that automatically runs once a day and perform the following actions: 1) fetches measured and forecasted data using APIs, 2) runs rolling three days forecast based on collected hydrological, meteorological and vegetation variables, and 3) sends the forecasted values back to the Norwegian Geotechnical Institute (NGI) data platform, NGI Live, making them available for real-time visualization in online dashboards. If <span><math><mrow><mi>F</mi><mi>o</mi><mi>S</mi></mrow></math></span>, VWC or PWP threshold values are exceeded, text messages and emails are sent to the system managers, enabling them t","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106228"},"PeriodicalIF":4.8,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142427015","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号