Pub Date : 2025-02-01DOI: 10.1016/j.envsoft.2025.106327
Mia M. Wu , Yu Liang , Hong S. He , Jian Yang , Bo Liu , Tianxiao Ma
Forest landscape models (FLMs) simulate forest dynamics by integrating stand- and landscape-scale processes. Thus, evaluating FLMs simulations necessitates including both processes. Thus far, stand-scale processes were evaluated in some FLMs, whereas landscape-scale processes were rarely evaluated. This study presents a framework that evaluates both stand- and landscape-scale processes. For the stand-scale processes, we proposed using stand density management diagrams to evaluate the simulated stand development trajectories that encapsulate the interplay of tree growth, competition, and mortality. For the landscape-scale processes, we evaluated seed dispersal, the basic spatial process driving forest landscape dynamics and not evaluated previously, through comparing simulated tree species colonization pattern against tree age distribution data from inventory data. We demonstrated the applicability of the framework to a 300-year historical forest landscape reconstructed using LANDIS. Given the common features, the framework is applicable to other FLMs or terrestrial ecosystem models operating at large scales.
{"title":"A process-based framework for validating forest landscape modeling outcomes","authors":"Mia M. Wu , Yu Liang , Hong S. He , Jian Yang , Bo Liu , Tianxiao Ma","doi":"10.1016/j.envsoft.2025.106327","DOIUrl":"10.1016/j.envsoft.2025.106327","url":null,"abstract":"<div><div>Forest landscape models (FLMs) simulate forest dynamics by integrating stand- and landscape-scale processes. Thus, evaluating FLMs simulations necessitates including both processes. Thus far, stand-scale processes were evaluated in some FLMs, whereas landscape-scale processes were rarely evaluated. This study presents a framework that evaluates both stand- and landscape-scale processes. For the stand-scale processes, we proposed using stand density management diagrams to evaluate the simulated stand development trajectories that encapsulate the interplay of tree growth, competition, and mortality. For the landscape-scale processes, we evaluated seed dispersal, the basic spatial process driving forest landscape dynamics and not evaluated previously, through comparing simulated tree species colonization pattern against tree age distribution data from inventory data. We demonstrated the applicability of the framework to a 300-year historical forest landscape reconstructed using LANDIS. Given the common features, the framework is applicable to other FLMs or terrestrial ecosystem models operating at large scales.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106327"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142990596","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106292
Zhouyayan Li , Yusuf Sermet , Ibrahim Demir
Recently, there are attempts to expand the current usage of satellite Earth surface observation images to forward-looking applications to support decision-making and fast response against future natural hazards. Specifically, deep learning techniques were employed to synthesize Earth surface images at the pixel level. Those studies found that precipitation and soil moisture play non-trivial roles in Earth surface condition prediction tasks. However, unlike many well-defined and well-studied topics, such as change detection, for which many benchmark datasets are openly available, there are limited public datasets for the abovementioned topic for fast prototyping and comparison. To close this gap, we introduced a comprehensive dataset containing SAR images, precipitation, soil moisture, land cover, Height Above Nearest Drainage (HAND), DEM, and slope data collected during the 2019 Central US Flooding events. Deep-learning-based SAR image synthesis and flood mapping with the synthesized images were presented as sample use cases of the dataset.
{"title":"EarthObsNet: A comprehensive Benchmark dataset for data-driven earth observation image synthesis","authors":"Zhouyayan Li , Yusuf Sermet , Ibrahim Demir","doi":"10.1016/j.envsoft.2024.106292","DOIUrl":"10.1016/j.envsoft.2024.106292","url":null,"abstract":"<div><div>Recently, there are attempts to expand the current usage of satellite Earth surface observation images to forward-looking applications to support decision-making and fast response against future natural hazards. Specifically, deep learning techniques were employed to synthesize Earth surface images at the pixel level. Those studies found that precipitation and soil moisture play non-trivial roles in Earth surface condition prediction tasks. However, unlike many well-defined and well-studied topics, such as change detection, for which many benchmark datasets are openly available, there are limited public datasets for the abovementioned topic for fast prototyping and comparison. To close this gap, we introduced a comprehensive dataset containing SAR images, precipitation, soil moisture, land cover, Height Above Nearest Drainage (HAND), DEM, and slope data collected during the 2019 Central US Flooding events. Deep-learning-based SAR image synthesis and flood mapping with the synthesized images were presented as sample use cases of the dataset.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106292"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825338","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}
This study develops an artificial intelligence (AI) model to forecast harmful algal blooms (HABs) in the Persian Gulf and Gulf of Oman using freely available remote sensing data, including chlorophyll-a (Chl-a), sea surface temperature (SST), salinity, and wind. The model introduces novel features such as spatial and temporal standard deviations of Chl-a concentration and a derived gradient feature. Correlation analysis indicated that these features enhance predictive capability. A multi-layer artificial neural network (ANN) was trained using a 66%/34% data split for training and testing, achieving 88.7% accuracy in binary classification (bloom/non-bloom) with an area under the ROC curve (AUC) of 90.1%. Overfitting was mitigated by monitoring training and validation loss, both of which consistently decreased over epochs, confirming robust model generalization. The use of standard deviation in SST and salinity highlights their influence on bloom dynamics, providing key insights into algal bloom drivers. The focus on freely available data enables stakeholders to better manage the environmental challenges posed by HABs.
{"title":"AI-driven forecasting of harmful algal blooms in Persian Gulf and Gulf of Oman using remote sensing","authors":"Amirreza Shahmiri, Mohamad Hosein Seyed-Djawadi, Seyed Mostafa Siadatmousavi","doi":"10.1016/j.envsoft.2024.106311","DOIUrl":"10.1016/j.envsoft.2024.106311","url":null,"abstract":"<div><div>This study develops an artificial intelligence (AI) model to forecast harmful algal blooms (HABs) in the Persian Gulf and Gulf of Oman using freely available remote sensing data, including chlorophyll-a (Chl-a), sea surface temperature (SST), salinity, and wind. The model introduces novel features such as spatial and temporal standard deviations of Chl-a concentration and a derived gradient feature. Correlation analysis indicated that these features enhance predictive capability. A multi-layer artificial neural network (ANN) was trained using a 66%/34% data split for training and testing, achieving 88.7% accuracy in binary classification (bloom/non-bloom) with an area under the ROC curve (AUC) of 90.1%. Overfitting was mitigated by monitoring training and validation loss, both of which consistently decreased over epochs, confirming robust model generalization. The use of standard deviation in SST and salinity highlights their influence on bloom dynamics, providing key insights into algal bloom drivers. The focus on freely available data enables stakeholders to better manage the environmental challenges posed by HABs.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106311"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905668","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106313
Yuquan Zhao , Lu Zhang , Shilong Lei , Lirong Liao , Chao Zhang
Precise and accurate quantification of belowground biomass (BGB) is essential for understanding terrestrial carbon dynamics. Traditional methods for estimating BGB suffer from a number of disadvantages, including inability to resolve differences among plant species, high dependence on Diameter at Breast Height, and destructive sampling. To address these issues, we developed a novel machine learning framework to estimate grassland BGB by integrating vegetation and soil data from 294 plots on China's Loess Plateau. An ensemble model combining XGBoost regression, Gradient boosting regression, Ridge regression, and ElasticNet regression outperformed the individual models, achieving a training R2 of 0.623 and a testing R2 of 0.502, highlighting its superior ability to identify the complex dependencies of BGB. Integration of key features, including soil organic carbon, plant height, and aboveground biomass, significantly improved the predictive accuracy. Nonlinear BGB–environment interactions are commonly underrecognized in traditional models. The model presented herein advances our ability to assess underground carbon stocks and offers insights into the ecological strategies of grassland species under competitive light conditions. By revealing the multifaceted influences of soil and vegetation on BGB, our research refines the understanding of grassland carbon dynamics. This study marks a precedent for harnessing advanced machine learning in ecological modeling to facilitate more accurate predictions of global change.
{"title":"Machine learning-based prediction of belowground biomass from aboveground biomass and soil properties","authors":"Yuquan Zhao , Lu Zhang , Shilong Lei , Lirong Liao , Chao Zhang","doi":"10.1016/j.envsoft.2024.106313","DOIUrl":"10.1016/j.envsoft.2024.106313","url":null,"abstract":"<div><div>Precise and accurate quantification of belowground biomass (BGB) is essential for understanding terrestrial carbon dynamics. Traditional methods for estimating BGB suffer from a number of disadvantages, including inability to resolve differences among plant species, high dependence on Diameter at Breast Height, and destructive sampling. To address these issues, we developed a novel machine learning framework to estimate grassland BGB by integrating vegetation and soil data from 294 plots on China's Loess Plateau. An ensemble model combining XGBoost regression, Gradient boosting regression, Ridge regression, and ElasticNet regression outperformed the individual models, achieving a training R<sup>2</sup> of 0.623 and a testing R<sup>2</sup> of 0.502, highlighting its superior ability to identify the complex dependencies of BGB. Integration of key features, including soil organic carbon, plant height, and aboveground biomass, significantly improved the predictive accuracy. Nonlinear BGB–environment interactions are commonly underrecognized in traditional models. The model presented herein advances our ability to assess underground carbon stocks and offers insights into the ecological strategies of grassland species under competitive light conditions. By revealing the multifaceted influences of soil and vegetation on BGB, our research refines the understanding of grassland carbon dynamics. This study marks a precedent for harnessing advanced machine learning in ecological modeling to facilitate more accurate predictions of global change.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106313"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142935470","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}
The preparation of an accurate bathymetry is crucial for flood modeling and is usually done using a LiDAR-derived Digital Elevation Model (DEM). However, a recurrent flaw of LiDAR DEM is the presence of water along rivers, that prevents a careful reproduction of the river bed and channel conveyance. This paper provides a simple and effective algorithm to tackle this problem when ground surveyed cross sections are available to complement DEM data. In contrast to most interpolation approaches, the algorithm is physically-based, using a 2D Shallow Water Equations solver in the identification of the wetted river bed perimeter. The method was applied to a 37 km long stretch of the Mella River (Northern Italy) providing satisfactory results. Further examples show the potential of the method in cases of increasing complexity of riverbed bathymetry. The procedure is explained step by step in the supplementary material, using two widely used freeware software.
{"title":"A simple method for the enhancement of river bathymetry in LiDAR DEM","authors":"Gabriele Farina , Marco Pilotti , Luca Milanesi , Giulia Valerio","doi":"10.1016/j.envsoft.2025.106354","DOIUrl":"10.1016/j.envsoft.2025.106354","url":null,"abstract":"<div><div>The preparation of an accurate bathymetry is crucial for flood modeling and is usually done using a LiDAR-derived Digital Elevation Model (DEM). However, a recurrent flaw of LiDAR DEM is the presence of water along rivers, that prevents a careful reproduction of the river bed and channel conveyance. This paper provides a simple and effective algorithm to tackle this problem when ground surveyed cross sections are available to complement DEM data. In contrast to most interpolation approaches, the algorithm is physically-based, using a 2D Shallow Water Equations solver in the identification of the wetted river bed perimeter. The method was applied to a 37 km long stretch of the Mella River (Northern Italy) providing satisfactory results. Further examples show the potential of the method in cases of increasing complexity of riverbed bathymetry. The procedure is explained step by step in the supplementary material, using two widely used freeware software.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"186 ","pages":"Article 106354"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388454","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106283
Ofek Aloni , Gal Perelman , Barak Fishbain
Synthetic datasets are widely used in applications like missing data imputation, simulations, training data-driven models, and system robustness analysis. Typically based on historical data, these datasets need to represent specific system behaviors while being diverse enough to challenge the system with a broad range of inputs. This paper introduces a method using discrete Fourier transform to generate synthetic time series with similar statistical moments to any given signal. The method allows control over the similarity level between the original and synthetic signals. Analytical proof shows that this method preserves the first two statistical moments and the autocorrelation function of the input signal. It is compared to ARMA, GAN, and CoSMoS methods using various environmental datasets with different temporal resolutions and domains, demonstrating its generality and flexibility. A Python library implementing this method is available as open-source software.
{"title":"Synthetic random environmental time series generation with similarity control, preserving original signal’s statistical characteristics","authors":"Ofek Aloni , Gal Perelman , Barak Fishbain","doi":"10.1016/j.envsoft.2024.106283","DOIUrl":"10.1016/j.envsoft.2024.106283","url":null,"abstract":"<div><div>Synthetic datasets are widely used in applications like missing data imputation, simulations, training data-driven models, and system robustness analysis. Typically based on historical data, these datasets need to represent specific system behaviors while being diverse enough to challenge the system with a broad range of inputs. This paper introduces a method using discrete Fourier transform to generate synthetic time series with similar statistical moments to any given signal. The method allows control over the similarity level between the original and synthetic signals. Analytical proof shows that this method preserves the first two statistical moments and the autocorrelation function of the input signal. It is compared to ARMA, GAN, and CoSMoS methods using various environmental datasets with different temporal resolutions and domains, demonstrating its generality and flexibility. A Python library implementing this method is available as open-source software.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106283"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142793155","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106279
Mazdak Arabi , Tyler Dell , Mahshid Mohammad Zadeh , Christine A. Pomeroy , Jennifer M. Egan , Tyler Wible , Sybil Sharvelle
Urbanization, land use change, and climate change have profound effects on urban stormwater. This study develops the Community-enabled Life-cycle Analysis of Stormwater Infrastructure Costs (CLASIC) software to support decisions about stormwater control infrastructure over a range of alternative scenarios at the neighborhood to municipal scales. The tool quantifies hydrologic and stormwater quality performance, life-cycle costs, and triple-bottom-line social, economic, and environmental co-benefits of green, gray, and hybrid green-gray stormwater practices. CLASIC is deployed as a cloud-based web-tool, with a geographical information system (GIS) enabled interface, and built-in computing services to characterize terrain, soil, land use, and climatic conditions using publicly available datasets, and to parameterize and execute the modeling modules. Three community level case studies in the United States illustrate the utility of CLASIC for climate change assessments, green infrastructure implementation for community redevelopment, and assessment of the effects of changes in rainfall characteristics on the performance of stormwater practices.
{"title":"Community-enabled life-cycle assessment Stormwater Infrastructure Costs (CLASIC) tool","authors":"Mazdak Arabi , Tyler Dell , Mahshid Mohammad Zadeh , Christine A. Pomeroy , Jennifer M. Egan , Tyler Wible , Sybil Sharvelle","doi":"10.1016/j.envsoft.2024.106279","DOIUrl":"10.1016/j.envsoft.2024.106279","url":null,"abstract":"<div><div>Urbanization, land use change, and climate change have profound effects on urban stormwater. This study develops the Community-enabled Life-cycle Analysis of Stormwater <span>Infrastructure</span> Costs (CLASIC) software to support decisions about stormwater control infrastructure over a range of alternative scenarios at the neighborhood to municipal scales. The tool quantifies hydrologic and stormwater quality performance, life-cycle costs, and triple-bottom-line social, economic, and environmental co-benefits of green, gray, and hybrid green-gray stormwater practices. CLASIC is deployed as a cloud-based web-tool, with a geographical information system (GIS) enabled interface, and built-in computing services to characterize terrain, soil, land use, and climatic conditions using publicly available datasets, and to parameterize and execute the modeling modules. Three community level case studies in the United States illustrate the utility of CLASIC for climate change assessments, green infrastructure implementation for community redevelopment, and assessment of the effects of changes in rainfall characteristics on the performance of stormwater practices.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106279"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142793157","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106310
Fucang Zhou , Zhi Chen , Zaiyang Zhou , Bing Cao , Lili Xu , Dongyan Liu , Ruishan Chen , Karline Soetaert , Jianzhong Ge
Increasingly frequent and severe floating macroalgal blooms present significant challenges to coastal and ocean environments. Here a short-term forecast system of floating macroalgal blooms was developed to predict the physical-biogeochemical environment and macroalgal ecodynamic processes in a regional ocean. Predictions of macroalgal ecodynamic processes are influenced by oceanic conditions (hydrodynamics, temperature, and nutrients), as well as atmospheric conditions (wind). The system's effectiveness is demonstrated by successfully hindcasting the June 2021 green tide bloom event in the Yellow Sea and using real-time satellite data to make reliable and robust continuous short-term predictions for 2022 and 2023. The prediction accuracy of coverage reaches 87.5%, and the minimum transport error of the green tide center of mass is 6.09 nautical miles over an 7-day prediction duration. Supported by regional marine physics and biogeochemistry and macroalgal physiological characteristic datasets, this system may serve as a crucial cornerstone for similar floating macroalgal disaster prevention.
{"title":"Predicting massive floating macroalgal blooms in a regional sea","authors":"Fucang Zhou , Zhi Chen , Zaiyang Zhou , Bing Cao , Lili Xu , Dongyan Liu , Ruishan Chen , Karline Soetaert , Jianzhong Ge","doi":"10.1016/j.envsoft.2024.106310","DOIUrl":"10.1016/j.envsoft.2024.106310","url":null,"abstract":"<div><div>Increasingly frequent and severe floating macroalgal blooms present significant challenges to coastal and ocean environments. Here a short-term forecast system of floating macroalgal blooms was developed to predict the physical-biogeochemical environment and macroalgal ecodynamic processes in a regional ocean. Predictions of macroalgal ecodynamic processes are influenced by oceanic conditions (hydrodynamics, temperature, and nutrients), as well as atmospheric conditions (wind). The system's effectiveness is demonstrated by successfully hindcasting the June 2021 green tide bloom event in the Yellow Sea and using real-time satellite data to make reliable and robust continuous short-term predictions for 2022 and 2023. The prediction accuracy of coverage reaches 87.5%, and the minimum transport error of the green tide center of mass is 6.09 nautical miles over an 7-day prediction duration. Supported by regional marine physics and biogeochemistry and macroalgal physiological characteristic datasets, this system may serve as a crucial cornerstone for similar floating macroalgal disaster prevention.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106310"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901913","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106288
Samuele De Bartolo , Gaetano Napoli , Stefano Rizzello , Raffaele Vitolo
We describe the algorithms and the software that have been used in a new computational method based on the use of Master Equations. Our computer algebra procedures simulate the diffusion of a pollutant in river networks. The representation of river networks as trees makes the derivation of governing equations for pollutant transport an easy task. This includes mass balance equations that account for the sources, sinks, and transport of pollutants in the river network. In two previous papers we described the model and some simulations obtained from our software. In this paper we describe two software libraries, respectively for the Reduce and the Mathematica computer algebra systems, that have been developed on the basis of our model. The libraries can be found in our GitHub repository.
{"title":"Solving the Master Equation on river networks: A computer algebra approach","authors":"Samuele De Bartolo , Gaetano Napoli , Stefano Rizzello , Raffaele Vitolo","doi":"10.1016/j.envsoft.2024.106288","DOIUrl":"10.1016/j.envsoft.2024.106288","url":null,"abstract":"<div><div>We describe the algorithms and the software that have been used in a new computational method based on the use of Master Equations. Our computer algebra procedures simulate the diffusion of a pollutant in river networks. The representation of river networks as trees makes the derivation of governing equations for pollutant transport an easy task. This includes mass balance equations that account for the sources, sinks, and transport of pollutants in the river network. In two previous papers we described the model and some simulations obtained from our software. In this paper we describe two software libraries, respectively for the Reduce and the Mathematica computer algebra systems, that have been developed on the basis of our model. The libraries can be found in our <span>GitHub</span> repository.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106288"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874846","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 : 2025-02-01DOI: 10.1016/j.envsoft.2024.106289
Jin Qi , Wenting Lv , Junxia Zhu , Minyu Wang , Zhe Zhang , Guangyuan Zhang , Sensen Wu , Zhenhong Du
The spatiotemporal interpolation model is necessary for generating continuous distributions for spatiotemporally discrete sampling points. However, there remain challenges in spatiotemporal interpolation due to the complex spatiotemporal effect and the imprecise kernel functions. Here, we proposed a spatiotemporal autoregressive neural network interpolation model (STARNN) that incorporates adaptive spatiotemporal distance quantification and supervised learning. The 10-fold cross-validation modelling on sea surface temperature and coastal nutrients demonstrated that the STARNN model performs better than baseline models and can well depict reasonable spatiotemporal distributions for environmental factors. By proposing two stacked neural networks, the STARNN model can accurately integrate spatial and temporal distances and avoids subjective selection of the kernel function. This study developed a novel interpolation model for processing discrete spatiotemporal points by following the data-driven paradigm, which can offer decision support for simulating the spread of sea temperature anomalies and optimizing the distribution of water quality measurement stations.
{"title":"A spatiotemporal autoregressive neural network interpolation method for discrete environmental factors","authors":"Jin Qi , Wenting Lv , Junxia Zhu , Minyu Wang , Zhe Zhang , Guangyuan Zhang , Sensen Wu , Zhenhong Du","doi":"10.1016/j.envsoft.2024.106289","DOIUrl":"10.1016/j.envsoft.2024.106289","url":null,"abstract":"<div><div>The spatiotemporal interpolation model is necessary for generating continuous distributions for spatiotemporally discrete sampling points. However, there remain challenges in spatiotemporal interpolation due to the complex spatiotemporal effect and the imprecise kernel functions. Here, we proposed a spatiotemporal autoregressive neural network interpolation model (STARNN) that incorporates adaptive spatiotemporal distance quantification and supervised learning. The 10-fold cross-validation modelling on sea surface temperature and coastal nutrients demonstrated that the STARNN model performs better than baseline models and can well depict reasonable spatiotemporal distributions for environmental factors. By proposing two stacked neural networks, the STARNN model can accurately integrate spatial and temporal distances and avoids subjective selection of the kernel function. This study developed a novel interpolation model for processing discrete spatiotemporal points by following the data-driven paradigm, which can offer decision support for simulating the spread of sea temperature anomalies and optimizing the distribution of water quality measurement stations.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"185 ","pages":"Article 106289"},"PeriodicalIF":4.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797866","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}