Pub Date : 2026-03-24DOI: 10.1016/j.envsoft.2026.106960
A. Lee, S. White, G.B. Pasternack, B. Lane
{"title":"RiverSTICH: Sewing Together 3D Rivers from Only a Few Loose Threads of Transect Data","authors":"A. Lee, S. White, G.B. Pasternack, B. Lane","doi":"10.1016/j.envsoft.2026.106960","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106960","url":null,"abstract":"","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"15 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147501687","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 : 2026-03-21DOI: 10.1016/j.envsoft.2026.106962
Matthias Schlögl, Laura Waltersdorfer, Peter Regner, Andrea Siposova, Alexander Brenning
{"title":"Overcoming barriers to reproducibility in geoscientific data analysis: Challenges and practical implementation strategies","authors":"Matthias Schlögl, Laura Waltersdorfer, Peter Regner, Andrea Siposova, Alexander Brenning","doi":"10.1016/j.envsoft.2026.106962","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106962","url":null,"abstract":"","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"16 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147495842","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 : 2026-03-17DOI: 10.1016/j.envsoft.2026.106945
Andrew Holmes, Hidemi Mitani Shen, Matt Jensen, Sarah Coffland, Logan Sizemore, Seth Bassetti, Brenna Nieva, Claudia Tebaldi, Abigail Snyder, Brian Hutchinson
The Global Change Analysis Model (GCAM) simulates the evolution of the coupled Earth-human system, but its complexity makes large ensemble studies for uncertainty exploration computationally expensive. We develop an efficient deep-learning emulator that approximates GCAM outputs. This allows us to estimate the model response across many more parameter settings than feasible with full model runs, enabling faster exploration and improved scenario discovery. The deep learning-based emulator is trained on an existing large ensemble with outputs spanning the water, land, and energy sectors. We evaluate performance across multiple training set sizes. Results show high predictive accuracy across 22,528 outputs, even when trained on substantially fewer samples than the original ensemble. This efficiency allows the design of large ensembles that more efficiently explore the GCAM input–output space. To our knowledge, this is the first successful multi-sector dynamic model emulator for scenario discovery, offering a simple, adaptable machine-learning approach for exploratory modeling studies.
{"title":"Emulating the Global Change Analysis Model with deep learning: An energy sector case study","authors":"Andrew Holmes, Hidemi Mitani Shen, Matt Jensen, Sarah Coffland, Logan Sizemore, Seth Bassetti, Brenna Nieva, Claudia Tebaldi, Abigail Snyder, Brian Hutchinson","doi":"10.1016/j.envsoft.2026.106945","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106945","url":null,"abstract":"The Global Change Analysis Model (GCAM) simulates the evolution of the coupled Earth-human system, but its complexity makes large ensemble studies for uncertainty exploration computationally expensive. We develop an efficient deep-learning emulator that approximates GCAM outputs. This allows us to estimate the model response across many more parameter settings than feasible with full model runs, enabling faster exploration and improved scenario discovery. The deep learning-based emulator is trained on an existing large ensemble with outputs spanning the water, land, and energy sectors. We evaluate performance across multiple training set sizes. Results show high predictive accuracy across 22,528 outputs, even when trained on substantially fewer samples than the original ensemble. This efficiency allows the design of large ensembles that more efficiently explore the GCAM input–output space. To our knowledge, this is the first successful multi-sector dynamic model emulator for scenario discovery, offering a simple, adaptable machine-learning approach for exploratory modeling studies.","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"5 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147464867","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 : 2026-03-16DOI: 10.1016/j.envsoft.2026.106961
Jingming Liu, Jianli Ding, Jinjie Wang, Zhe Zhang, Jie Zou, Zipeng Zhang, Xiao Wang, Zan Fu, Xiangyu Ge
This study investigated the Ebinur Lake Basin in arid inland China, focusing on the spatiotemporal dynamics of hydrogen and oxygen isotopes to elucidate water recharge mechanisms and transformation processes. A two-endmember mixing model was used to quantify the respective contributions of precipitation and snowmelt, while the SHAP (Shapley Additive Explanations) framework was employed to identify key environmental drivers. The results indicate that snowmelt account for an average of 58% of total surface and groundwater recharge, with the remaining 42% originating from precipitation. A progressive monthly decline in surface–groundwater exchange rates was observed, reflecting seasonal hydrological variations. Climate variability remains the primary control on basin-scale isotope dynamics, whereas LUCC and irrigation-related disturbance can impose strong sub-basin modulation. These findings provide a scientific foundation for sustainable water resource management in arid regions.
{"title":"A framework approach for analyzing water transformation characteristics of typical watersheds in arid zones during irrigation periods","authors":"Jingming Liu, Jianli Ding, Jinjie Wang, Zhe Zhang, Jie Zou, Zipeng Zhang, Xiao Wang, Zan Fu, Xiangyu Ge","doi":"10.1016/j.envsoft.2026.106961","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106961","url":null,"abstract":"This study investigated the Ebinur Lake Basin in arid inland China, focusing on the spatiotemporal dynamics of hydrogen and oxygen isotopes to elucidate water recharge mechanisms and transformation processes. A two-endmember mixing model was used to quantify the respective contributions of precipitation and snowmelt, while the SHAP (Shapley Additive Explanations) framework was employed to identify key environmental drivers. The results indicate that snowmelt account for an average of 58% of total surface and groundwater recharge, with the remaining 42% originating from precipitation. A progressive monthly decline in surface–groundwater exchange rates was observed, reflecting seasonal hydrological variations. Climate variability remains the primary control on basin-scale isotope dynamics, whereas LUCC and irrigation-related disturbance can impose strong sub-basin modulation. These findings provide a scientific foundation for sustainable water resource management in arid regions.","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"308 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147464926","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}
{"title":"Extended Hydrofabric: A Standardized Geospatial Database for Reproducible Water Management Modeling in the United States","authors":"Ehsan Ebrahimi, Pin Shuai, Sophia Bakar, Enrique Triana","doi":"10.1016/j.envsoft.2026.106955","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106955","url":null,"abstract":"","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"19 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147447813","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 : 2026-03-12DOI: 10.1016/j.envsoft.2026.106953
P.J. Navinkumar, RAAJ Ramsankaran
{"title":"AutoICE: An Automated Tool for Estimating Ice Thickness and Volume of Glaciers in Mountain Regions","authors":"P.J. Navinkumar, RAAJ Ramsankaran","doi":"10.1016/j.envsoft.2026.106953","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106953","url":null,"abstract":"","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"1 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147447815","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 : 2026-03-08DOI: 10.1016/j.envsoft.2026.106942
Thomas Keeble, Christopher Sean Lyell, Tim Gazzard, Thomas James Duff, Gary Sheridan
Dead fuel moisture content (DFMC) critically influences wildfire behaviour, and its modelling underpins many fire management decision support systems. Recent modelling advances have enabled accurate forecast of point-scale fuel moisture, but their reliance on continuous real-time sensor functionality creates operational vulnerabilities when sensors may fail. Maintaining sensor networks across large, remote domains is costly and unreliable. Therefore, we developed a spatially continuous DFMC forecast system that eliminates real-time sensor dependency by replacing sensor initialisation with remotely sensed and modelled proxies for landscape fuel moisture states. Using 23,354 site-day observations from 27 forested sites in Victoria, Australia, our machine learning model produces 7-day ahead sub-canopy DFMC forecasts with median RMSE of 11.5% and 12.8% for day 1 and 7. The approach delivers reliable spatial forecasts across forested landscapes without sensor-dependent vulnerabilities, representing a significant advancement in operational fire risk management by providing comprehensive coverage for wildfire suppression planning and prescribed burning.
{"title":"Untethered from earthly constraints: A spatial seven-day ahead machine-learning forest fuel moisture forecasting system, independent of real-time sensor networks","authors":"Thomas Keeble, Christopher Sean Lyell, Tim Gazzard, Thomas James Duff, Gary Sheridan","doi":"10.1016/j.envsoft.2026.106942","DOIUrl":"https://doi.org/10.1016/j.envsoft.2026.106942","url":null,"abstract":"Dead fuel moisture content (DFMC) critically influences wildfire behaviour, and its modelling underpins many fire management decision support systems. Recent modelling advances have enabled accurate forecast of point-scale fuel moisture, but their reliance on continuous real-time sensor functionality creates operational vulnerabilities when sensors may fail. Maintaining sensor networks across large, remote domains is costly and unreliable. Therefore, we developed a spatially continuous DFMC forecast system that eliminates real-time sensor dependency by replacing sensor initialisation with remotely sensed and modelled proxies for landscape fuel moisture states. Using 23,354 site-day observations from 27 forested sites in Victoria, Australia, our machine learning model produces 7-day ahead sub-canopy DFMC forecasts with median RMSE of 11.5% and 12.8% for day 1 and 7. The approach delivers reliable spatial forecasts across forested landscapes without sensor-dependent vulnerabilities, representing a significant advancement in operational fire risk management by providing comprehensive coverage for wildfire suppression planning and prescribed burning.","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"8 1","pages":""},"PeriodicalIF":4.9,"publicationDate":"2026-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147392386","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 : 2026-03-01Epub Date: 2026-01-27DOI: 10.1016/j.envsoft.2026.106897
Jorge Saavedra-Garrido , Jorge Arevalo , Luis De La Fuente , Aldo Tapia , Christopher Paredes-Arroyo , Ana Maria Cordova , Daira Velandia , Pablo Álvarez , Héctor Reyes-Serrano , Rodrigo Salas
Reliable short-term streamflow forecasting remains a key challenge due to data latency, uncertainty, and other real-world constraints. This study presents a regional Long Short-Term Memory (LSTM) model to predict daily mean and maximum streamflow across 340 points in Chile over a five-day horizon, explicitly accounting for operational limitations such as unavailable recent streamflow and delayed input data. Compared to locally trained models, the regional model demonstrates superior performance in temporal correlation and variance representation, with Kling–Gupta Efficiency (KGE) 0.6 at 156 points. Crucially, high-flow event prediction improves significantly: bias in the Fractional High-flow Volume (FHV) is reduced by 50% at the 90th percentile and 25% at the 99th percentile, demonstrating strong operational robustness with minimal degradation over the forecast horizon. These findings highlight the potential of regional deep learning models to offer scalable and resilient performance across diverse hydrological settings, supporting flood preparedness and water management.
{"title":"Regional vs local LSTM models for short-term streamflow forecasting under operational constraints","authors":"Jorge Saavedra-Garrido , Jorge Arevalo , Luis De La Fuente , Aldo Tapia , Christopher Paredes-Arroyo , Ana Maria Cordova , Daira Velandia , Pablo Álvarez , Héctor Reyes-Serrano , Rodrigo Salas","doi":"10.1016/j.envsoft.2026.106897","DOIUrl":"10.1016/j.envsoft.2026.106897","url":null,"abstract":"<div><div>Reliable short-term streamflow forecasting remains a key challenge due to data latency, uncertainty, and other real-world constraints. This study presents a regional Long Short-Term Memory (LSTM) model to predict daily mean and maximum streamflow across 340 points in Chile over a five-day horizon, explicitly accounting for operational limitations such as unavailable recent streamflow and delayed input data. Compared to locally trained models, the regional model demonstrates superior performance in temporal correlation and variance representation, with Kling–Gupta Efficiency (KGE) <span><math><mo>≥</mo></math></span> 0.6 at 156 points. Crucially, high-flow event prediction improves significantly: bias in the Fractional High-flow Volume (FHV) is reduced by <span><math><mo>∼</mo></math></span>50% at the 90th percentile and <span><math><mo>∼</mo></math></span>25% at the 99th percentile, demonstrating strong operational robustness with minimal degradation over the forecast horizon. These findings highlight the potential of regional deep learning models to offer scalable and resilient performance across diverse hydrological settings, supporting flood preparedness and water management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"198 ","pages":"Article 106897"},"PeriodicalIF":4.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146072501","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 : 2026-03-01Epub Date: 2026-02-12DOI: 10.1016/j.envsoft.2026.106905
Haoran Xing, Ying Li, Dashe Li, Huanhai Yang
Accurate prediction of dissolved oxygen (DO) is crucial for intelligent decision-making in aquaculture. However, achieving this goal is challenging due to nonstationarity, multi-period aliasing, and local phase shifts inherent in DO series. We propose the Multi-scale Adaptive transformer (MAformer) for water quality prediction. First, the hierarchical adaptive smoothing decomposer stabilizes long-term patterns while preserving short-term details. Second, a multi-period phase-aligned attention module achieves cross-period synchronization. Third, the phase-shift correction attention module enhances robustness to short-term disturbances. Experiments on six marine ranching datasets from diverse geographical and climatic regions demonstrate that MAformer significantly outperforms seven state-of-the-art baseline models. For instance, it achieves an average reduction of 9.59% in MAE and 7.96% in RMSE, alongside improvements of 8.39% in and 6.25% in KGE. These results confirm MAformer’s superior capability as a reliable and generalizable tool for intelligent aquaculture management.
{"title":"MAformer: A multivariate prediction framework with adaptive multi-scale decomposition and phase correction for water quality in aquaculture environments","authors":"Haoran Xing, Ying Li, Dashe Li, Huanhai Yang","doi":"10.1016/j.envsoft.2026.106905","DOIUrl":"10.1016/j.envsoft.2026.106905","url":null,"abstract":"<div><div>Accurate prediction of dissolved oxygen (DO) is crucial for intelligent decision-making in aquaculture. However, achieving this goal is challenging due to nonstationarity, multi-period aliasing, and local phase shifts inherent in DO series. We propose the Multi-scale Adaptive transformer (MAformer) for water quality prediction. First, the hierarchical adaptive smoothing decomposer stabilizes long-term patterns while preserving short-term details. Second, a multi-period phase-aligned attention module achieves cross-period synchronization. Third, the phase-shift correction attention module enhances robustness to short-term disturbances. Experiments on six marine ranching datasets from diverse geographical and climatic regions demonstrate that MAformer significantly outperforms seven state-of-the-art baseline models. For instance, it achieves an average reduction of 9.59% in MAE and 7.96% in RMSE, alongside improvements of 8.39% in <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> and 6.25% in KGE. These results confirm MAformer’s superior capability as a reliable and generalizable tool for intelligent aquaculture management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"198 ","pages":"Article 106905"},"PeriodicalIF":4.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146209274","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：