Environmental Modelling & Software最新文献

{"title":"Ensemble deep learning towards high-resolution soil-moisture mapping for enhanced water management in California's Central Valley","authors":"Ali Azedou ,&nbsp;Aouatif Amine ,&nbsp;Said Lahssini ,&nbsp;Gordon Osterman ,&nbsp;Mauricio Arboleda-Zapata ,&nbsp;Michael Cosh ,&nbsp;Isaya Kisekka","doi":"10.1016/j.envsoft.2025.106824","DOIUrl":"10.1016/j.envsoft.2025.106824","url":null,"abstract":"<div><div>Soil moisture (SM) plays a vital role in both hydrological and agricultural processes and is critical for achieving groundwater sustainability in agriculture through demand management. NASA's Soil Moisture Active Passive (SMAP) satellite measures the SM across the Earth and provides data on both the surface and root zone SM but at a coarse spatial resolution of 9 km, thereby limiting detailed analyses. This study aimed to develop an optimized deep ensemble learning framework to downscale the resolution of SMAP observations of California's Central Valley from 9 km to 30 m for both the surface and root-zone SM. Sensitivity analysis was employed to identify key explanatory variables. The models were then combined into an ensemble DNN trained on multiscale SMAP data and validated against in-situ SM measurements. The results demonstrated that the ensemble model achieved the highest coefficients of determination (<span><math><mrow><msup><mi>R</mi><mn>2</mn></msup></mrow></math></span>) of 0.789 and 0.683 for surface and root-zone SM, respectively, with the lowest root mean square errors of 0.0281 and 0.0814 cm3/cm3, respectively, along with the highest NSE scores of 0.50 and 0.433, thereby reliably capturing spatial patterns and predictive accuracy. A sensitivity analysis identified precipitation, LST, topographic factors, land cover, and vegetation indices as key predictors for SSM, while organic matter, silt content, precipitation, and DEM were the most influential for RZSM. Seasonal analysis revealed distinct patterns linked to climate and management practices at a spatial resolution of 30 m, thereby capturing seasonal variations in soil moisture among major crops. Additionally, SM maps can be used to refine the estimated evapotranspiration resulting from applied irrigation water sourced from groundwater pumping, allowing for better monitoring of water use. SM can also be used to inform agronomic practices, such as delayed irrigation in early spring, which can reduce groundwater demand.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106824"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689339","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":"FloodTransformer: Efficient real-time high-resolution flood forecasting","authors":"Zhanzhong Gu ,&nbsp;Jiachen Kang ,&nbsp;Wenzheng Jin ,&nbsp;Feifei Tong ,&nbsp;Y. Jay Guo ,&nbsp;Wenjing Jia","doi":"10.1016/j.envsoft.2025.106832","DOIUrl":"10.1016/j.envsoft.2025.106832","url":null,"abstract":"<div><div>Flood forecasting is crucial for disaster planning and risk management, yet conventional hydrodynamic-based approaches are often slow in response and computationally intensive. We present a hybrid framework leveraging traditional hydrodynamic modelling with a novel AI model to enable accurate, real-time, and high-resolution flood prediction. To address the computational challenges of large-scale, dense flood prediction, we develop an efficient flood prediction model, <em>FloodTransformer</em>, which possesses three key novelties: variable-size cell embedding, tokenised time-sequence encoding, and physics-informed multi-task optimisation. These components effectively capture complex spatiotemporal dependencies, allowing accurate sequential predictions in a single run. Comprehensive evaluations on both simulated and historical flood events demonstrate FloodTransformer’s excellent accuracy and efficiency: NSE 0.9445, KGE 0.9759 for water-depth prediction, and IoU 0.8180, F1 0.8997 for inundation classification, outperforming all comparative models. With 3s inference enabling multiple horizons in one pass, FloodTransformer offers a robust and practical solution for operational flood risk management.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106832"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145732501","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":"What drives reservoir infrastructure upgrade decisions under deep uncertainty?","authors":"Jiajia Huang ,&nbsp;Wenyan Wu ,&nbsp;Holger R. Maier ,&nbsp;Justin Hughes ,&nbsp;Quan J. Wang ,&nbsp;Yuan Cao","doi":"10.1016/j.envsoft.2026.106862","DOIUrl":"10.1016/j.envsoft.2026.106862","url":null,"abstract":"<div><div>Huang et al. (2026) recently developed a comprehensive framework to jointly optimize reservoir operation policies and infrastructure upgrades under deep uncertainty. Building on this framework, this commentary provides several new, yet important, insights into reservoir planning and management under deep uncertainty. First, while the discount rate is frequently treated as a constant economic input, high discount rates may create a false sense of security by making delayed infrastructure upgrades economically preferable. In addition, initially undersized key infrastructure increases the risks of locking systems into long-term underperformance that subsequent infrastructure upgrades and operational adaptations cannot fully rectify. Furthermore, the presence or absence of key infrastructure within the system can reshape infrastructure upgrade priorities, highlighting the importance of having a clear system boundary at the planning stage. These new insights are essential for supporting credible and defensible infrastructure decisions in a climate-sensitive planning environment.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106862"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903154","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":"The transformative role of artificial intelligence in water resources engineering: A comprehensive review","authors":"Muhammad Rashid ,&nbsp;Adan Saeed ,&nbsp;Mohiq Khalid ,&nbsp;Aniqa Murtaza ,&nbsp;Muhammad Waqar Saleem","doi":"10.1016/j.envsoft.2026.106857","DOIUrl":"10.1016/j.envsoft.2026.106857","url":null,"abstract":"<div><div>Artificial intelligence (AI) is reshaping water resources engineering by tackling complex forecasting, control, and decision problems across the hydrologic cycle. This review synthesizes how core AI families, machine learning (supervised, unsupervised, reinforcement), deep learning (ANNs, CNNs, RNNs, Transformers), fuzzy logic, and hybrid schemes are used for streamflow and rainfall–runoff prediction, water-quality assessment, flood and drought risk, precision irrigation, urban water operations (demand, leakage, treatment), groundwater management, climate-impact analysis, and reservoir scheduling. Reported gains include higher predictive skill, operational efficiency, and cost savings that support more sustainable management. We also surface persistent constraints: sparse and noisy data, limited interpretability, deployment cost and skill barriers, and ethical concerns around bias, accountability, and privacy. Looking ahead, priorities include Explainable AI, resilient hybrid physics, ML models, tighter coupling with IoT and remote sensing, and principled strategies for data scarcity. We argue for rigorous, transparent, and interdisciplinary practice to realize AI's benefits while safeguarding water security and equity.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106857"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921053","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":"A generalized user-friendly method for fusing observational data and chemical transport model (Gen-Friberg V1.0: GF-1)","authors":"Zongrun Li ,&nbsp;Abiola S. Lawal ,&nbsp;Bingqing Zhang ,&nbsp;Kamal J. Maji ,&nbsp;Pengfei Liu ,&nbsp;Yongtao Hu ,&nbsp;Armistead G. Russell ,&nbsp;M. Talat Odman","doi":"10.1016/j.envsoft.2025.106827","DOIUrl":"10.1016/j.envsoft.2025.106827","url":null,"abstract":"<div><div>A generalized, user-friendly data fusion method (Gen-Friberg) to reduce differences between chemical transport models (CTMs) and observational data is implemented to be compatible with widely used CTMs such as CMAQ, GEOS-Chem, and WRF-Chem. Key source code improvements included encapsulating the data fusion algorithm within a single function and enabling parallel processing to minimize runtime for long simulations. We applied the data fusion method to CMAQ outputs and observations from 2010 to 2019 to evaluate the method's performance. After data fusion, pollutant concentration fields showed improved performance. Additionally, we assessed the generalizability of the data fusion method by demonstrating its effectiveness in reducing bias in the GEOS-Chem and WRF-Chem concentration fields using evaluations based on 2017 simulations. Comparisons across CMAQ, GEOS-Chem, and WRF-Chem with and without data fusion demonstrate that data fusion reduces inter-model discrepancies, yielding more consistent concentration fields for use in health and policy assessments.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106827"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689373","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":"A sub-seasonal to seasonal climate forecast informed irrigation scheduling tool for the Contiguous United States","authors":"Haiyang Shi ,&nbsp;Ximing Cai ,&nbsp;Xinchen Hu ,&nbsp;Alaa Jamal ,&nbsp;Donghui Li ,&nbsp;Chao Sun ,&nbsp;Xin-Zhong Liang","doi":"10.1016/j.envsoft.2025.106819","DOIUrl":"10.1016/j.envsoft.2025.106819","url":null,"abstract":"<div><div>Irrigation accounts for a significant share of global freshwater use, and optimizing scheduling is crucial for improving water use efficiency. Current methods rely on short-term weather forecasts, limiting long-term planning. Additionally, most models are site-specific due to data constraints, and lacking national applicability. This study develops a real-time irrigation scheduling tool for cornfields across the Contiguous United States (CONUS). By integrating sub-seasonal to seasonal (S2S) climate forecasts with the Soil Water Atmosphere Plant (SWAP) model, the tool optimizes irrigation scheduling at any day in the season, balancing water cost and crop yield. A human-computer interaction framework provides real-time irrigation recommendations while incorporating farmer feedback. S2S-informed scheduling improves water use efficiency and net profit compared to default SWAP schedules. Various up-to-date CONUS-scale datasets helped to reduce dependence on in-situ observations and extend the applicability of the tool to diverse field conditions in the CONUS.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106819"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689378","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":"Model support tools for Informed Decision Making - MIDAS and sensitivity analysis","authors":"Matthew Hardy,&nbsp;Elena Bastianon,&nbsp;d'Artis Kancs,&nbsp;Enrico Pisoni,&nbsp;Rossana Rosati","doi":"10.1016/j.envsoft.2026.106873","DOIUrl":"10.1016/j.envsoft.2026.106873","url":null,"abstract":"<div><div>Models play a key role in informing evidence-based policymaking, particularly in addressing complex societal-economic-environmental issues. By promoting informed decision-making and responsible use of models, the European Commission (EC) has developed tools and procedures for a trustworthy modelling workflow. Two complementary good modelling practice tools of the EC are presented, and their crucial role in enhancing modelling transparency is detailed. MIDAS – a publicly accessible meta-database that consolidates a standardised information on models and provides real-time information to modelling-supported EU legislative documents – ensures FAIR principles in model use. Uncertainty and Sensitivity Analysis methods allows us to identify and prioritise sources of uncertainty, and visualise how model uncertainties affect decision-making. To illustrate the role of sensitivity analysis for policymaking an application on the Screening for High Emission Reduction Potential on Air (SHERPA) model is presented. The SIML@B tool for global sensitivity analysis developed by European Commission has been employed.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106873"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956765","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":"Supervised learning-based water quality prediction and ecological risk factor mining across China’s 12 major river basins","authors":"Jishu Guo,&nbsp;Yimin Huang,&nbsp;Yun Zhang","doi":"10.1016/j.envsoft.2025.106840","DOIUrl":"10.1016/j.envsoft.2025.106840","url":null,"abstract":"<div><div>Surface water quality underpins ecosystem stability, regional security, and public health, yet capturing spatio-temporal heterogeneity from historical monitoring remains challenging. We propose a Spatio-Temporal Aware Neural Network (SANN) that couples high-order spatial structure learning with explicit temporal modeling to represent nonlinear interactions among 11 physicochemical variables across China’s 12 major river basins. Using 15,855 samples from the National Surface Water Monitoring Network, SANN is benchmarked against ten traditional, deep, and graph-based models, attaining a mean accuracy of 91.87%, an F1-score of 91.15%, and a precision of 91.32%, outperforming the state of the art water quality prediction model. Feature-importance analysis reveals distinct, time-varying regional drivers: total phosphorus dominates the eight eastern–southern basins, whereas the permanganate index prevails in the four western–northern basins. The framework clarifies spatio-temporal heterogeneity in water-quality controls and provides actionable guidance for basin-specific, time-aware pollution mitigation and ecological restoration. The source code is available at: <span><span>https://github.com/FengLiuii/SANN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106840"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785082","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":"Enhancing flood forecasting with deep learning: A scalable alternative to traditional hydrodynamic models","authors":"Weeraphat Duangkhwan ,&nbsp;Chaiwat Ekkawatpanit ,&nbsp;Chanchai Petpongpan ,&nbsp;Duangrudee Kositgittiwong ,&nbsp;So Kazama ,&nbsp;Yusuke Hiraga ,&nbsp;Chai Jaturapitakkul","doi":"10.1016/j.envsoft.2025.106841","DOIUrl":"10.1016/j.envsoft.2025.106841","url":null,"abstract":"<div><div>Flooding, intensified by climate change, necessitates advanced prediction models. Traditional hydrodynamic simulation, HEC-RAS 1D/2D is computationally intensive, limiting real-time flood forecasting. This study proposes an integrated deep learning framework to emulate HEC-RAS 1D/2D, significantly reducing computational demands. The framework comprises an LSTM for river water level prediction and a CNN for flood inundation mapping. To ensure physical consistency, the CNN learns the relationship between river water levels and flood inundation by mimicking overflow results of 1D/2D models. Training uses observed hydrological data and flood inundation maps from 1D/2D simulations. Results indicate the LSTM achieving good accuracy to predict water level. The CNN effectively translates water level predictions into flood depth maps, demonstrating close agreement with HEC-RAS outputs. Overall, the AI-based framework significantly accelerates flood simulations while maintaining high accuracy, making it a promising tool for real-time flood prediction and large-scale flood risk assessment.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106841"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785084","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":"Development of a River Dynamical Core for E3SM to simulate compound flooding on Exascale-class heterogeneous supercomputers","authors":"Gautam Bisht ,&nbsp;Donghui Xu ,&nbsp;Jeffrey Johnson ,&nbsp;Jed Brown ,&nbsp;Matthew Knepley ,&nbsp;Mark Adams ,&nbsp;Dongyu Feng ,&nbsp;Dalei Hao ,&nbsp;Darren Engwirda ,&nbsp;Mukesh Kumar ,&nbsp;Zeli Tan","doi":"10.1016/j.envsoft.2025.106804","DOIUrl":"10.1016/j.envsoft.2025.106804","url":null,"abstract":"<div><div>Physically-consistent quantification of flood risks in global models requires kilometer scale flood simulations using 2D physics schemes, both of which are unavailable in the current generation Earth System Models. In this work, we have developed the River Dynamical Core (RDycore), which is an open-source, 2D shallow water equation library for the Energy Exascale Earth System Model (E3SM). RDycore uses PETSc and libCEED libraries to run efficiently on CPUs and GPUs. RDycore was validated for analytical, manufactured, and a well-studied dam break problem. For a problem with 471 million grid cells, RDycore achieves a speedup of 6.6x and 7.6x on GPUs compared to CPUs on Perlmutter and Frontier supercomputers, respectively. The one-way E3SM-RDycore coupling is demonstrated by performing multiple 5-day flooding simulations during Hurricane Harvey driven by five precipitation datasets. The work presented here is the foundational step in providing hardware and algorithmic portability for simulating kilometer-scale river dynamics within E3SM.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"197 ","pages":"Article 106804"},"PeriodicalIF":4.6,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785089","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}